Upload folder using huggingface_hub

README.md

@@ -0,0 +1,120 @@
+---
+license: apache-2.0
+tags:
+- moe
+- merge
+- mergekit
+- lazymergekit
+- mlabonne/NeuralBeagle14-7B
+- AdaptLLM/finance-chat
+- AdaptLLM/medicine-chat
+- AdaptLLM/law-chat
+---
+
+# AdaptLLM-4x7B-MoE
+
+AdaptLLM-4x7B-MoE is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B)
+* [AdaptLLM/finance-chat](https://huggingface.co/AdaptLLM/finance-chat)
+* [AdaptLLM/medicine-chat](https://huggingface.co/AdaptLLM/medicine-chat)
+* [AdaptLLM/law-chat](https://huggingface.co/AdaptLLM/law-chat)
+
+## 🧩 Configuration
+
+```yaml
+base_model: mlabonne/NeuralBeagle14-7B
+experts:
+  - source_model: mlabonne/NeuralBeagle14-7B
+    positive_prompts:
+    - "chat"
+    - "assistant"
+    - "tell me"
+    - "explain"
+    - "storywriting"
+    - "write"
+    - "scene"
+    - "story"
+    - "character"
+    - "instruct"
+    - "summarize"
+    - "count"
+
+  - source_model: AdaptLLM/finance-chat
+    positive_prompts:
+    - "personal finance"
+    - "budgeting"
+    - "investing"
+    - "retirement planning"
+    - "debt management"
+    - "financial education"
+    - "consumer protection"
+    - "financial"
+    - "money"
+    - "investment"
+    - "banking"
+    - "stock"
+    - "bond"
+    - "portfolio"
+    - "risk"
+    - "return"
+
+  - source_model: AdaptLLM/medicine-chat
+    positive_prompts:
+    - "diagnose"
+    - "treat"
+    - "disease"
+    - "symptom"
+    - "medication"
+    - "anatomy"
+    - "physiology"
+    - "pharmacology"
+    - "clinical trial"
+    - "medical research"
+
+  - source_model: AdaptLLM/law-chat
+    positive_prompts:
+    - "law"
+    - "legal"
+    - "attorney"
+    - "lawyer"
+    - "court"
+    - "contract"
+    - "criminal"
+    - "evidence"
+    - "procedure"
+    - "contracts"
+    - "mergers & acquisitions"
+    - "corporate governance"
+    - "intellectual property"
+    - "employment law"
+    - "international trade"
+    - "competition law"
+    - "antitrust"
+    - "litigation"
+    - "arbitration"
+    - "mediation"
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Isotonic/AdaptLLM-4x7B-MoE"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
+)
+
+messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
+prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+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 +1,30 @@
+{
+  "_name_or_path": "mlabonne/NeuralBeagle14-7B",
+  "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": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "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": "4.37.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,72 @@
+
+base_model: mlabonne/NeuralBeagle14-7B
+experts:
+  - source_model: mlabonne/NeuralBeagle14-7B
+    positive_prompts:
+    - "chat"
+    - "assistant"
+    - "tell me"
+    - "explain"
+    - "storywriting"
+    - "write"
+    - "scene"
+    - "story"
+    - "character"
+    - "instruct"
+    - "summarize"
+    - "count"
+
+  - source_model: AdaptLLM/finance-chat
+    positive_prompts:
+    - "personal finance"
+    - "budgeting"
+    - "investing"
+    - "retirement planning"
+    - "debt management"
+    - "financial education"
+    - "consumer protection"
+    - "financial"
+    - "money"
+    - "investment"
+    - "banking"
+    - "stock"
+    - "bond"
+    - "portfolio"
+    - "risk"
+    - "return"
+
+  - source_model: AdaptLLM/medicine-chat
+    positive_prompts:
+    - "diagnose"
+    - "treat"
+    - "disease"
+    - "symptom"
+    - "medication"
+    - "anatomy"
+    - "physiology"
+    - "pharmacology"
+    - "clinical trial"
+    - "medical research"
+
+  - source_model: AdaptLLM/law-chat
+    positive_prompts:
+    - "law"
+    - "legal"
+    - "attorney"
+    - "lawyer"
+    - "court"
+    - "contract"
+    - "criminal"
+    - "evidence"
+    - "procedure"
+    - "contracts"
+    - "mergers & acquisitions"
+    - "corporate governance"
+    - "intellectual property"
+    - "employment law"
+    - "international trade"
+    - "competition law"
+    - "antitrust"
+    - "litigation"
+    - "arbitration"
+    - "mediation"

