ehristoforu commited on
Commit
88f24de
1 Parent(s): 26dee9e

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 1024000,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 32,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 40,
19
+ "num_key_value_heads": 8,
20
+ "num_local_experts": 2,
21
+ "output_router_logits": false,
22
+ "pad_token_id": 10,
23
+ "quantization_config": {
24
+ "_load_in_4bit": true,
25
+ "_load_in_8bit": false,
26
+ "bnb_4bit_compute_dtype": "bfloat16",
27
+ "bnb_4bit_quant_storage": "uint8",
28
+ "bnb_4bit_quant_type": "nf4",
29
+ "bnb_4bit_use_double_quant": true,
30
+ "llm_int8_enable_fp32_cpu_offload": false,
31
+ "llm_int8_has_fp16_weight": false,
32
+ "llm_int8_skip_modules": null,
33
+ "llm_int8_threshold": 6.0,
34
+ "load_in_4bit": true,
35
+ "load_in_8bit": false,
36
+ "quant_method": "bitsandbytes"
37
+ },
38
+ "rms_norm_eps": 1e-05,
39
+ "rope_theta": 1000000.0,
40
+ "router_aux_loss_coef": 0.001,
41
+ "router_jitter_noise": 0.0,
42
+ "sliding_window": null,
43
+ "tie_word_embeddings": false,
44
+ "torch_dtype": "bfloat16",
45
+ "transformers_version": "4.46.3",
46
+ "unsloth_version": "2024.9",
47
+ "use_cache": true,
48
+ "vocab_size": 131072
49
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ base_model: unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit
2
+ gate_mode: random
3
+ architecture: mixtral
4
+ dtype: bfloat16
5
+ experts:
6
+ - source_model: unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit
7
+ - source_model: unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc35a65f9d019f288064abca7d2cb150db5b616a537a0d6c08c3739e8df834ad
3
+ size 2946585912
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bfabcd76d668e1865886e632b76d8a3197cf89dea82e0750a7c5cf51159fd14
3
+ size 2957116120
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ca3d2a07bfa9898cbbf84db5d7688c6bb991626b7862dffcdc08ae58e091e80
3
+ size 2957116176
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2c6ff46891b9c098e1b91415678b162dc4e57678ebab32d45a195aee1ec0851
3
+ size 2957116192
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c490bd579ff4a7e0735c3eaab4e6e5c8f003f7937989882d516b0f19650060e3
3
+ size 2957116192
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2576064a7c33c67c21155c37cd6bbdbfb0e228b8e8c3a8dd3269e9739f3d027c
3
+ size 2957116192
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2929974a2785476796ce45d1587f9ab7f74a896eeef920755f833c6986aa9489
3
+ size 2957116192
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7139901e54cb0847cbfe06d788272620fb03799b991117ac92e8d7f6f00f992
3
+ size 1710013992
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.5.1", "total_size": 22399232000}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.33.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.35.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.36.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.37.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.38.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.39.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.norm.weight": "model-00008-of-00008.safetensors", "lm_head.weight": "model-00008-of-00008.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
3
+ size 17078292
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff