david commited on
Commit
971c35d
1 Parent(s): a796067

initial upload

Browse files
.gitattributes CHANGED
@@ -32,4 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.xz 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
 
32
  *.xz 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
+ *.gguf filter=lfs diff=lfs merge=lfs -text
36
  *tfevents* filter=lfs diff=lfs merge=lfs -text
NebulaNet-v2-4x7B.Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fd15243f264b2a9baf0d876979a49ea913b7aea1f8b41c7ba0724834222d187
3
+ size 8841898240
README.md CHANGED
@@ -1,3 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
  ---
 
 
1
+ <<<<<<< HEAD
2
+ ## Usage
3
+ NebulaNet-v2: An MOE of 4 7b expert models.
4
+ It is good at coding and multi language translation. It should be fluent at chat and math too.
5
+
6
+ ## mergekit config
7
+ ```
8
+ base_model: ContextualAI/Contextual_KTO_Mistral_PairRM
9
+ experts:
10
+ - source_model: ContextualAI/Contextual_KTO_Mistral_PairRM
11
+ positive_prompts:
12
+ - "chat"
13
+ - "assistant"
14
+ - "tell me"
15
+ - "explain"
16
+ - "I want"
17
+ - source_model: Nexusflow/Starling-LM-7B-beta
18
+ positive_prompts:
19
+ - "code"
20
+ - "python"
21
+ - "javascript"
22
+ - "programming"
23
+ - "algorithm"
24
+ - source_model: snorkelai/Snorkel-Mistral-PairRM-DPO
25
+ positive_prompts:
26
+ - ""
27
+ - source_model: mlabonne/NeuralDaredevil-7B
28
+ positive_prompts:
29
+ - "reason"
30
+ - "math"
31
+ - "mathematics"
32
+ - "solve"
33
+ - "count"
34
+ ```
35
+
36
+ =======
37
  ---
38
  license: mit
39
  ---
40
+ >>>>>>> a796067 (initial commit)
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ContextualAI/Contextual_KTO_Mistral_PairRM",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 4,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.39.1",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: ContextualAI/Contextual_KTO_Mistral_PairRM
2
+ experts:
3
+ - source_model: ContextualAI/Contextual_KTO_Mistral_PairRM
4
+ positive_prompts:
5
+ - "chat"
6
+ - "assistant"
7
+ - "tell me"
8
+ - "explain"
9
+ - "I want"
10
+ - source_model: Nexusflow/Starling-LM-7B-beta
11
+ positive_prompts:
12
+ - "code"
13
+ - "python"
14
+ - "javascript"
15
+ - "programming"
16
+ - "algorithm"
17
+ - source_model: snorkelai/Snorkel-Mistral-PairRM-DPO
18
+ positive_prompts:
19
+ - ""
20
+ - source_model: mlabonne/NeuralDaredevil-7B
21
+ positive_prompts:
22
+ - "reason"
23
+ - "math"
24
+ - "mathematics"
25
+ - "solve"
26
+ - "count"
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00025.safetensors", "model.norm.weight": "model-00001-of-00025.safetensors", "lm_head.weight": "model-00001-of-00025.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00025.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00025.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00025.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00025.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00025.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00025.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00025.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00025.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00025.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00025.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00025.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00025.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00025.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00025.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00025.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00025.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00025.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00025.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00025.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00025.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00025.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00025.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00025.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00025.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00025.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00025.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00025.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00025.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00025.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00025.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00025.safetensors", "model.layers.7.input_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00025.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00025.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00025.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00025.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00025.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00025.safetensors", "model.layers.8.input_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00025.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00025.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00025.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00025.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00025.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00025.safetensors", "model.layers.9.input_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00025.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00025.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00025.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00025.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00025.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00025.safetensors", "model.layers.10.input_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00008-of-00025.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00025.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00025.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00025.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00025.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00025.safetensors", "model.layers.11.input_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00009-of-00025.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00009-of-00025.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00009-of-00025.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00009-of-00025.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00025.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00025.safetensors", "model.layers.12.input_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00025.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00025.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00025.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00025.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00025.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.input_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00025.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00025.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00025.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00025.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00025.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00025.safetensors", "model.layers.14.input_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00025.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00012-of-00025.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00012-of-00025.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00025.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00025.safetensors", "model.layers.15.input_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00012-of-00025.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00012-of-00025.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00012-of-00025.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00025.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00025.safetensors", "model.layers.16.input_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00013-of-00025.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00013-of-00025.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00013-of-00025.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00025.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00025.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00025.safetensors", "model.layers.17.input_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00014-of-00025.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00014-of-00025.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00014-of-00025.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00014-of-00025.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00025.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00025.safetensors", "model.layers.18.input_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00015-of-00025.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00015-of-00025.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00015-of-00025.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00015-of-00025.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00025.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00025.safetensors", "model.layers.19.input_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00015-of-00025.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00015-of-00025.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00015-of-00025.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00015-of-00025.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00025.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00025.safetensors", "model.layers.20.input_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00016-of-00025.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00016-of-00025.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00016-of-00025.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00016-of-00025.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00025.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00025.safetensors", "model.layers.21.input_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00017-of-00025.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00017-of-00025.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00017-of-00025.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00017-of-00025.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00025.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00025.safetensors", "model.layers.22.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00018-of-00025.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00018-of-00025.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00025.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00025.safetensors", "model.layers.23.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00018-of-00025.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00018-of-00025.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00025.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00025.safetensors", "model.layers.24.input_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00019-of-00025.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00019-of-00025.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00019-of-00025.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00019-of-00025.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00020-of-00025.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00020-of-00025.safetensors", "model.layers.25.input_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00020-of-00025.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00020-of-00025.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00020-of-00025.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00020-of-00025.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00025.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00025.safetensors", "model.layers.26.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00021-of-00025.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00021-of-00025.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00025.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00025.safetensors", "model.layers.27.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00021-of-00025.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00021-of-00025.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00022-of-00025.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00022-of-00025.safetensors", "model.layers.28.input_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00022-of-00025.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00022-of-00025.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00022-of-00025.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00022-of-00025.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00022-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00023-of-00025.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00023-of-00025.safetensors", "model.layers.29.input_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00023-of-00025.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00023-of-00025.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00023-of-00025.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00025.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00025.safetensors", "model.layers.30.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00025.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00025.safetensors", "model.layers.31.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00025-of-00025.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00025-of-00025.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00025-of-00025.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00025-of-00025.safetensors"}}
special_tokens_map.json 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
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{% if message['role'] == 'user' %}{{ bos_token + '\n<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>\n' + message['content'] + eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "max_length": 2048,
37
+ "model_max_length": 1000000000000000019884624838656,
38
+ "pad_to_multiple_of": null,
39
+ "pad_token": "<s>",
40
+ "pad_token_type_id": 0,
41
+ "padding_side": "left",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "stride": 0,
45
+ "tokenizer_class": "LlamaTokenizer",
46
+ "truncation_side": "right",
47
+ "truncation_strategy": "longest_first",
48
+ "unk_token": "<unk>",
49
+ "use_default_system_prompt": true
50
+ }