Upload folder using huggingface_hub

README.md

@@ -0,0 +1,55 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- zhengr/MixTAO-7Bx2-MoE-v8.1
+base_model:
+- zhengr/MixTAO-7Bx2-MoE-v8.1
+- zhengr/MixTAO-7Bx2-MoE-v8.1
+---
+
+# MixTAO-19B-pass
+
+MixTAO-19B-pass is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [zhengr/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1)
+* [zhengr/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+    - model: zhengr/MixTAO-7Bx2-MoE-v8.1
+      layer_range: [0, 24]
+  - sources:
+    - model: zhengr/MixTAO-7Bx2-MoE-v8.1
+      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/MixTAO-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 +1,33 @@
+{
+  "_name_or_path": "zhengr/MixTAO-7Bx2-MoE-v8.1",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.1",
+  "unsloth_version": "2024.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,10 @@
+
+slices:
+  - sources:
+    - model: zhengr/MixTAO-7Bx2-MoE-v8.1
+      layer_range: [0, 24]
+  - sources:
+    - model: zhengr/MixTAO-7Bx2-MoE-v8.1
+      layer_range: [8, 32]
+merge_method: passthrough
+dtype: float16

model-00001-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:821aabafc39d9025f5bff2429e01b4d8cfa0fea17e4b1b06e9f68065e7cfc50e
+size 994050792

model-00002-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e47dcbdc2ce0623b3a6bd991373972f50aaa6e99ec12b23cac7d1d65ea76db5b
+size 906004160

model-00003-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0676d9a70bd6c6d9c9cab7a1b4750f040a086b5154ffe90249ffe8ea34f60ab
+size 906004168

model-00004-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5190f0544de8adf5dd6f1d2fe070864d0512dc2e1f569b38c9792baf7f047fd
+size 989923824

model-00005-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0465b27b2f43d36ee9836c941a325246ea90424e13dfb8af8e7df61b89a10592
+size 939525160

model-00006-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21bac79b7b2ea6286bc6b15fadfff4daf79f373a39fd6f459bbe176b0b5f4517
+size 989923824

model-00007-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f2b0a15811cdf927c893918fe26b8305470fffb78afbb40a5f2336e234cce17
+size 989923384

model-00008-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17c38ec889645c6c9e46e47151da2877406ff281af8676fd69c110db7ee7b03
+size 939525600

model-00009-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b092a6eb8494bc80f5abf8e5c1cd8aca0cc821fc71e41e5db5a938bc653410
+size 989923824

model-00010-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:457f4543dbd6d7fa0c77f041b4dc862bdde584f841e801b345b02d4a5ecd08cd
+size 939525160

model-00011-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c2d9828ee0ba501b11ccf6fbfdfbc77f94d05b88ae3eabf34f6ae22f75c8c62
+size 989923824

model-00012-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d7497baa7bb7325934d8ee5b1731868e0959b96b94a0502602a2952dc066d45
+size 989923824

model-00013-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26b903d731bb2bd1ea9a6dd571e35299070961d29c8e2f9e686d0ed9eb9cc725
+size 939525160

model-00014-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6e042424bf5c771fb974d04c57767339dc089503e9b13713d7fcd417d38e07a
+size 989923824

model-00015-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:734ef062ce763fe1c0b5b391b867d946a2beaaecad0a87af2e0232139cf55d23
+size 939525160

model-00016-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af40096dade5dd0828ba4b9b9bd77d8b51c526b37487ba4de2c66f0aacf88920
+size 989923824

model-00017-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32738605d0bcd8a8ac716a617a9dd049cd9f7d5d7113bcf94570e072aefc729a
+size 989923824

model-00018-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17bd13ec9ee98f19c061f8fd2729fd85510d98b582ca763cd3e43279c18362d5
+size 939525160

model-00019-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ae70f35ca1a83a87f1c0cbbb356b69643e032bd779c0192ad02b4e799debc03
+size 989923824

model-00020-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f30732f57b51bca1900f92c7fed537e74f8a2b7b0803ac724f0fc0d26188c75
+size 906004168

model-00021-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f05f5924f03c624e893a0093262a07e2d73eb69a8bd74aa405d978fc8fc2d9c
+size 989923824

model-00022-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b443d9a867ca3ce4d9c07acb2c2078b6a82790103554895450004828662d3fef
+size 939525160

model-00023-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b62f08e0bd206a7c2f5db32f9e3fea82a165e93ffe8f7946b70ae57682130028
+size 989923824

model-00024-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bf6df90af84119f0d6434e9808d0918049ae75e915d698adf89b5e2ea1205a0
+size 939525160

model-00025-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec685acbedc914d295102cf3a136410aa228844310c2bd2d18c4762a22488c9
+size 989923824

model-00026-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ee5244e429dd9c73bdf9e77aa54a99326fdcf30741a7efefa80b7101aeca800
+size 989923824

model-00027-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d0eaeab92cc30cd6983110923599128ba14271ce7eb5ceaa853ba956b9ea178
+size 906004176

model-00028-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6060eafa2792ee336c7e95c02a4d02826081c1276605431077b4ecb23a78bc26
+size 906004176

model-00029-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:700e7bc59af9afc118b0f80a76ea61ebf54f72bec0dba0c35861a35d43c51553
+size 906004176

model-00030-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74515efbdf22bdf13fd816902b3b090a2aadeb6ad388f466b20631944e2d11da
+size 906004176

model-00031-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd7f028224c2a41bb6afa01dd181d93c0171225569ea94048ec17e22aae20c6
+size 989923824

model-00032-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:130f769a04cc330d077dd8d40e6180223c4f296c07a8893d7a3deb92afbd69d5
+size 906004160

model-00033-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75588dccbc42086aa7cf9d463fde7a812e6668d18c8edfcbb057eb17faa5a182
+size 906004176

model-00034-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bfe226ee33fa9a82af944cc6e98bfad3b056f28f08f3c2ad41317c3b6df0a24
+size 906004168

model-00035-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:477a00f025e33cedd3cfbe7d313da4a7e2b3d977f55d194c1c2bba3cebb305d6
+size 906004160

model-00036-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05bd22e9ea590a5825b569bb5dd669f761293ee3e48d36b1ec637ea32f9ac1e
+size 906004160

model-00037-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deff25ca14ed661fcbe8b29381eba388ceaaf22009e72a27cd73eefd94048e48
+size 989923808

model-00038-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:561d1cadedbef4b1636298107b31560489371e6a5cad55073e5125efa883a40b
+size 939525160

model-00039-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab27379d10654d917e1b5cd87e2e2f9f5d4e92aebf4fa8c6f014f7be59995c55
+size 989923816

model-00040-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbe8af892203f79c772eca058165a3e1cb695804768f7ace7c89889a7e16f743
+size 939525160

model-00041-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20609378be7b626b2d2ec3ce9dee52164fa0805a9d4379b8b46b914facbf6b0
+size 285288216

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-00041.safetensors", "model.embed_tokens.weight": "model-00001-of-00041.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00041.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00041.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00041.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00041.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00041.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00041.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00002-of-00041.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00041.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00041.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00041.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00041.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00041.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00041.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00041.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00041.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00041.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00041.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00041.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00041.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00003-of-00041.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00041.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00041.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00041.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00041.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00041.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00041.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00041.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00041.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00041.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00041.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00041.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00041.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00041.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00041.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00041.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00041.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00041.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00041.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00004-of-00041.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00004-of-00041.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00041.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00041.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00041.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00041.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00041.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00041.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00041.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00041.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00041.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00041.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00041.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00041.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00041.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00041.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00041.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00041.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00041.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00041.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00041.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00041.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00041.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00041.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00041.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00041.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00006-of-00041.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00006-of-00041.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00041.safetensors", "model.layers.11.input_layernorm.weight": "model-00006-of-00041.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00041.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00041.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00041.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00041.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00041.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00041.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00041.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00041.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00041.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00041.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00041.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00041.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00041.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00041.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00041.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00041.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00041.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00041.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00041.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00041.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00041.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00041.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00007-of-00041.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00007-of-00041.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00041.safetensors", "model.layers.12.input_layernorm.weight": "model-00007-of-00041.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00041.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00041.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00041.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00041.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00041.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00041.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00041.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00041.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00041.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00041.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00041.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00041.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00041.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00041.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00041.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00041.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00041.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00041.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00041.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00041.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00041.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00041.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00009-of-00041.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00009-of-00041.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00041.safetensors", "model.layers.13.input_layernorm.weight": "model-00009-of-00041.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00041.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00041.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00041.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00009-of-00041.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00041.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00009-of-00041.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00041.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00009-of-00041.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00041.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00009-of-00041.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00041.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00041.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00041.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00041.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00041.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00041.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00041.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00041.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00041.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00041.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00041.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00041.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00011-of-00041.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00011-of-00041.safetensors", "model.layers.30.input_layernorm.weight": "model-00011-of-00041.safetensors", "model.layers.14.input_layernorm.weight": "model-00011-of-00041.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00041.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00011-of-00041.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00041.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00011-of-00041.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00041.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00011-of-00041.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00041.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00041.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00041.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00011-of-00041.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00041.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00041.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00041.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00041.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00041.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00041.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00041.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00041.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00041.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00041.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00041.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00041.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00012-of-00041.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00012-of-00041.safetensors", "model.layers.31.input_layernorm.weight": "model-00012-of-00041.safetensors", "model.layers.15.input_layernorm.weight": "model-00012-of-00041.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00041.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00012-of-00041.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00041.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00012-of-00041.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00041.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00012-of-00041.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00041.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00012-of-00041.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00041.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00012-of-00041.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00041.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00041.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00041.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00041.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00041.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00041.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00041.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00041.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00041.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00041.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00041.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00041.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00014-of-00041.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00014-of-00041.safetensors", "model.layers.32.input_layernorm.weight": "model-00014-of-00041.safetensors", "model.layers.16.input_layernorm.weight": "model-00014-of-00041.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00014-of-00041.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00014-of-00041.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00014-of-00041.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00014-of-00041.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00014-of-00041.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00014-of-00041.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00014-of-00041.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00014-of-00041.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00014-of-00041.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00014-of-00041.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00041.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00041.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00041.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00041.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00041.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00041.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00041.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00041.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00041.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00041.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00041.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00041.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00016-of-00041.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00016-of-00041.safetensors", "model.layers.33.input_layernorm.weight": "model-00016-of-00041.safetensors", "model.layers.17.input_layernorm.weight": "model-00016-of-00041.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00016-of-00041.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00016-of-00041.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00016-of-00041.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00016-of-00041.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00016-of-00041.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00016-of-00041.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00016-of-00041.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00016-of-00041.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00016-of-00041.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00016-of-00041.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00041.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00041.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00041.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00041.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00041.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00041.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00041.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00041.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00041.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00041.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00041.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00041.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00017-of-00041.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00017-of-00041.safetensors", "model.layers.34.input_layernorm.weight": "model-00017-of-00041.safetensors", "model.layers.18.input_layernorm.weight": "model-00017-of-00041.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00017-of-00041.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00017-of-00041.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00017-of-00041.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00017-of-00041.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00017-of-00041.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00017-of-00041.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00017-of-00041.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00017-of-00041.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00017-of-00041.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00017-of-00041.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00041.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00041.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00041.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00041.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00041.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00041.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00041.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00041.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00041.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00041.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00041.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00041.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00019-of-00041.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00019-of-00041.safetensors", "model.layers.35.input_layernorm.weight": "model-00019-of-00041.safetensors", "model.layers.19.input_layernorm.weight": "model-00019-of-00041.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00019-of-00041.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00019-of-00041.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00019-of-00041.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00019-of-00041.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00019-of-00041.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00019-of-00041.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00019-of-00041.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00019-of-00041.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00019-of-00041.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00019-of-00041.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00041.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00041.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00041.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00041.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00041.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00041.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00020-of-00041.safetensors", "model.layers.2.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00020-of-00041.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00020-of-00041.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00020-of-00041.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00020-of-00041.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00041.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00041.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00041.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00041.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00041.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00041.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00041.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00041.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00041.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00041.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00041.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00041.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00021-of-00041.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00021-of-00041.safetensors", "model.layers.36.input_layernorm.weight": "model-00021-of-00041.safetensors", "model.layers.20.input_layernorm.weight": "model-00021-of-00041.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00021-of-00041.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00021-of-00041.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00021-of-00041.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00021-of-00041.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00021-of-00041.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00041.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00021-of-00041.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00021-of-00041.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00021-of-00041.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00021-of-00041.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00041.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00041.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00041.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00041.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00041.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00041.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00041.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00041.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00041.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00041.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00041.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00041.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00023-of-00041.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00023-of-00041.safetensors", "model.layers.37.input_layernorm.weight": "model-00023-of-00041.safetensors", "model.layers.21.input_layernorm.weight": "model-00023-of-00041.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00023-of-00041.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00023-of-00041.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00023-of-00041.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00023-of-00041.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00023-of-00041.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00023-of-00041.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00023-of-00041.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00023-of-00041.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00023-of-00041.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00023-of-00041.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00041.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00041.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00041.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00041.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00041.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00041.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00041.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00041.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00041.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00041.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00041.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00041.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00025-of-00041.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00025-of-00041.safetensors", "model.layers.38.input_layernorm.weight": "model-00025-of-00041.safetensors", "model.layers.22.input_layernorm.weight": "model-00025-of-00041.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00025-of-00041.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00025-of-00041.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00025-of-00041.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00025-of-00041.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00025-of-00041.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00025-of-00041.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00025-of-00041.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00025-of-00041.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00025-of-00041.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00025-of-00041.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00041.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00041.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00041.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00041.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00041.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00041.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00041.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00041.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00041.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00041.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00041.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00041.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00026-of-00041.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00026-of-00041.safetensors", "model.layers.39.input_layernorm.weight": "model-00026-of-00041.safetensors", "model.layers.23.input_layernorm.weight": "model-00026-of-00041.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00026-of-00041.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00026-of-00041.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00026-of-00041.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00026-of-00041.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00026-of-00041.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00026-of-00041.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00026-of-00041.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00026-of-00041.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00026-of-00041.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00026-of-00041.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00041.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00041.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00041.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00041.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00027-of-00041.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00041.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00027-of-00041.safetensors", "model.layers.40.input_layernorm.weight": "model-00027-of-00041.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00027-of-00041.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00027-of-00041.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00027-of-00041.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00027-of-00041.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00027-of-00041.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00041.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00041.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00041.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00041.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00041.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00041.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00028-of-00041.safetensors", "model.layers.41.input_layernorm.weight": "model-00028-of-00041.