Upload folder using huggingface_hub

README.md

@@ -0,0 +1,55 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- allknowingroger/Multimerge-12B-MoE
+base_model:
+- allknowingroger/Multimerge-12B-MoE
+- allknowingroger/Multimerge-12B-MoE
+---
+
+# Multimerge-19B-pass
+
+Multimerge-19B-pass is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [allknowingroger/Multimerge-12B-MoE](https://huggingface.co/allknowingroger/Multimerge-12B-MoE)
+* [allknowingroger/Multimerge-12B-MoE](https://huggingface.co/allknowingroger/Multimerge-12B-MoE)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+    - model: allknowingroger/Multimerge-12B-MoE
+      layer_range: [8, 32]
+  - sources:
+    - model: allknowingroger/Multimerge-12B-MoE
+      layer_range: [8, 32]
+merge_method: passthrough
+dtype: float16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "allknowingroger/Multimerge-19B-pass"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "allknowingroger/Multimerge-12B-MoE",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,10 @@
+
+slices:
+  - sources:
+    - model: allknowingroger/Multimerge-12B-MoE
+      layer_range: [8, 32]
+  - sources:
+    - model: allknowingroger/Multimerge-12B-MoE
+      layer_range: [8, 32]
+merge_method: passthrough
+dtype: float16

model-00001-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c45d1d3295db21414eb44a5ce30a95983fe33052ff80d7ad84358f84a2e7eca4
+size 994050792

model-00002-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e01ca2f3dd0f5befb721de0aacd570f4a0c86563c63650a33d41abece05c638
+size 989923376

model-00003-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f8da36b50f6abba2bec6e0cabb0e8b36d342e40ed6cd7d55271f721ca624fab
+size 939525600

model-00004-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed6f44e0ef41d550cdfe95d52b1984057025b2f008b2882116040d9b03b9730f
+size 989923816

model-00005-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d0f3229d450fec6d4fbf04e01d433347392c7c859237e433197ad4922c89e7
+size 939525160

model-00006-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2aade1d47f798b1bdcb48e04d6405299ae0a489dcce12b208e410771ed7149b
+size 989923816

model-00007-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:702de26d8b36d5b4c76535e768964ca573883ed6c94a40bac6b5ff9ff7c29868
+size 989923816

model-00008-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:030ab8e58a14c18e590d39f8258ac9d895e12dc01d10d5593d807e3014fc5e0e
+size 939525160

model-00009-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c71567dc7ae8e6de35a359e5fe4a9a2d5761cd45c69250bc6e81d949ddba56e
+size 989923816

model-00010-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80751641ad015f0aaa505747f68f517f6e79d32c898d024b71c34d7994506d1c
+size 939525160

model-00011-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1b7cc8367339f511666e8ab6e327849e78c9d560876432cbf482efa52fb2c4
+size 989923784

model-00012-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ae68772c06acd1f53a8a02b8c0bf2c832488392c8258c1d4c08d0a46b85ef8f
+size 989923816

model-00013-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9707e8a35812638ba0268d1654306d5674352c87e948cc2615cbc30ea392b498
+size 939525160

model-00014-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d019d361c67fd11b8f86b7612abed9c89b246c0d067051d71fd23025072f846
+size 989923816

model-00015-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b03c4bb41c9a721a88fd48d3e6cd03b1914a713c8e34d0e3357cf78bfbb35402
+size 989923384

model-00016-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373f8c6b17ff1e4bc7cfa7e35ee80cb0482501eec5b32f38261e353d1c147c60
+size 939525600

model-00017-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a36499c27cd722f7c80c0f299fc8b94196003ee9c27064e6567211afc02228f4
+size 989923824

model-00018-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22622635264a161217d8edb10add0e4d2556e909d0686089481de3c0cc0c2b30
+size 939525160

model-00019-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a67d634ff28e2438530ecf15e610903b9878db98a250f0c61f4c38639407a84f
+size 989923824

model-00020-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d72a7f54597b81e2ffe15c14a60ac0c81fccb5820ef286ee5418a19f59751b7
+size 989923824

model-00021-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:339bf714b8cecd8eed5f3d5202b686ac154eb65aa27ff8cab9f7429569c1742d
+size 939525160

model-00022-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce52e00ffd6b9fa629a190628366275a7151319b1ab1101f6353e3d24fdcce90
+size 989923824

model-00023-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0c056a8e7efa38d031cf7d5b3dfdd65dfd34c5a04e2b05bb5464f61802f800e
+size 939525160

model-00024-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c34bed623471e984f75174ce78d260ed15f2008d9e59e2252036abd9f534c85
+size 989923824

model-00025-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec22f259c3ae186f998cf5cfff81070bd83ba88be861772c9a5a34933ea5ed5d
+size 989923824

model-00026-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ab5379e1d5fbe2fa7aa31f12bd19d18e281e2109a1e2b74ebfa0a36bf78b7a6
+size 939525160

model-00027-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75dabaefe704d5cfdfc8fd3dba98aa8f81886d330ed8daf27d416612bef44d24
+size 989923824

model-00028-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e951d8a3de8f91024f49d464a262803a5d315647162ba66e361f00baa082e74
+size 989923384

model-00029-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9656586413ee587cc18ea975f3722588a013417fc504c23d00440d8865a8a914
+size 939525600

model-00030-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ee7da69b18db9a9da7e3ea135575a564ee7112f7411ad1597cd402f0d3069b3
+size 989923824

model-00031-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90a93049bb125d45f3871cc5f5b51756b80d1394b73cafdf0ca4feead424fea4
+size 939525160

model-00032-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:464928816fa2a6e7dca5272820b6e23bb8cdc43d71d4eb57beefca5e6d2a7c35
+size 989923824

model-00033-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d973c5ac0ccaca5c7cf788c1da23bb00320293e96d455f78759b0240c39c6c80
+size 989923824

model-00034-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a2d6fa6522b6ae21770bdb82c715eb0639c4947d3140b116b16d86b209b48b6
+size 939525160

model-00035-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aabb680595b4b2ae9ddd6666f3b030a28b661d914399101301441bf43f0aed2d
+size 989923824

model-00036-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90a19f2e20f009096ec2d71f4bab0227e60ffeb32ea94ef4f9f7c32edd306388
+size 939525160

model-00037-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e4362141c05b8ca6b40479c8b4045d3e59a0a4021886d40c95fe6d1255e691
+size 989923824

model-00038-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8094c19159d6bdd433d0a5fcae7c97f0f96224da8ae225e91fb3f8fb575d7629
+size 989923816

model-00039-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c55a850df122f4856382888472eea049839a8d4b2d0e8040532fbe8ffce612f
+size 939525160

model-00040-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27e1a6e24ccd05db0a3e0cb3bfc60e4f87342b8c69bbd4d2aa257eb10320b104
+size 520169536

