Upload folder using huggingface_hub

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+tags:
+- moe
+- merge
+- mergekit
+- HuggingFaceH4/zephyr-7b-beta
+- mistralai/Mistral-7B-Instruct-v0.2
+- teknium/OpenHermes-2.5-Mistral-7B
+- meta-math/MetaMath-Mistral-7B
+base_model:
+- HuggingFaceH4/zephyr-7b-beta
+- mistralai/Mistral-7B-Instruct-v0.2
+- teknium/OpenHermes-2.5-Mistral-7B
+- meta-math/MetaMath-Mistral-7B
+---
+
+# Boundary-4x7b-MoE
+
+Boundary-4x7b-MoE is a Mixture of Experts (MoE) made with the following models:
+* [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)
+* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
+* [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
+* [meta-math/MetaMath-Mistral-7B](https://huggingface.co/meta-math/MetaMath-Mistral-7B)
+
+## 🧩 Configuration
+
+```yaml
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+dtype: float16
+gate_mode: cheap_embed
+experts:
+  - source_model: HuggingFaceH4/zephyr-7b-beta
+    positive_prompts: ["You are an helpful general-pupose assistant."]
+  - source_model: mistralai/Mistral-7B-Instruct-v0.2
+    positive_prompts: ["You are helpful assistant."]
+  - source_model: teknium/OpenHermes-2.5-Mistral-7B
+    positive_prompts: ["You are helpful a coding assistant."]
+  - source_model: meta-math/MetaMath-Mistral-7B
+    positive_prompts: ["You are an assistant good at math."]
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "NotAiLOL/Boundary-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": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,13 @@
+
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+dtype: float16
+gate_mode: cheap_embed
+experts:
+  - source_model: HuggingFaceH4/zephyr-7b-beta
+    positive_prompts: ["You are an helpful general-pupose assistant."]
+  - source_model: mistralai/Mistral-7B-Instruct-v0.2
+    positive_prompts: ["You are helpful assistant."]
+  - source_model: teknium/OpenHermes-2.5-Mistral-7B
+    positive_prompts: ["You are helpful a coding assistant."]
+  - source_model: meta-math/MetaMath-Mistral-7B
+    positive_prompts: ["You are an assistant good at math."]

model-00001-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f568b21f2d03ecf9006e1ff57971843213ddb9b89bc81f68f70ec6641db6a52b
+size 1900046720

model-00002-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e49858c7ee4ab7456ba69ad057c1c8dbc4b6d839fdfa91d978e4ddab682d530b
+size 1929415960

model-00003-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a356e5f890d6dba901dd99f45a68b3afa6594f5438d97d9f4fd56298cd034f9f
+size 1962953448

model-00004-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99d942fc059c74451beebfc315950756b9001b90604479f8406a8ccf93d2bc7d
+size 1962953448

model-00005-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bdfbf110b755d2d4d289d4fa493fb337c3406fdbf3d4e7a5b4f87abe09307f0
+size 1929415960

model-00006-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e02a4faa1eb225618168462f8101c3687f4f8fd91c732e799ced0aa8ad81d78
+size 1962953448

model-00007-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e435b2e5f167e9e91942d33a76a092e92d07ae219e165612924bb1f8bcd7bcf
+size 1962953448

model-00008-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f03999f66ba580883d6550e633b508f7781ed6a28bd41d17b61e8cbd7c6d835
+size 1929415928

model-00009-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4615229119a64b63cf4839954ff7fcab3e082e93a6e259e14c9cdb031400d7
+size 1962953472

model-00010-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c702957f08a11db9fd185242de0e03b18ca7a5e53efa17e37662d22b9e60f0e0
+size 1962953472

model-00011-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee8daf07573608bf32713f3817cda85a52324e4479951afe2dc825c2af9e4d3d
+size 1996516320

model-00012-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f0aa1027645ec2f0a4b4fb4dcbd2ffecf3f67d82ae78a5faadc7ec5544df91d
+size 1895853136

model-00013-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f68b6b64859f2be143b9b41de76381a1d479d26f2db7b07a82509f12479f1b7
+size 1962953472

model-00014-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a6210df0497eddcdf73977853ba1c49868c4946a910d9ddda6049a541bbe303
+size 1962953472

model-00015-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3554d6207a39c5c7e093c403bc48fc649e558cce42869bb5eaa8a80cbb97565b
+size 1929415992

model-00016-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4907560b16c935f98343b888fcd4df8c183871e2458166ad2887683c24aec513
+size 1962953472

