mychen76 commited on
Commit
c1a0afc
1 Parent(s): 91a7aa6

Upload folder using huggingface_hub

Browse files
.ipynb_checkpoints/README-checkpoint.md ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ ---
6
+
7
+ # openmixtral-4x7b-merged
8
+
9
+ openmixtral-4x7b-merged is a merge of the following models:
10
+
11
+ ## 🧩 Configuration
12
+
13
+ ```yaml
14
+ base_model: mlabonne/Marcoro14-7B-slerp
15
+ experts:
16
+ - source_model: openchat/openchat-3.5-1210
17
+ positive_prompts:
18
+ - "chat"
19
+ - "assistant"
20
+ - "tell me"
21
+ - "explain"
22
+ - source_model: beowolx/CodeNinja-1.0-OpenChat-7B
23
+ positive_prompts:
24
+ - "code"
25
+ - "python"
26
+ - "javascript"
27
+ - "programming"
28
+ - "algorithm"
29
+ - source_model: maywell/PiVoT-0.1-Starling-LM-RP
30
+ positive_prompts:
31
+ - "storywriting"
32
+ - "write"
33
+ - "scene"
34
+ - "story"
35
+ - "character"
36
+ - source_model: WizardLM/WizardMath-7B-V1.1
37
+ positive_prompts:
38
+ - "reason"
39
+ - "math"
40
+ - "mathematics"
41
+ - "solve"
42
+ - "count"
43
+ tokenizer_source: union
44
+ ```
README.md ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ ---
6
+
7
+ # openmixtral-4x7b-merged
8
+
9
+ openmixtral-4x7b-merged is a merge of the following models:
10
+
11
+ ## 🧩 Configuration
12
+
13
+ ```yaml
14
+ base_model: mlabonne/Marcoro14-7B-slerp
15
+ experts:
16
+ - source_model: openchat/openchat-3.5-1210
17
+ positive_prompts:
18
+ - "chat"
19
+ - "assistant"
20
+ - "tell me"
21
+ - "explain"
22
+ - source_model: beowolx/CodeNinja-1.0-OpenChat-7B
23
+ positive_prompts:
24
+ - "code"
25
+ - "python"
26
+ - "javascript"
27
+ - "programming"
28
+ - "algorithm"
29
+ - source_model: maywell/PiVoT-0.1-Starling-LM-RP
30
+ positive_prompts:
31
+ - "storywriting"
32
+ - "write"
33
+ - "scene"
34
+ - "story"
35
+ - "character"
36
+ - source_model: WizardLM/WizardMath-7B-V1.1
37
+ positive_prompts:
38
+ - "reason"
39
+ - "math"
40
+ - "mathematics"
41
+ - "solve"
42
+ - "count"
43
+ tokenizer_source: union
44
+ ```
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mlabonne/Marcoro14-7B-slerp",
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": 10000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ base_model: mlabonne/Marcoro14-7B-slerp
3
+ experts:
4
+ - source_model: openchat/openchat-3.5-1210
5
+ positive_prompts:
6
+ - "chat"
7
+ - "assistant"
8
+ - "tell me"
9
+ - "explain"
10
+ - source_model: beowolx/CodeNinja-1.0-OpenChat-7B
11
+ positive_prompts:
12
+ - "code"
13
+ - "python"
14
+ - "javascript"
15
+ - "programming"
16
+ - "algorithm"
17
+ - source_model: maywell/PiVoT-0.1-Starling-LM-RP
18
+ positive_prompts:
19
+ - "storywriting"
20
+ - "write"
21
+ - "scene"
22
+ - "story"
23
+ - "character"
24
+ - source_model: WizardLM/WizardMath-7B-V1.1
25
+ positive_prompts:
26
+ - "reason"
27
+ - "math"
28
+ - "mathematics"
29
+ - "solve"
30
+ - "count"
31
+ tokenizer_source: union
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f08a24c9804c646205039f13c5f6028f691ccd25478852fdc7ec7f222f7d686
3
+ size 9919666872
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bec4aa7d027100df7f33c574141ddfc52c3285b6c617fc1afa45d20abc0e063
3
+ size 9898670488
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58f11f7760c0c3fa0555516182cd15c271b1a32f13a9a6688f3d23df72ff09cf
3
+ size 9982573720
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e1633569062886d354abda470c263dabbb25e8d2aec63372b72e1d9c4289b04
3
+ size 9982573720
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04a24d81140ab5566eb16ecde828af7ede094123c38cb45c39b135637d57abce
3
+ size 8523972544
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-00005.safetensors", "model.norm.weight": "model-00001-of-00005.safetensors", "lm_head.weight": "model-00001-of-00005.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00005.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00005.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00005.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00005.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00005.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00005.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00005.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00005.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00005.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00005.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00005.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00005.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00005-of-00005.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": "<s>",
22
+ "unk_token": {
23
+ "content": "<unk>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
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 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "clean_up_tokenization_spaces": false,
37
+ "eos_token": "</s>",
38
+ "legacy": true,
39
+ "model_max_length": 1000000000000000019884624838656,
40
+ "pad_token": "<s>",
41
+ "sp_model_kwargs": {},
42
+ "spaces_between_special_tokens": false,
43
+ "tokenizer_class": "LlamaTokenizer",
44
+ "unk_token": "<unk>",
45
+ "use_default_system_prompt": true
46
+ }