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 38375268352}, "weight_map": {"lm_head.weight": "model-00001-of-00040.safetensors", "model.embed_tokens.weight": "model-00001-of-00040.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00040.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00040.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00040.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00040.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00040.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00040.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00040.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00040.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00040.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00040.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00040.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00040.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00002-of-00040.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00002-of-00040.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00040.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00040.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00040.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00040.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00040.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00040.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00040.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00040.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00040.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00040.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00040.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00040.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00040.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00040.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00040.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00040.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00040.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00040.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00040.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00040.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00040.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00040.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00040.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00040.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00004-of-00040.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00004-of-00040.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00040.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00040.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00040.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00040.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00040.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00040.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00040.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00040.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00040.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00040.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00040.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00040.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00040.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00040.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00040.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00040.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00040.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00040.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00040.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00040.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00040.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00040.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00040.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00040.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00006-of-00040.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00006-of-00040.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00040.safetensors", "model.layers.4.input_layernorm.weight": "model-00006-of-00040.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00040.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00040.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00040.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00040.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00040.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00040.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00040.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00040.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00040.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00040.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00040.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00040.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00040.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00040.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00040.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00040.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00040.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00040.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00040.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00040.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00040.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00040.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00007-of-00040.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00007-of-00040.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00040.safetensors", "model.layers.5.input_layernorm.weight": "model-00007-of-00040.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00040.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00040.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00040.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00007-of-00040.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00040.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00007-of-00040.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00040.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00040.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00040.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00007-of-00040.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00040.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00040.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00040.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00040.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00040.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00040.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00040.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00040.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00040.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00040.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00040.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00040.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00009-of-00040.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00009-of-00040.safetensors", "model.layers.30.input_layernorm.weight": "model-00009-of-00040.safetensors", "model.layers.6.input_layernorm.weight": "model-00009-of-00040.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00040.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00009-of-00040.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00040.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00009-of-00040.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00040.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00009-of-00040.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00040.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00009-of-00040.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00040.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00009-of-00040.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00040.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00040.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00040.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00040.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00040.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00040.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00040.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00040.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00040.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00040.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00040.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00040.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00011-of-00040.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00011-of-00040.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00040.safetensors", "model.layers.7.input_layernorm.weight": "model-00011-of-00040.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00040.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00011-of-00040.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00040.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00011-of-00040.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00040.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00011-of-00040.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00040.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00011-of-00040.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00040.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00011-of-00040.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00040.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00040.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00040.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00040.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00040.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00040.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00040.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00040.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00040.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00040.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00040.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00040.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00012-of-00040.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00012-of-00040.safetensors", "model.layers.32.input_layernorm.weight": "model-00012-of-00040.safetensors", "model.layers.8.input_layernorm.weight": "model-00012-of-00040.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00012-of-00040.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00012-of-00040.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00040.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00012-of-00040.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00040.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00012-of-00040.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00040.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00012-of-00040.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00040.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00012-of-00040.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00040.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00040.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00040.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00040.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00040.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00040.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00040.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00040.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00040.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00040.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00040.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00040.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00014-of-00040.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00014-of-00040.safetensors", "model.layers.33.input_layernorm.weight": "model-00014-of-00040.safetensors", "model.layers.9.input_layernorm.weight": "model-00014-of-00040.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00014-of-00040.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00014-of-00040.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00014-of-00040.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00014-of-00040.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00014-of-00040.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00014-of-00040.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00014-of-00040.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00014-of-00040.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00014-of-00040.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00040.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00040.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00040.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00040.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00040.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00040.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00040.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00040.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00040.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00040.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00040.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00040.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00040.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00015-of-00040.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00015-of-00040.safetensors", "model.layers.34.input_layernorm.weight": "model-00015-of-00040.safetensors", "model.layers.10.input_layernorm.weight": "model-00015-of-00040.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00015-of-00040.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00015-of-00040.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00015-of-00040.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00015-of-00040.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00015-of-00040.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00016-of-00040.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00016-of-00040.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00016-of-00040.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00016-of-00040.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00016-of-00040.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00040.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00040.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00040.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00040.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00040.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00040.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00040.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00040.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00040.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00040.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00040.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00040.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00017-of-00040.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00017-of-00040.safetensors", "model.layers.35.input_layernorm.weight": "model-00017-of-00040.safetensors", "model.layers.11.input_layernorm.weight": "model-00017-of-00040.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00017-of-00040.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00017-of-00040.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00017-of-00040.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00017-of-00040.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00017-of-00040.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00017-of-00040.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00017-of-00040.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00017-of-00040.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00017-of-00040.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00017-of-00040.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00040.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00040.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00040.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00040.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00040.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00040.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00040.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00040.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00040.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00040.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00040.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00040.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00019-of-00040.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00019-of-00040.safetensors", "model.layers.36.input_layernorm.weight": "model-00019-of-00040.safetensors", "model.layers.12.input_layernorm.weight": "model-00019-of-00040.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00019-of-00040.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00019-of-00040.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00019-of-00040.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00019-of-00040.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00019-of-00040.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00019-of-00040.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00019-of-00040.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00019-of-00040.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00019-of-00040.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00019-of-00040.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00040.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00040.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00040.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00040.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00040.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00040.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00040.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00040.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00040.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00040.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00040.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00040.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00020-of-00040.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00020-of-00040.safetensors", "model.layers.37.input_layernorm.weight": "model-00020-of-00040.safetensors", "model.layers.13.input_layernorm.weight": "model-00020-of-00040.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00020-of-00040.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00020-of-00040.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00020-of-00040.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00020-of-00040.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00020-of-00040.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00020-of-00040.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00020-of-00040.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00020-of-00040.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00020-of-00040.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00020-of-00040.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00040.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00040.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00040.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00040.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00040.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00040.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00040.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00040.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00040.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00040.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00040.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00040.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00022-of-00040.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00022-of-00040.safetensors", "model.layers.38.input_layernorm.weight": "model-00022-of-00040.safetensors", "model.layers.14.input_layernorm.weight": "model-00022-of-00040.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00022-of-00040.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00022-of-00040.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00022-of-00040.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00022-of-00040.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00022-of-00040.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00022-of-00040.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00022-of-00040.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00022-of-00040.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00022-of-00040.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00022-of-00040.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00040.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00040.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00040.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00040.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00040.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00040.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00040.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00040.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00040.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00040.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00040.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00040.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00024-of-00040.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00024-of-00040.safetensors", "model.layers.39.input_layernorm.weight": "model-00024-of-00040.safetensors", "model.layers.15.input_layernorm.weight": "model-00024-of-00040.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00024-of-00040.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00024-of-00040.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00024-of-00040.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00024-of-00040.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00024-of-00040.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00024-of-00040.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00024-of-00040.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00024-of-00040.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00024-of-00040.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00024-of-00040.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00040.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00040.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00040.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00040.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00040.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00040.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00040.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00040.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00040.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00040.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00040.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00040.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00025-of-00040.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00025-of-00040.safetensors", "model.layers.40.input_layernorm.weight": "model-00025-of-00040.safetensors", "model.layers.16.input_layernorm.weight": "model-00025-of-00040.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00025-of-00040.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00025-of-00040.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00025-of-00040.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00025-of-00040.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00025-of-00040.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00025-of-00040.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00025-of-00040.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00025-of-00040.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00025-of-00040.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00025-of-00040.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00040.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00040.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00040.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00040.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00040.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00040.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00040.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00040.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00040.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00027-of-00040.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00040.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00040.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00027-of-00040.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00027-of-00040.safetensors", "model.layers.41.input_layernorm.weight": "model-00027-of-00040.safetensors", "model.layers.17.input_layernorm.weight": "model-00027-of-00040.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00027-of-00040.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00027-of-00040.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00027-of-00040.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00027-of-00040.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00027-of-00040.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00027-of-00040.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00027-of-00040.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00027-of-00040.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00027-of-00040.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00027-of-00040.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00040.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00040.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00040.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00040.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00040.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00040.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00040.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00040.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00040.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00040.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00040.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00040.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00028-of-00040.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00028-of-00040.safetensors", "model.layers.42.input_layernorm.weight": "model-00028-of-00040.safetensors", "model.layers.18.input_layernorm.weight": "model-00028-of-00040.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00028-of-00040.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00028-of-00040.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00028-of-00040.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00028-of-00040.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00028-of-00040.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00029-of-00040.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00029-of-00040.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00029-of-00040.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00029-of-00040.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00029-of-00040.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00029-of-00040.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00029-of-00040.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00040.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00040.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00029-of-00040.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00029-of-00040.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00029-of-00040.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00030-of-00040.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00030-of-00040.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00030-of-00040.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00030-of-00040.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00030-of-00040.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00030-of-00040.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00030-of-00040.safetensors", "model.layers.43.input_layernorm.weight": "model-00030-of-00040.safetensors", "model.layers.19.input_layernorm.weight": "model-00030-of-00040.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00030-of-00040.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00030-of-00040.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00030-of-00040.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00030-of-00040.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00030-of-00040.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00030-of-00040.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00030-of-00040.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00030-of-00040.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00030-of-00040.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00030-of-00040.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00030-of-00040.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00030-of-00040.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00031-of-00040.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00031-of-00040.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00031-of-00040.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00031-of-00040.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00031-of-00040.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00031-of-00040.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00031-of-00040.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00031-of-00040.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00032-of-00040.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00032-of-00040.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00032-of-00040.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00032-of-00040.safetensors", "model.layers.44.input_layernorm.weight": "model-00032-of-00040.safetensors", "model.layers.20.input_layernorm.weight": "model-00032-of-00040.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00032-of-00040.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00032-of-00040.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00032-of-00040.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00032-of-00040.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00032-of-00040.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00032-of-00040.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00032-of-00040.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00032-of-00040.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00032-of-00040.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00032-of-00040.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00032-of-00040.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00032-of-00040.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00032-of-00040.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00032-of-00040.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00032-of-00040.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00033-of-00040.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00033-of-00040.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00033-of-00040.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00033-of-00040.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00033-of-00040.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00033-of-00040.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00033-of-00040.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00033-of-00040.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00033-of-00040.safetensors", "model.layers.45.input_layernorm.weight": "model-00033-of-00040.safetensors", "model.layers.21.input_layernorm.weight": "model-00033-of-00040.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00033-of-00040.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00033-of-00040.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00033-of-00040.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00033-of-00040.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00033-of-00040.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00033-of-00040.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00033-of-00040.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00033-of-00040.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00033-of-00040.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00033-of-00040.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00040.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00040.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00034-of-00040.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00034-of-00040.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00040.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00040.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00040.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00040.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00035-of-00040.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00035-of-00040.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00035-of-00040.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00035-of-00040.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00035-of-00040.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00035-of-00040.safetensors", "model.layers.46.input_layernorm.weight": "model-00035-of-00040.safetensors", "model.layers.22.input_layernorm.weight": "model-00035-of-00040.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00035-of-00040.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00035-of-00040.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00035-of-00040.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00035-of-00040.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00035-of-00040.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00035-of-00040.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00035-of-00040.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00035-of-00040.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00035-of-00040.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00035-of-00040.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00035-of-00040.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00035-of-00040.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00035-of-00040.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00036-of-00040.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00036-of-00040.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00036-of-00040.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00036-of-00040.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00036-of-00040.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00036-of-00040.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00036-of-00040.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00036-of-00040.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00037-of-00040.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00037-of-00040.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00037-of-00040.safetensors", "model.layers.47.input_layernorm.weight": "model-00037-of-00040.safetensors", "model.layers.23.input_layernorm.weight": "model-00037-of-00040.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00037-of-00040.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00037-of-00040.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00037-of-00040.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00037-of-00040.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00037-of-00040.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00037-of-00040.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00037-of-00040.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00037-of-00040.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00037-of-00040.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00037-of-00040.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00037-of-00040.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00037-of-00040.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00037-of-00040.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00037-of-00040.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00037-of-00040.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00037-of-00040.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00038-of-00040.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00038-of-00040.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00038-of-00040.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00038-of-00040.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00038-of-00040.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00038-of-00040.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00038-of-00040.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00038-of-00040.safetensors", "model.layers.24.input_layernorm.weight": "model-00038-of-00040.safetensors", "model.layers.0.input_layernorm.weight": "model-00038-of-00040.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00038-of-00040.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00038-of-00040.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00038-of-00040.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00038-of-00040.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00038-of-00040.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00038-of-00040.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00038-of-00040.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00038-of-00040.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00038-of-00040.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00038-of-00040.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00038-of-00040.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00039-of-00040.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00039-of-00040.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00039-of-00040.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00039-of-00040.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00039-of-00040.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00039-of-00040.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00039-of-00040.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00039-of-00040.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00040-of-00040.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00040-of-00040.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00040-of-00040.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00040-of-00040.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00040-of-00040.safetensors", "model.layers.25.input_layernorm.weight": "model-00040-of-00040.safetensors", "model.layers.1.input_layernorm.weight": "model-00040-of-00040.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00040-of-00040.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00040-of-00040.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00040-of-00040.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00040-of-00040.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00040-of-00040.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00040-of-00040.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00040-of-00040.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00040-of-00040.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00040-of-00040.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00040-of-00040.safetensors", "model.norm.weight": "model-00040-of-00040.safetensors"}}

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_length": null,
+  "model_max_length": 32768,
+  "pad_to_multiple_of": null,
+  "pad_token": "<s>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}