Upload folder using huggingface_hub
Browse files- added_tokens.json +4 -0
- config.json +32 -0
- mergekit_moe_config.yml +13 -0
- model-00001-of-00007.safetensors +3 -0
- model-00002-of-00007.safetensors +3 -0
- model-00003-of-00007.safetensors +3 -0
- model-00004-of-00007.safetensors +3 -0
- model-00005-of-00007.safetensors +3 -0
- model-00006-of-00007.safetensors +3 -0
- model-00007-of-00007.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +62 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|im_end|>": 32000,
|
3 |
+
"<|im_start|>": 32001
|
4 |
+
}
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "C:/Users/Jacoby/Downloads/text-generation-webui-main/models/BAAI_Infinity-Instruct-7M-Gen-mistral-7B",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 32000,
|
9 |
+
"head_dim": 128,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 14336,
|
14 |
+
"max_position_embeddings": 32768,
|
15 |
+
"model_type": "mixtral",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_experts_per_tok": 2,
|
18 |
+
"num_hidden_layers": 32,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"num_local_experts": 4,
|
21 |
+
"output_router_logits": false,
|
22 |
+
"rms_norm_eps": 1e-05,
|
23 |
+
"rope_theta": 10000.0,
|
24 |
+
"router_aux_loss_coef": 0.001,
|
25 |
+
"router_jitter_noise": 0.0,
|
26 |
+
"sliding_window": null,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"torch_dtype": "float16",
|
29 |
+
"transformers_version": "4.44.2",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 32002
|
32 |
+
}
|
mergekit_moe_config.yml
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
base_model: C:/Users/Jacoby/Downloads/text-generation-webui-main/models/BAAI_Infinity-Instruct-7M-Gen-mistral-7B
|
3 |
+
dtype: float16
|
4 |
+
gate_mode: cheap_embed
|
5 |
+
experts:
|
6 |
+
- source_model: C:/Users/Jacoby/Downloads/text-generation-webui-main/models/senseable_WestLake-7B-v2
|
7 |
+
positive_prompts: ["You are a roleplay assistant, who excels at logical reasoning and incorporating past details into your responses."]
|
8 |
+
- source_model: C:/Users/Jacoby/Downloads/text-generation-webui-main/models/SanjiWatsuki_Kunoichi-DPO-v2-7B
|
9 |
+
positive_prompts: ["You are a creative roleplay assistant who is an expert at crafting engaging and interactive stories, bringing a flavor and style of writing all your own."]
|
10 |
+
- source_model: C:/Users/Jacoby/Downloads/text-generation-webui-main/models/Gryphe_Tiamat-7b-1.1-DPO
|
11 |
+
positive_prompts: ["You are a negative emotion expert, the id to the ego. Not everything is positive. You handle character's emotions and ensure a realistic and well-rounded character for roleplay."]
|
12 |
+
- source_model: C:/Users/Jacoby/Downloads/text-generation-webui-main/models/uukuguy_speechless-instruct-mistral-7b-v0.2
|
13 |
+
positive_prompts: ["You are an expert of foresight and logical reasoning, and will guide characters thoughts, actions, and ambitions."]
|
model-00001-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52bdf176c8a2ce72c8649e1cc5de5096df2b4a79a4c4bf95c3d2c4da65acdd00
|
3 |
+
size 7923355424
|
model-00002-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02b92a77c7e3dde4ac00201e9301df4d0ffe6e2f24023170e49cc9a5d514555e
|
3 |
+
size 7985963736
|
model-00003-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3be9440d595ff8665f4f27a01fc586d201837494f202e6a8fdbf99307a555f4
|
3 |
+
size 7985963704
|
model-00004-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c093c322f347cfaa7c3f63b1fffd23a6b34ca941786d4e186932254afcbf581c
|
3 |
+
size 7985963728
|
model-00005-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:628ca5333a9621112e1189233ca932cc682f54226daa7891cf3130388f7ae432
|
3 |
+
size 7985963712
|
model-00006-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f55754601d63df6e0be2270dd03f27870f1cf7ed7265b0a46949c9009eb1241f
|
3 |
+
size 7969463192
|
model-00007-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fd5f416d9ddf649e0111c549307234bdf87503992a9f33cc28bda55a0e192f3
|
3 |
+
size 470815920
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00007.safetensors", "model.norm.weight": "model-00001-of-00007.safetensors", "lm_head.weight": "model-00001-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00007-of-00007.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|im_end|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.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 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|im_end|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|im_start|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"additional_special_tokens": [],
|
48 |
+
"bos_token": "<s>",
|
49 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
50 |
+
"clean_up_tokenization_spaces": false,
|
51 |
+
"eos_token": "<|im_end|>",
|
52 |
+
"legacy": true,
|
53 |
+
"model_max_length": 1000000000000000019884624838656,
|
54 |
+
"pad_token": "<s>",
|
55 |
+
"sp_model_kwargs": {},
|
56 |
+
"spaces_between_special_tokens": false,
|
57 |
+
"tokenizer_class": "LlamaTokenizer",
|
58 |
+
"trust_remote_code": false,
|
59 |
+
"unk_token": "<unk>",
|
60 |
+
"use_default_system_prompt": true,
|
61 |
+
"use_fast": true
|
62 |
+
}
|