model-00017-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af56e570f993395a11d311ba384cada5426dedf3931ce347279483b4876524c8
+size 1962953472

model-00018-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee1dbc93b208a451951e3c5bf991553a6a687ac767d7825d8d265e8829486e74
+size 1929415992

model-00019-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60d925f4cff4fecf6470de1c33cd894f133d09a16c5166402b3b19115d1067ea
+size 1962953472

model-00020-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1062bf1c36d7eb1ca91e9dbd0da4c022ea19f628f00b622c7578250b22048eca
+size 1962953472

model-00021-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e095bf17fe8851200ff0ca7242c1e2cb6a3ee193dc9c66e3ed09420c85594f2
+size 1929415992

model-00022-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5892d6151ed4aa43e4dd49f77305d4df51777951f48fe53d9f79bb58f92823
+size 1962953472

model-00023-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d318983a49dc3d8a7788cd54a05fa8dfb3c2996551bc28bf41a15b81476a3be
+size 1962953472

model-00024-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcc453a44aaa870af3d92e70e2ed71b82a8e7499bfff20f3314eec45d2afb938
+size 1996516320

model-00025-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f6f946d8e2dd42c9c09af10d0a543cef442193253679bd08af76cbaadfed366
+size 1460680216

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 48307380224}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00025.safetensors", "model.norm.weight": "model-00001-of-00025.safetensors", "lm_head.weight": "model-00001-of-00025.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00025.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00025.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00025.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00025.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00025.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00025.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00025.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00025.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00025.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00025.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00025.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00025.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00025.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00025.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00025.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00025.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00025.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00025.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00025.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00025.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00025.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00025.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00025.safetensors", "model.layers.7.input_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00025.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00025.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00025.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00025.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00025.safetensors", "model.layers.8.input_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00025.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00025.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00025.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00025.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00025.safetensors", "model.layers.9.input_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00025.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00025.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00025.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00025.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00025.safetensors", "model.layers.10.input_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00008-of-00025.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00025.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00025.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00025.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00025.safetensors", "model.layers.11.input_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00009-of-00025.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00009-of-00025.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00009-of-00025.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00009-of-00025.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00025.safetensors", "model.layers.12.input_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00025.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00025.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00025.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00025.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.input_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00025.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00025.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00025.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00025.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00025.safetensors", "model.layers.14.input_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00025.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00012-of-00025.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00012-of-00025.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00025.safetensors", "model.layers.15.input_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00012-of-00025.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00012-of-00025.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00012-of-00025.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00025.safetensors", "model.layers.16.input_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00013-of-00025.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00013-of-00025.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00013-of-00025.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00025.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00025.safetensors", "model.layers.17.input_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00014-of-00025.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00014-of-00025.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00014-of-00025.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00014-of-00025.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00025.safetensors", "model.layers.18.input_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00015-of-00025.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00015-of-00025.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00015-of-00025.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00015-of-00025.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00025.safetensors", "model.layers.19.input_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00015-of-00025.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00015-of-00025.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00015-of-00025.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00015-of-00025.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00025.safetensors", "model.layers.20.input_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00016-of-00025.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00016-of-00025.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00016-of-00025.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00016-of-00025.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00025.safetensors", "model.layers.21.input_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00017-of-00025.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00017-of-00025.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00017-of-00025.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00017-of-00025.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00025.safetensors", "model.layers.22.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00018-of-00025.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00018-of-00025.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00025.safetensors", "model.layers.23.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00018-of-00025.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00018-of-00025.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00025.safetensors", "model.layers.24.input_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00019-of-00025.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00019-of-00025.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00019-of-00025.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00019-of-00025.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00020-of-00025.safetensors", "model.layers.25.input_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00020-of-00025.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00020-of-00025.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00020-of-00025.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00020-of-00025.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00025.safetensors", "model.layers.26.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00021-of-00025.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00021-of-00025.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00025.safetensors", "model.layers.27.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00021-of-00025.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00021-of-00025.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00022-of-00025.safetensors", "model.layers.28.input_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00022-of-00025.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00022-of-00025.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00022-of-00025.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00022-of-00025.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00023-of-00025.safetensors", "model.layers.29.input_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00023-of-00025.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00023-of-00025.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00023-of-00025.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00025.safetensors", "model.layers.30.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00025.safetensors", "model.layers.31.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00025-of-00025.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00025-of-00025.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00025-of-00025.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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 +1,43 @@
+{
+  "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": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}