Upload folder using huggingface_hub
Browse files- config.json +6 -6
- mergekit_moe_config.yml +15 -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 +0 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +2 -2
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"MixtralForCausalLM"
|
5 |
],
|
@@ -10,7 +10,7 @@
|
|
10 |
"hidden_size": 4096,
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 14336,
|
13 |
-
"max_position_embeddings":
|
14 |
"model_type": "mixtral",
|
15 |
"num_attention_heads": 32,
|
16 |
"num_experts_per_tok": 2,
|
@@ -19,12 +19,12 @@
|
|
19 |
"num_local_experts": 4,
|
20 |
"output_router_logits": false,
|
21 |
"rms_norm_eps": 1e-05,
|
22 |
-
"rope_theta":
|
23 |
-
"router_aux_loss_coef": 0.
|
24 |
-
"sliding_window":
|
25 |
"tie_word_embeddings": false,
|
26 |
"torch_dtype": "bfloat16",
|
27 |
-
"transformers_version": "4.
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 32000
|
30 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "stabilityai/japanese-stablelm-base-gamma-7b",
|
3 |
"architectures": [
|
4 |
"MixtralForCausalLM"
|
5 |
],
|
|
|
10 |
"hidden_size": 4096,
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 4096,
|
14 |
"model_type": "mixtral",
|
15 |
"num_attention_heads": 32,
|
16 |
"num_experts_per_tok": 2,
|
|
|
19 |
"num_local_experts": 4,
|
20 |
"output_router_logits": false,
|
21 |
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
+
"router_aux_loss_coef": 0.001,
|
24 |
+
"sliding_window": null,
|
25 |
"tie_word_embeddings": false,
|
26 |
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.36.2",
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 32000
|
30 |
}
|
mergekit_moe_config.yml
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
base_model: stabilityai/japanese-stablelm-base-gamma-7b
|
2 |
+
gate_mode: random
|
3 |
+
experts:
|
4 |
+
- source_model: stabilityai/japanese-stablelm-base-gamma-7b
|
5 |
+
positive_prompts:
|
6 |
+
- ""
|
7 |
+
- source_model: stabilityai/japanese-stablelm-base-gamma-7b
|
8 |
+
positive_prompts:
|
9 |
+
- ""
|
10 |
+
- source_model: stabilityai/japanese-stablelm-base-gamma-7b
|
11 |
+
positive_prompts:
|
12 |
+
- ""
|
13 |
+
- source_model: stabilityai/japanese-stablelm-base-gamma-7b
|
14 |
+
positive_prompts:
|
15 |
+
- ""
|
model-00001-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64797d5b1966d01b09c88276af83c1f7ed48ef8b931aab2987b8369fe6bed18b
|
3 |
+
size 9919813704
|
model-00002-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f880eded26eb7956b3eedae60fef15de0648cff4bcc068b715cb85b4515917c
|
3 |
+
size 9982454720
|
model-00003-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ae7e7967a196d90784eb7359797339ef4560841eaf23f035fba3073e5da721c
|
3 |
+
size 9982454752
|
model-00004-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:996ab3f39c3d8e6391998ed7f66aef6de26427c0e312ae8fce07ca5f6e031061
|
3 |
+
size 9982454720
|
model-00005-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09d31b98bc2e8cfb0aa5598ec43ebcb08653b93ed0fd33e02ee024f350dcd77e
|
3 |
+
size 8440279464
|
model.safetensors.index.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
CHANGED
@@ -13,6 +13,7 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
|
|
16 |
"unk_token": {
|
17 |
"content": "<unk>",
|
18 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "<s>",
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -33,10 +33,10 @@
|
|
33 |
"eos_token": "</s>",
|
34 |
"legacy": true,
|
35 |
"model_max_length": 1000000000000000019884624838656,
|
36 |
-
"pad_token":
|
37 |
"sp_model_kwargs": {},
|
38 |
"spaces_between_special_tokens": false,
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
40 |
"unk_token": "<unk>",
|
41 |
-
"use_default_system_prompt":
|
42 |
}
|
|
|
33 |
"eos_token": "</s>",
|
34 |
"legacy": true,
|
35 |
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": "<s>",
|
37 |
"sp_model_kwargs": {},
|
38 |
"spaces_between_special_tokens": false,
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
40 |
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": true
|
42 |
}
|