Upload folder using huggingface_hub

README.md

@@ -0,0 +1,39 @@
+---
+base_model:
+- unsloth/Mistral-Nemo-Instruct-2407
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+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:
+* [unsloth/Mistral-Nemo-Instruct-2407](https://huggingface.co/unsloth/Mistral-Nemo-Instruct-2407)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - model: unsloth/Mistral-Nemo-Instruct-2407
+        layer_range: [0, 16]
+  - sources:
+      - model: unsloth/Mistral-Nemo-Instruct-2407
+        layer_range: [0, 16]
+merge_method: passthrough
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "unsloth/Mistral-Nemo-Instruct-2407",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,9 @@
+slices:
+  - sources:
+      - model: unsloth/Mistral-Nemo-Instruct-2407
+        layer_range: [0, 16]
+  - sources:
+      - model: unsloth/Mistral-Nemo-Instruct-2407
+        layer_range: [0, 16]
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:060ee6ca35d686f5e0dfefaf89669f860552587b4402e71fc450061844fbc579
+size 1887481256

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acc55dd8a5454e0fad9d8628382d115a4366cf62346a1001a7f8222d65635e8d
+size 1887522664

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:939c1e36e9f49e66164dbf1a2039cf50feb46409e5b423c5ef7b8c30d0baffac
+size 1971387360

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a80341040bd5fe5e8c52e410036ce6601a7741b94f9743f3560de695b378df58
+size 1300298928

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f3185c25e3216fd95471bb4a5c1da5a51ca4500b89e4b78f2eddddcd2a12146
+size 1992295832

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f992d2ec19977dd484941a43730d648e4b5d8dc96182487fe2d7aa0ff3bddadb
+size 1992359592

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab749063820fdc47ce369434c479c323bce16b9b3376419e6b77ac4d0a603cc2
+size 1866529752

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df8d69edaa13f892b8241ee20c767fac1b646a0f1163319f3a942b6307b8c0e1
+size 1887522688

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d38faa32ca8d94b8bb4c272590bd34bfb61f60bd457e444310e164895070ccff
+size 1887522672

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9a70843a42a044e096eb7a38432839865686f54db1dd33611dd2ff0421cfdb
+size 1971408048

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a497d5271f3977862140c80bc6be8558face467c48d545e6e3ae817606453f6c
+size 1489029920

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 20133324800}, "weight_map": {"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.embed_tokens.weight": "model-00005-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00011-of-00011.safetensors", "lm_head.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}