Upload folder using huggingface_hub

README.md

@@ -0,0 +1,70 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- zhengr/MixTAO-7Bx2-MoE-v8.1
+base_model:
+- zhengr/MixTAO-7Bx2-MoE-v8.1
+- zhengr/MixTAO-7Bx2-MoE-v8.1
+- zhengr/MixTAO-7Bx2-MoE-v8.1
+- zhengr/MixTAO-7Bx2-MoE-v8.1
+- zhengr/MixTAO-7Bx2-MoE-v8.1
+---
+
+# TaoPassthrough-15B-s
+
+TaoPassthrough-15B-s is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [zhengr/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1)
+* [zhengr/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1)
+* [zhengr/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1)
+* [zhengr/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1)
+* [zhengr/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1)
+
+## 🧩 Configuration
+
+```yaml
+dtype: float16
+merge_method: passthrough
+slices:
+  - sources:
+    - model: zhengr/MixTAO-7Bx2-MoE-v8.1
+      layer_range: [0,9]
+  - sources:
+    - model: zhengr/MixTAO-7Bx2-MoE-v8.1
+      layer_range: [5,14]
+  - sources:
+    - model: zhengr/MixTAO-7Bx2-MoE-v8.1
+      layer_range: [10,19]
+  - sources:
+    - model: zhengr/MixTAO-7Bx2-MoE-v8.1
+      layer_range: [15,24]
+  - sources:
+    - model: zhengr/MixTAO-7Bx2-MoE-v8.1
+      layer_range: [20,32]
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "allknowingroger/TaoPassthrough-15B-s"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "zhengr/MixTAO-7Bx2-MoE-v8.1",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "unsloth_version": "2024.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,19 @@
+
+dtype: float16
+merge_method: passthrough
+slices:
+  - sources:
+    - model: zhengr/MixTAO-7Bx2-MoE-v8.1
+      layer_range: [0,9]
+  - sources:
+    - model: zhengr/MixTAO-7Bx2-MoE-v8.1
+      layer_range: [5,14]
+  - sources:
+    - model: zhengr/MixTAO-7Bx2-MoE-v8.1
+      layer_range: [10,19]
+  - sources:
+    - model: zhengr/MixTAO-7Bx2-MoE-v8.1
+      layer_range: [15,24]
+  - sources:
+    - model: zhengr/MixTAO-7Bx2-MoE-v8.1
+      layer_range: [20,32]

model-00001-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a167a83097b40d56a6beab788f118544968ae8421b4d7dbaa31df6a396ff348
+size 1996640360

model-00002-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2b9655ff7545d9b73a1d127b84b0e3dbadcfd27c35c87a4c3a7326308113487
+size 1906404456

model-00003-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0577405765cd23c91f577a5f0430f5d8a8d247935847aba0793c8ddc17b15389
+size 1996490944

model-00004-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3219c43c9f4f676e0126085e1a1cbef7119c9468648af7565277702f636d9af3
+size 1996565664

model-00005-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b5cc5aba52351ab72a8c7961fcfb32234eebc5f1dd571da6cbe6286908d31d4
+size 1996524160

model-00006-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b219e3eb9d7fbd31b6686d286bf05e88dfa9897c44c18ae673b3a2463de762
+size 1996532456

model-00007-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cac40c8a295c83c340cf055591d7f7bef5fb7f860bf510b72d7561e1cd8364e
+size 1906321384

model-00008-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86665fdc5bf1f6293a240c89d1e290ce7ae8f02adef5617b8ec15f3a5f78da1b
+size 1996499248

model-00009-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38464f822ebd895311d5785470758d0045f7640714a936e231feff7ceae58cf5
+size 1996490952

model-00010-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da263285e3d9ce18a7fd4a3cc84243997efabc224946495e97ea6377c2ec548f
+size 1996490952

model-00011-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02feba85471b77c9c5666a3965ac6620452907d44f16d058b75d32c8679c015a
+size 1996490952

model-00012-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c82e606a96626a09536414d454cd94d9175d595ad819159921010745810335d
+size 1996490944

model-00013-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e129f173053077f0063b7e45347d41387f8324bdc3d7ed1b04d956d5e472803e
+size 1996490936

model-00014-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b95bf3ff446fcde14054660b5f2e24138e996ff0244138ffa0bbcb2daf97c9e6
+size 1996490944

model-00015-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca6c81017314b1a162a27628e1e865d9bec63bd2be6e6216132978fd01261ae
+size 1996490952

model-00016-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:644d7e684696a564aafb4865757e0832a14b6917d28a5f65dec2fd6d7ed370db
+size 1996490952

model-00017-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d22b62952cdaad616e24b3e99af9154b3b6226ba3aaf6614b854268fba7c1b05
+size 1996524200

model-00018-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1764c4a0219c83b80d85d23885b470cdcc02c8ccffacf2cf233de1e4c2cd2f35
+size 1996868328

model-00019-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f5572e883f78a04d2505d398d95cadf080a7a697edebdc074999d48765bde2c
+size 1997079272

model-00020-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf0f6ec336d0e18d272e8aaf7b9ecc982585535c43c65cb7985cd3b8bba71663
+size 620967416

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1", "total_size": 38375268352}, "weight_map": {"model.layers.19.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.embed_tokens.weight": "model-00002-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.39.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.35.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.38.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.37.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.46.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.45.input_layernorm.weight": "model-00005-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.44.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.43.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.42.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.41.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "lm_head.weight": "model-00007-of-00020.safetensors", "model.norm.weight": "model-00007-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.47.input_layernorm.weight": "model-00008-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00020.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00020.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00018-of-00020.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00018-of-00020.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00018-of-00020.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00018-of-00020.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00018-of-00020.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00019-of-00020.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00020-of-00020.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00020-of-00020.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00020-of-00020.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00020-of-00020.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 255,
+  "pad_token": "<s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}