model-00001-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5ba582d1516d603a29571ad28f4768296502b76ffa8016b662a8b3121197c5b
+size 1986279080

model-00002-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4286cc7de1f790fce5d0d2dcbe03cd05df29544a6718e1c5d7fa6dcd75e2da0a
+size 1939868216

model-00003-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3346a332112cdf2489f7bed5ddd7e30f1933dbac5dbd5018f3daec0720c9ae3
+size 1939868232

model-00004-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:316492b223de3c66c01892b008fa7ceebde8f79a27deabea54893b1d97613f83
+size 1939868232

model-00005-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:357fb21e64700f2105d023f51018dfefa39bc4bc1356ca626008cd90d11e3e61
+size 1939868232

model-00006-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d31c7a2a685eee2b34ce02e3bd606db55014ce4ca6205e46c136302c06c9988c
+size 1939868232

model-00007-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bfd837c4f9593df05d80b81322e0ea71c313a6b3d71e496a6580226f32b0756
+size 1939868224

model-00008-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8306d8643dde4f70d4e7112a0979ceae150b561f80623584715b1b69e840004e
+size 1939868216

model-00009-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bfb2876af3271bd7c0a41a4b996b5e10f8d0d5efed48fe0251b018c9a95211a
+size 1939868224

model-00010-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:430a35cd2bb8ba308050640ace1b511a7c9620b59b5259bee3d34ffb44a8c5d1
+size 1939868232

model-00011-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37ee7e1ad809e9ed1a69c2a2a30f48147d1f1174540d8baac1c68f3a2c5143c2
+size 1939868232

model-00012-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a9e774d982455b933f73c451fc56fb57b1f9399d464b966f12cc380c27639c9
+size 1939868232

model-00013-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:657fe0edeb679892b2c76fd991659cfc3bf0764bccaefb0620c9c9e2912050d6
+size 1939868232

model-00014-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b2e236f7da6bf50f4e1ab27a724b881e7270b925172cb9a9ceca43a4d8894c0
+size 1939868216

model-00015-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b47b20f4ad3bb2de87b3c807e449591128763f91d1efb798fa3c7d3a7d6f3ac
+size 1939868216

model-00016-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cd1898817f7c94110aba3609837867ba051b7af30a030975d6311808054fb95
+size 1939868232

model-00017-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0094bf42f64438bc17caa28d94b7580c823e76ead3f1ff61af72caee328b702
+size 1939868232

model-00018-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecab74f865069e5edb16a874e605e861912996ed134e57542381e2ecca92f67e
+size 1939868232

model-00019-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a49e7d0fbb0ad78b1f7a5c9d2a2745a8e0393bfa0cbab3f00932f97656c7fb2c
+size 1939868232

model-00020-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcd93081e8913c3ed9b4616ed197ebedb93d4170290bf58f5dd026ad2deef847
+size 1998857456

model-00021-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be352efb1f43a776a78c1cca4a01c52df2a946fb215bfbb6892e05145ca116de
+size 1552955096

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00021.safetensors", "model.norm.weight": "model-00001-of-00021.safetensors", "lm_head.weight": "model-00001-of-00021.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00021.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00021.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00021.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00021.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00021.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00021.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00021.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00021.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00021.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00021.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00021.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00021.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00021.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00021.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00021.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00021.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00021.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00021.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00021.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00021.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00021.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00021.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00021.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00021.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00021.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00021.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00021.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00021.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00021.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00021.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00021.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00021.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00021.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00020-of-00021.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00020-of-00021.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00020-of-00021.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00020-of-00021.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00020-of-00021.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00020-of-00021.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00020-of-00021.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00020-of-00021.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00020-of-00021.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00021-of-00021.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00021-of-00021.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00021-of-00021.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00021-of-00021.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "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": "<s>",
+  "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,
+  "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>",
+  "chat_template": "{% for message in messages %}{{bos_token + message['role'] + '\n' + message['content'] + eos_token + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ bos_token + 'assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 8192,
+  "pad_token": "<s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}