Gustav0-Freind commited on
Commit
04f1107
·
verified ·
1 Parent(s): d41663a

Upload 9 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 131072,
3
+ "<|im_start|>": 131073
4
+ }
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 131072,
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
+ "rms_norm_eps": 1e-05,
23
+ "rope_theta": 1000000.0,
24
+ "router_aux_loss_coef": 0.001,
25
+ "router_jitter_noise": 0.0,
26
+ "sliding_window": null,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.44.2",
30
+ "use_cache": false,
31
+ "vocab_size": 131074
32
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
2
+ gate_mode: hidden
3
+ dtype: bfloat16
4
+ experts:
5
+ - source_model: cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
6
+ positive_prompts:
7
+ - "mathematics"
8
+ - "science"
9
+ - source_model: BeaverAI/mistral-dory-12b
10
+ positive_prompts:
11
+ - "conversation"
12
+ - "writing"
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.4", "total_size": 42112501760}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00009.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00009.safetensors", "model.norm.weight": "model-00009-of-00009.safetensors", "lm_head.weight": "model-00009-of-00009.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00009-of-00009.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": "<|im_end|>",
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
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff