Add files using upload-large-folder tool

README.md

@@ -0,0 +1,180 @@
+---
+base_model:
+- Qwen/Qwen2.5-32B-Instruct
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge2
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  # First 8 layers: No replication
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [0, 8]
+
+  # Next 8 layers: Replicate 2 layers
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [8, 9]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [8, 9]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [9, 13]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [13, 14]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [13, 14]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [14, 16]
+
+  # Next 8 layers: Replicate 4 layers
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [16, 18]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [17, 19]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [18, 20]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [19, 21]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [20, 22]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [21, 23]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [22, 24]
+
+  # Next 8 layers: Replicate all 8 layers
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [24, 25]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [24, 26]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [25, 27]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [26, 28]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [27, 29]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [28, 30]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [29, 31]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [30, 32]
+
+  # Middle 8 layers: Replicate all 8 layers
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [32, 33]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [32, 34]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [33, 35]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [34, 36]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [35, 37]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [36, 38]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [37, 39]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [38, 40]
+
+  # Next 8 layers: Replicate 4 layers
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [40, 42]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [41, 43]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [42, 44]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [43, 45]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [44, 46]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [45, 47]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [46, 48]
+
+  # Next 8 layers: Replicate 2 layers
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [48, 49]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [48, 49]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [49, 53]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [53, 54]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [53, 54]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [54, 56]
+
+  # Last 8 layers: No replication
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [56, 64]
+
+merge_method: passthrough
+dtype: bfloat16
+```

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-32B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 94,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

mergekit_config.yml

@@ -0,0 +1,151 @@
+slices:
+  # First 8 layers: No replication
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [0, 8]
+
+  # Next 8 layers: Replicate 2 layers
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [8, 9]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [8, 9]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [9, 13]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [13, 14]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [13, 14]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [14, 16]
+
+  # Next 8 layers: Replicate 4 layers
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [16, 18]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [17, 19]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [18, 20]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [19, 21]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [20, 22]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [21, 23]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [22, 24]
+
+  # Next 8 layers: Replicate all 8 layers
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [24, 25]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [24, 26]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [25, 27]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [26, 28]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [27, 29]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [28, 30]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [29, 31]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [30, 32]
+
+  # Middle 8 layers: Replicate all 8 layers
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [32, 33]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [32, 34]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [33, 35]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [34, 36]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [35, 37]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [36, 38]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [37, 39]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [38, 40]
+
+  # Next 8 layers: Replicate 4 layers
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [40, 42]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [41, 43]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [42, 44]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [43, 45]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [44, 46]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [45, 47]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [46, 48]
+
+  # Next 8 layers: Replicate 2 layers
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [48, 49]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [48, 49]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [49, 53]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [53, 54]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [53, 54]
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [54, 56]
+
+  # Last 8 layers: No replication
+  - sources:
+    - model: Qwen/Qwen2.5-32B-Instruct
+      layer_range: [56, 64]
+
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74deab43bf4d1d06a666360a704fcc6b809e1775b866cb8f5c711aa57f285128
+size 4949338472

model-00002-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf92992b3517486901f4ae06f5cc92958f4cbb8d3fb3e4755cdeacfda1c06637
+size 4991425976

model-00003-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae94f7b1fef69b027524c80d9bc36080ac28e955c31c4aa34ef28ee557e0c989
+size 4876069760

model-00004-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d001e1f79ef3f73c2a907bacb9c8cff5a748d9e571b36094a500ea2f5f483e0
+size 4876059392

model-00005-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6c7cbe5c72f0a7208bd66a6ff00af8e1413024ce671e068779f1cffc25dfa84
+size 4750194440

model-00006-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63bc69d5324cb2ae5b84288bcc23bd764090d80be3a26cd31ad1fa0e0704e3ec
+size 4876059408

model-00007-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aff406d552ffcde96ad782cd175ff419e5d707ec387e6a104e5a87cc6421d8af
+size 4991417800

model-00008-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db6d9a591103d81d0b53ce8a8897e3defc89b00c8b30fef8d3b28649332ea2e0
+size 4886565968

model-00009-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9c995cf6bbb15a1e43a02847681b93b3c477eb152d6c842d5fe2229c9732801
+size 4876059416

model-00010-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4e04420f313a1e230af015c8995a34c7c3d3ecf56ca9589ad4ae176a602f216
+size 4750194440

model-00011-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57fe6afa033ad45bc256a3d3b614c6a0779143402405d96d5a45cbb148aeb0ec
+size 4991417800

model-00012-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63008fc5cbc0a945d844583d5aee8ca3e075ca1c973d3518e116afb7f11d1063
+size 4886565968

model-00013-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f7bd27072de16b2bf23bfc058977ed4da94295819aba4e145441da46350900
+size 4750194440

model-00014-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac40b878ae1ebf24e657369baf23c49c342309713df75aff5a45077f053818df
+size 4991417800

model-00015-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8782bbc5c3234709116731ff285413c9be8304041af42114f835b2dde0fbf2f1
+size 4886555632

model-00016-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1be1a4b9367a33d942dc86357dcde61657a3722671c0c99e54310168d9b06aa9
+size 4876069744

model-00017-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76d977feb170f33a29b81a55dbf00779d206aa82db9a73823370be8e2e3a19a
+size 4876049064

model-00018-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd934cb0f89f8b090ed99baea7b3b7e602122ffd59a9640cf7de973b3ce9e373
+size 4876059392

model-00019-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a423b07767072b25461e73bf97dfa6dd84bc13ee3d201237d940b690b77b555a
+size 4750204760

model-00020-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:540bec2b4c1ea3a5a31b6e85533823fcca4b2df0cea9aaa9351fbf3ea66ea316
+size 2076278344

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 94784067584}, "weight_map": {"lm_head.weight": "model-00001-of-00020.safetensors", "model.embed_tokens.weight": "model-00001-of-00020.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00020.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00020.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00020.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00020.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00020.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00020.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00020.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00020.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00020.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00020.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00020.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00020.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00020.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00020.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00020.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00020.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00020.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00020.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00020.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00020.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00020.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00020.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00020.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00020.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00020.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00020.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00020.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00020.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00020.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00020.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00020.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00020.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00020.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00020.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00020.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00020.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00020.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00020.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00020.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00020.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00020.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00020.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00020.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00020.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00020.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00020.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00020.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00020.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00020.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00020.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00020.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00020.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00020.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00020.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00020.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00020.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00020.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00020.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00020.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00020.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00020.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00020.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00020.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00020.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00020.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00020.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00020.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00020.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00020.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00020.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00020.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00020.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00020.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00020.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00020.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00020.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00020.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00020.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00020.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00020.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00004-of-00020.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00004-of-00020.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00004-of-00020.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00004-of-00020.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00004-of-00020.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00004-of-00020.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00020.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00020.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00020.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00020.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00020.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00020.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00020.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00020.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00020.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00020.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00020.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00020.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00020.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00020.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00020.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00004-of-00020.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00020.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00020.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00004-of-00020.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00020.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00004-of-00020.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00020.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00020.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00020.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00020.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00020.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00020.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00020.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00005-of-00020.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00005-of-00020.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00020.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00020.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00005-of-00020.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00005-of-00020.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00005-of-00020.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00005-of-00020.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00020.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00020.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00020.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00020.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00020.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00020.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00005-of-00020.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00005-of-00020.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00020.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00020.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00020.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00005-of-00020.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00005-of-00020.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00020.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00005-of-00020.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00005-of-00020.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00020.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00005-of-00020.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00020.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00020.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00020.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00020.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00020.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00006-of-00020.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00006-of-00020.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00020.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00020.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00006-of-00020.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00006-of-00020.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00020.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00020.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00006-of-00020.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00006-of-00020.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00020.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00020.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00020.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00020.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00020.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00006-of-00020.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00020.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00006-of-00020.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00020.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00006-of-00020.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00020.safetensors", "model.layers.33.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00006-of-00020.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00006-of-00020.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00020.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00020.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00006-of-00020.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00006-of-00020.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00006-of-00020.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00006-of-00020.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00020.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00020.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00020.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00006-of-00020.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00006-of-00020.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00020.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00020.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00006-of-00020.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00006-of-00020.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00020.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00020.safetensors", "model.layers.35.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.34.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00006-of-00020.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00006-of-00020.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00020.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00020.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00007-of-00020.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00007-of-00020.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00007-of-00020.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00007-of-00020.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00007-of-00020.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00007-of-00020.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00007-of-00020.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00007-of-00020.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.37.input_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.36.input_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00007-of-00020.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00007-of-00020.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00020.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00020.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00007-of-00020.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00007-of-00020.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00007-of-00020.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00007-of-00020.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00007-of-00020.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00007-of-00020.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00007-of-00020.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00007-of-00020.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.39.input_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.38.input_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00007-of-00020.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00007-of-00020.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00020.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00020.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00007-of-00020.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00007-of-00020.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00007-of-00020.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00007-of-00020.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00020.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00020.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00007-of-00020.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00007-of-00020.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00020.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00007-of-00020.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00007-of-00020.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00020.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.41.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.40.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00008-of-00020.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00008-of-00020.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00020.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00020.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00008-of-00020.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00008-of-00020.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00008-of-00020.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00008-of-00020.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00020.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00020.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00008-of-00020.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00008-of-00020.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00008-of-00020.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00008-of-00020.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.43.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.42.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00008-of-00020.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00008-of-00020.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00008-of-00020.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00008-of-00020.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00008-of-00020.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00008-of-00020.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00008-of-00020.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00008-of-00020.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00020.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00020.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00008-of-00020.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00008-of-00020.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00008-of-00020.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00008-of-00020.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.3.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00008-of-00020.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00008-of-00020.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00008-of-00020.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00008-of-00020.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00008-of-00020.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00008-of-00020.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00008-of-00020.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00008-of-00020.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00008-of-00020.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00008-of-00020.safetensors", "model.layers.45.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.44.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00009-of-00020.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00009-of-00020.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00020.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00009-of-00020.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00009-of-00020.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00009-of-00020.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00009-of-00020.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00009-of-00020.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00020.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00020.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00009-of-00020.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00020.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00009-of-00020.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00009-of-00020.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00009-of-00020.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00020.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00009-of-00020.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00009-of-00020.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00009-of-00020.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00020.safetensors", "model.layers.46.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00009-of-00020.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00020.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00009-of-00020.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00009-of-00020.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00020.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00020.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00009-of-00020.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00020.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00009-of-00020.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00020.safetensors", "model.layers.48.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.47.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00009-of-00020.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00009-of-00020.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00009-of-00020.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00009-of-00020.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00009-of-00020.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00009-of-00020.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00009-of-00020.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00009-of-00020.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00009-of-00020.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00009-of-00020.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00009-of-00020.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00009-of-00020.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00009-of-00020.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00009-of-00020.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00009-of-00020.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00009-of-00020.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00009-of-00020.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00009-of-00020.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00009-of-00020.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00009-of-00020.safetensors", "model.layers.50.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.49.input_layernorm.weight": "model-00009-of-00020.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00010-of-00020.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00010-of-00020.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00010-of-00020.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00010-of-00020.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00010-of-00020.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00010-of-00020.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00010-of-00020.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00010-of-00020.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00010-of-00020.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00010-of-00020.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00010-of-00020.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00010-of-00020.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00010-of-00020.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00010-of-00020.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00010-of-00020.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00010-of-00020.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00010-of-00020.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00010-of-00020.safetensors", "model.layers.52.input_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.51.input_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00010-of-00020.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00010-of-00020.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00010-of-00020.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00010-of-00020.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00010-of-00020.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00010-of-00020.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00010-of-00020.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00010-of-00020.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00010-of-00020.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00010-of-00020.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00010-of-00020.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00010-of-00020.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00010-of-00020.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00010-of-00020.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00010-of-00020.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00010-of-00020.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00010-of-00020.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00010-of-00020.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00010-of-00020.safetensors", "model.layers.54.input_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.53.input_layernorm.weight": "model-00010-of-00020.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00010-of-00020.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00010-of-00020.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00010-of-00020.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00020.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00011-of-00020.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00011-of-00020.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00011-of-00020.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00020.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00011-of-00020.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00020.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00011-of-00020.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00020.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.56.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.55.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00011-of-00020.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00011-of-00020.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00011-of-00020.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00011-of-00020.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00011-of-00020.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00011-of-00020.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00011-of-00020.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00011-of-00020.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00011-of-00020.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00011-of-00020.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00011-of-00020.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00011-of-00020.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.58.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.57.input_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00011-of-00020.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00011-of-00020.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00011-of-00020.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00011-of-00020.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00011-of-00020.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00011-of-00020.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00011-of-00020.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00011-of-00020.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00011-of-00020.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00011-of-00020.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00011-of-00020.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00011-of-00020.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00011-of-00020.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00011-of-00020.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00011-of-00020.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00011-of-00020.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.60.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.59.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00012-of-00020.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00012-of-00020.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00012-of-00020.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00012-of-00020.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00012-of-00020.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00012-of-00020.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00012-of-00020.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00012-of-00020.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00012-of-00020.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00012-of-00020.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00012-of-00020.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00012-of-00020.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.61.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00012-of-00020.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00012-of-00020.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00012-of-00020.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00012-of-00020.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00012-of-00020.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00012-of-00020.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.4.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00012-of-00020.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00012-of-00020.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00012-of-00020.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00012-of-00020.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00012-of-00020.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00012-of-00020.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.62.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00012-of-00020.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00012-of-00020.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00012-of-00020.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00012-of-00020.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00012-of-00020.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00012-of-00020.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00012-of-00020.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00012-of-00020.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00012-of-00020.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00012-of-00020.safetensors", "model.layers.64.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.63.input_layernorm.weight": "model-00012-of-00020.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00013-of-00020.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00013-of-00020.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00013-of-00020.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00020.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00013-of-00020.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00013-of-00020.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00013-of-00020.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00020.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00013-of-00020.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00020.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00013-of-00020.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00020.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.66.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.65.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00013-of-00020.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00013-of-00020.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00013-of-00020.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00013-of-00020.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00013-of-00020.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00013-of-00020.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00013-of-00020.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00013-of-00020.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00013-of-00020.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00013-of-00020.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00013-of-00020.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00013-of-00020.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00013-of-00020.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00013-of-00020.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00013-of-00020.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00013-of-00020.safetensors", "model.layers.68.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.67.input_layernorm.weight": "model-00013-of-00020.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00013-of-00020.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00013-of-00020.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00013-of-00020.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00014-of-00020.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00014-of-00020.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00014-of-00020.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00014-of-00020.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00014-of-00020.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00014-of-00020.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00014-of-00020.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00014-of-00020.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00014-of-00020.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00014-of-00020.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00014-of-00020.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00014-of-00020.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00014-of-00020.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00014-of-00020.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00014-of-00020.safetensors", "model.layers.70.input_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.69.input_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00014-of-00020.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00014-of-00020.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00014-of-00020.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00014-of-00020.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00014-of-00020.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00014-of-00020.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.70.self_attn.k_proj.bias": "model-00014-of-00020.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00014-of-00020.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00014-of-00020.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00014-of-00020.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.70.self_attn.q_proj.bias": "model-00014-of-00020.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00014-of-00020.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00014-of-00020.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00014-of-00020.safetensors", "model.layers.70.self_attn.v_proj.bias": "model-00014-of-00020.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00014-of-00020.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00014-of-00020.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00014-of-00020.safetensors", "model.layers.72.input_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.71.input_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00014-of-00020.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00014-of-00020.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00014-of-00020.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00014-of-00020.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00014-of-00020.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00014-of-00020.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", "model.layers.72.self_attn.k_proj.bias": "model-00014-of-00020.safetensors", "model.layers.71.self_attn.k_proj.bias": "model-00014-of-00020.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00014-of-00020.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00014-of-00020.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00014-of-00020.safetensors", "model.layers.72.self_attn.q_proj.bias": "model-00014-of-00020.safetensors", "model.layers.71.self_attn.q_proj.bias": "model-00014-of-00020.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00014-of-00020.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00014-of-00020.safetensors", "model.layers.72.self_attn.v_proj.bias": "model-00014-of-00020.safetensors", "model.layers.71.self_attn.v_proj.bias": "model-00014-of-00020.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00014-of-00020.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.74.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.73.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00015-of-00020.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00015-of-00020.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00015-of-00020.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00015-of-00020.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00015-of-00020.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00015-of-00020.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.74.self_attn.k_proj.bias": "model-00015-of-00020.safetensors", "model.layers.73.self_attn.k_proj.bias": "model-00015-of-00020.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.74.self_attn.q_proj.bias": "model-00015-of-00020.safetensors", "model.layers.73.self_attn.q_proj.bias": "model-00015-of-00020.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.74.self_attn.v_proj.bias": "model-00015-of-00020.safetensors", "model.layers.73.self_attn.v_proj.bias": "model-00015-of-00020.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.75.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00015-of-00020.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00015-of-00020.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00015-of-00020.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.75.self_attn.k_proj.bias": "model-00015-of-00020.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.75.self_attn.q_proj.bias": "model-00015-of-00020.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.75.self_attn.v_proj.bias": "model-00015-of-00020.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.77.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.76.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00015-of-00020.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00015-of-00020.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00015-of-00020.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00015-of-00020.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00015-of-00020.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00015-of-00020.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.77.self_attn.k_proj.bias": "model-00015-of-00020.safetensors", "model.layers.76.self_attn.k_proj.bias": "model-00015-of-00020.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00015-of-00020.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00015-of-00020.safetensors", "model.layers.77.self_attn.q_proj.bias": "model-00015-of-00020.safetensors", "model.layers.76.self_attn.q_proj.bias": "model-00015-of-00020.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00015-of-00020.safetensors", "model.layers.77.self_attn.v_proj.bias": "model-00015-of-00020.safetensors", "model.layers.76.self_attn.v_proj.bias": "model-00015-of-00020.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00015-of-00020.safetensors", "model.layers.78.input_layernorm.weight": "model-00015-of-00020.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00016-of-00020.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00016-of-00020.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00016-of-00020.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.78.self_attn.k_proj.bias": "model-00016-of-00020.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00016-of-00020.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00016-of-00020.safetensors", "model.layers.78.self_attn.q_proj.bias": "model-00016-of-00020.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00016-of-00020.safetensors", "model.layers.78.self_attn.v_proj.bias": "model-00016-of-00020.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00016-of-00020.safetensors", "model.layers.5.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00016-of-00020.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00016-of-00020.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00016-of-00020.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00016-of-00020.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00016-of-00020.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00016-of-00020.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00016-of-00020.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00016-of-00020.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00016-of-00020.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00016-of-00020.safetensors", "model.layers.79.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00016-of-00020.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00016-of-00020.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00016-of-00020.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.79.self_attn.k_proj.bias": "model-00016-of-00020.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00016-of-00020.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00016-of-00020.safetensors", "model.layers.79.self_attn.q_proj.bias": "model-00016-of-00020.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00016-of-00020.safetensors", "model.layers.79.self_attn.v_proj.bias": "model-00016-of-00020.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00016-of-00020.safetensors", "model.layers.80.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00016-of-00020.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00016-of-00020.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00016-of-00020.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.80.self_attn.k_proj.bias": "model-00016-of-00020.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00016-of-00020.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00016-of-00020.safetensors", "model.layers.80.self_attn.q_proj.bias": "model-00016-of-00020.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00016-of-00020.safetensors", "model.layers.80.self_attn.v_proj.bias": "model-00016-of-00020.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00016-of-00020.safetensors", "model.layers.81.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00016-of-00020.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00016-of-00020.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00016-of-00020.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.81.self_attn.k_proj.bias": "model-00016-of-00020.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00016-of-00020.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00016-of-00020.safetensors", "model.layers.81.self_attn.q_proj.bias": "model-00016-of-00020.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00016-of-00020.safetensors", "model.layers.81.self_attn.v_proj.bias": "model-00016-of-00020.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00016-of-00020.safetensors", "model.layers.83.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.82.input_layernorm.weight": "model-00016-of-00020.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00017-of-00020.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00017-of-00020.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00017-of-00020.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00017-of-00020.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00017-of-00020.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00017-of-00020.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.83.self_attn.k_proj.bias": "model-00017-of-00020.safetensors", "model.layers.82.self_attn.k_proj.bias": "model-00017-of-00020.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00017-of-00020.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00017-of-00020.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00017-of-00020.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00017-of-00020.safetensors", "model.layers.83.self_attn.q_proj.bias": "model-00017-of-00020.safetensors", "model.layers.82.self_attn.q_proj.bias": "model-00017-of-00020.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00017-of-00020.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00017-of-00020.safetensors", "model.layers.83.self_attn.v_proj.bias": "model-00017-of-00020.safetensors", "model.layers.82.self_attn.v_proj.bias": "model-00017-of-00020.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00017-of-00020.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00017-of-00020.safetensors", "model.layers.84.input_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00017-of-00020.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00017-of-00020.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00017-of-00020.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.84.self_attn.k_proj.bias": "model-00017-of-00020.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00017-of-00020.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00017-of-00020.safetensors", "model.layers.84.self_attn.q_proj.bias": "model-00017-of-00020.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00017-of-00020.safetensors", "model.layers.84.self_attn.v_proj.bias": "model-00017-of-00020.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00017-of-00020.safetensors", "model.layers.85.input_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00017-of-00020.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00017-of-00020.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00017-of-00020.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.85.self_attn.k_proj.bias": "model-00017-of-00020.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00017-of-00020.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00017-of-00020.safetensors", "model.layers.85.self_attn.q_proj.bias": "model-00017-of-00020.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00017-of-00020.safetensors", "model.layers.85.self_attn.v_proj.bias": "model-00017-of-00020.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00017-of-00020.safetensors", "model.layers.86.input_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00017-of-00020.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00017-of-00020.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00017-of-00020.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.86.self_attn.k_proj.bias": "model-00017-of-00020.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00017-of-00020.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00017-of-00020.safetensors", "model.layers.86.self_attn.q_proj.bias": "model-00017-of-00020.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00017-of-00020.safetensors", "model.layers.86.self_attn.v_proj.bias": "model-00017-of-00020.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00017-of-00020.safetensors", "model.layers.87.input_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00018-of-00020.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00018-of-00020.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00018-of-00020.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.87.self_attn.k_proj.bias": "model-00018-of-00020.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.87.self_attn.q_proj.bias": "model-00018-of-00020.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.87.self_attn.v_proj.bias": "model-00018-of-00020.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.88.input_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00018-of-00020.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00018-of-00020.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00018-of-00020.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.88.self_attn.k_proj.bias": "model-00018-of-00020.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.88.self_attn.q_proj.bias": "model-00018-of-00020.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.88.self_attn.v_proj.bias": "model-00018-of-00020.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.89.input_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00018-of-00020.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00018-of-00020.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00018-of-00020.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.89.self_attn.k_proj.bias": "model-00018-of-00020.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.89.self_attn.q_proj.bias": "model-00018-of-00020.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.89.self_attn.v_proj.bias": "model-00018-of-00020.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.6.input_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00018-of-00020.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00018-of-00020.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00018-of-00020.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00018-of-00020.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00018-of-00020.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00018-of-00020.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.90.input_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00018-of-00020.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00018-of-00020.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00018-of-00020.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.90.self_attn.k_proj.bias": "model-00018-of-00020.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.90.self_attn.q_proj.bias": "model-00018-of-00020.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.90.self_attn.v_proj.bias": "model-00018-of-00020.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.91.input_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00019-of-00020.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00019-of-00020.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00019-of-00020.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.91.self_attn.k_proj.bias": "model-00019-of-00020.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.91.self_attn.q_proj.bias": "model-00019-of-00020.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.91.self_attn.v_proj.bias": "model-00019-of-00020.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.92.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00019-of-00020.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00019-of-00020.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00019-of-00020.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.92.self_attn.k_proj.bias": "model-00019-of-00020.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.92.self_attn.q_proj.bias": "model-00019-of-00020.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.92.self_attn.v_proj.bias": "model-00019-of-00020.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.93.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00019-of-00020.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00019-of-00020.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00019-of-00020.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.93.self_attn.k_proj.bias": "model-00019-of-00020.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.93.self_attn.q_proj.bias": "model-00019-of-00020.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.93.self_attn.v_proj.bias": "model-00019-of-00020.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.9.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.8.input_layernorm.weight": "model-00019-of-00020.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00019-of-00020.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00020-of-00020.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00020-of-00020.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00020-of-00020.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00020-of-00020.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.10.input_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00020-of-00020.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00020-of-00020.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00020-of-00020.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00020-of-00020.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00020-of-00020.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00020-of-00020.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.norm.weight": "model-00020-of-00020.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}