Upload folder using huggingface_hub
Browse files- config.json +35 -0
- mergekit_moe_config.yml +75 -0
- model-00001-of-00005.safetensors +3 -0
- model-00002-of-00005.safetensors +3 -0
- model-00003-of-00005.safetensors +3 -0
- model-00004-of-00005.safetensors +3 -0
- model-00005-of-00005.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +2 -1
- tokenizer_config.json +1 -0
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": 128009,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 14336,
|
14 |
+
"max_position_embeddings": 8192,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "mixtral",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_experts_per_tok": 2,
|
19 |
+
"num_hidden_layers": 32,
|
20 |
+
"num_key_value_heads": 8,
|
21 |
+
"num_local_experts": 4,
|
22 |
+
"output_router_logits": false,
|
23 |
+
"pretraining_tp": 1,
|
24 |
+
"rms_norm_eps": 1e-05,
|
25 |
+
"rope_scaling": null,
|
26 |
+
"rope_theta": 500000.0,
|
27 |
+
"router_aux_loss_coef": 0.001,
|
28 |
+
"router_jitter_noise": 0.0,
|
29 |
+
"sliding_window": null,
|
30 |
+
"tie_word_embeddings": false,
|
31 |
+
"torch_dtype": "bfloat16",
|
32 |
+
"transformers_version": "4.41.2",
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 128256
|
35 |
+
}
|
mergekit_moe_config.yml
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
3 |
+
gate_mode: random
|
4 |
+
dtype: bfloat16
|
5 |
+
experts_per_token: 2
|
6 |
+
experts:
|
7 |
+
- source_model: meta-llama/Meta-Llama-3-8B-Instruct
|
8 |
+
positive_prompts:
|
9 |
+
- "What are the different"
|
10 |
+
- "what are the distinct"
|
11 |
+
- "Give me the unique"
|
12 |
+
- source_model: meta-llama/Meta-Llama-3-8B-Instruct
|
13 |
+
positive_prompts:
|
14 |
+
- "When"
|
15 |
+
- "when"
|
16 |
+
- "Where"
|
17 |
+
- "where"
|
18 |
+
- "Which"
|
19 |
+
- "which"
|
20 |
+
- "Who"
|
21 |
+
- "who"
|
22 |
+
- "What"
|
23 |
+
- "what"
|
24 |
+
- "Whom"
|
25 |
+
- "whom"
|
26 |
+
- "Whose"
|
27 |
+
- "whose"
|
28 |
+
- source_model: meta-llama/Meta-Llama-3-8B-Instruct
|
29 |
+
positive_prompts:
|
30 |
+
- "Larger"
|
31 |
+
- "larger"
|
32 |
+
- "Smaller"
|
33 |
+
- "smaller"
|
34 |
+
- "Bigger"
|
35 |
+
- "bigger"
|
36 |
+
- "Smallest"
|
37 |
+
- "smallest"
|
38 |
+
- "Largest"
|
39 |
+
- "largest"
|
40 |
+
- "Biggest"
|
41 |
+
- "biggest"
|
42 |
+
- "Most"
|
43 |
+
- "most"
|
44 |
+
- "Least"
|
45 |
+
- "least"
|
46 |
+
- "More"
|
47 |
+
- "more"
|
48 |
+
- "Less"
|
49 |
+
- "less"
|
50 |
+
- "Number"
|
51 |
+
- "number"
|
52 |
+
- "Numbers"
|
53 |
+
- "numbers"
|
54 |
+
- "Quantity"
|
55 |
+
- "quantity"
|
56 |
+
- "At least"
|
57 |
+
- "at least"
|
58 |
+
- "At most"
|
59 |
+
- "at most"
|
60 |
+
- "Greater"
|
61 |
+
- "greater"
|
62 |
+
- "Fewer"
|
63 |
+
- "fewer"
|
64 |
+
- "Than"
|
65 |
+
- "than"
|
66 |
+
- "Equal"
|
67 |
+
- "equal"
|
68 |
+
- "Same"
|
69 |
+
- "same"
|
70 |
+
- "Equal to"
|
71 |
+
- "equal to"
|
72 |
+
- source_model: meta-llama/Meta-Llama-3-8B-Instruct
|
73 |
+
positive_prompts:
|
74 |
+
- "that also"
|
75 |
+
- "who have the same"
|
model-00001-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:072c49ec463ff25981a001d196343a0b76b6bd5b418b24ec583cc581c6d86792
|
3 |
+
size 9970143648
|
model-00002-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25ff4fcb7e677a20079a6e95ef607c6baea5c437ed48cbe228383fb9af9a46ba
|
3 |
+
size 9982454736
|
model-00003-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:803ca309c8e7345bcb1505a36de25995c50c000deac4522a5278059ed14066b0
|
3 |
+
size 9982454744
|
model-00004-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e036e2c218f0d931258480de1ef9b3c0d24b33a28b6383be752b07fef6696ea
|
3 |
+
size 9982454720
|
model-00005-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db59b9799f71efb337f80cebcf9a00874e2ec27334969a68a9ccdd45ec14ade0
|
3 |
+
size 9967007856
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4"}, "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.1.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.31.input_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.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.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.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.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.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.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-00001-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.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.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.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.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.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.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.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00005.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00005.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00005.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00005.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.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.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.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.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.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.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.0.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.31.self_attn.o_proj.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
CHANGED
@@ -12,5 +12,6 @@
|
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
-
}
|
|
|
16 |
}
|
|
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|begin_of_text|>"
|
17 |
}
|
tokenizer_config.json
CHANGED
@@ -2058,5 +2058,6 @@
|
|
2058 |
"attention_mask"
|
2059 |
],
|
2060 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
2061 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2062 |
}
|
|
|
2058 |
"attention_mask"
|
2059 |
],
|
2060 |
"model_max_length": 1000000000000000019884624838656,
|
2061 |
+
"pad_token": "<|begin_of_text|>",
|
2062 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
}
|