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00028-of-00041.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00028-of-00041.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00028-of-00041.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00028-of-00041.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00028-of-00041.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00041.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00041.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00041.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00029-of-00041.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00029-of-00041.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00029-of-00041.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00029-of-00041.safetensors", "model.layers.42.input_layernorm.weight": "model-00029-of-00041.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00029-of-00041.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00029-of-00041.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00029-of-00041.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00029-of-00041.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00029-of-00041.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00029-of-00041.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00041.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00029-of-00041.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00029-of-00041.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00030-of-00041.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00030-of-00041.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00030-of-00041.safetensors", "model.layers.43.input_layernorm.weight": "model-00030-of-00041.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00030-of-00041.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00030-of-00041.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00030-of-00041.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00030-of-00041.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00030-of-00041.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00030-of-00041.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00030-of-00041.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00030-of-00041.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00030-of-00041.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00030-of-00041.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00031-of-00041.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00031-of-00041.safetensors", "model.layers.44.input_layernorm.weight": "model-00031-of-00041.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00031-of-00041.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00031-of-00041.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00031-of-00041.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00031-of-00041.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00031-of-00041.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00031-of-00041.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00031-of-00041.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00031-of-00041.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00031-of-00041.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00031-of-00041.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00031-of-00041.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00031-of-00041.safetensors", "model.layers.45.input_layernorm.weight": "model-00031-of-00041.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00031-of-00041.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00031-of-00041.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00031-of-00041.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00031-of-00041.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00031-of-00041.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00032-of-00041.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00032-of-00041.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00032-of-00041.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00032-of-00041.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00032-of-00041.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00032-of-00041.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00032-of-00041.safetensors", "model.layers.3.input_layernorm.weight": "model-00032-of-00041.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00032-of-00041.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00032-of-00041.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00032-of-00041.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00032-of-00041.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00032-of-00041.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00032-of-00041.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00033-of-00041.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00033-of-00041.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00033-of-00041.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00033-of-00041.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00033-of-00041.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00033-of-00041.safetensors", "model.layers.46.input_layernorm.weight": "model-00033-of-00041.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00033-of-00041.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00033-of-00041.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00033-of-00041.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00033-of-00041.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00033-of-00041.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00033-of-00041.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00033-of-00041.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00041.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00041.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00034-of-00041.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00034-of-00041.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00034-of-00041.safetensors", "model.layers.47.input_layernorm.weight": "model-00034-of-00041.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00034-of-00041.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00034-of-00041.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00034-of-00041.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00034-of-00041.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00034-of-00041.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00041.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00034-of-00041.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00041.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00035-of-00041.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00035-of-00041.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00035-of-00041.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00035-of-00041.safetensors", "model.layers.4.input_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00035-of-00041.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00035-of-00041.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00035-of-00041.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00035-of-00041.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00035-of-00041.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00035-of-00041.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00035-of-00041.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00036-of-00041.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00036-of-00041.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00036-of-00041.safetensors", "model.layers.5.input_layernorm.weight": "model-00036-of-00041.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00036-of-00041.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00036-of-00041.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00036-of-00041.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00036-of-00041.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00036-of-00041.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00036-of-00041.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00036-of-00041.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00036-of-00041.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00036-of-00041.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00037-of-00041.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00037-of-00041.safetensors", "model.layers.6.input_layernorm.weight": "model-00037-of-00041.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00037-of-00041.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00037-of-00041.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00037-of-00041.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00037-of-00041.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00037-of-00041.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00037-of-00041.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00037-of-00041.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00037-of-00041.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00037-of-00041.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00037-of-00041.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00037-of-00041.safetensors", "model.layers.7.input_layernorm.weight": "model-00037-of-00041.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00037-of-00041.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00037-of-00041.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00037-of-00041.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00037-of-00041.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00038-of-00041.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00038-of-00041.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00038-of-00041.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00038-of-00041.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00038-of-00041.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00038-of-00041.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00038-of-00041.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00038-of-00041.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00039-of-00041.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00039-of-00041.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00039-of-00041.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00039-of-00041.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00039-of-00041.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00039-of-00041.safetensors", "model.layers.24.input_layernorm.weight": "model-00039-of-00041.safetensors", "model.layers.8.input_layernorm.weight": "model-00039-of-00041.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00039-of-00041.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00039-of-00041.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00039-of-00041.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00039-of-00041.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00039-of-00041.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00039-of-00041.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00039-of-00041.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00039-of-00041.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00039-of-00041.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00039-of-00041.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00039-of-00041.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00039-of-00041.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00039-of-00041.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00040-of-00041.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00040-of-00041.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00040-of-00041.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00040-of-00041.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00040-of-00041.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00040-of-00041.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00040-of-00041.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00040-of-00041.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00041-of-00041.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00041-of-00041.safetensors", "model.layers.25.input_layernorm.weight": "model-00041-of-00041.safetensors", "model.layers.9.input_layernorm.weight": "model-00041-of-00041.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00041-of-00041.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00041-of-00041.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00041-of-00041.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00041-of-00041.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00041-of-00041.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00041-of-00041.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00041-of-00041.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00041-of-00041.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00041-of-00041.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00041-of-00041.safetensors", "model.norm.weight": "model-00041-of-00041.safetensors"}}

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

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