yentinglin commited on
Commit
b09beee
1 Parent(s): e628178

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/home/f08944064/.cache/huggingface/hub/models--yentinglin--Taiwan-LLM-8x7B-DPO/snapshots/122a34917053003240a8390115c75105916e7986",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 32000,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 8,
20
+ "output_router_logits": false,
21
+ "quantization_config": {
22
+ "bits": 4,
23
+ "group_size": 128,
24
+ "modules_to_not_convert": [
25
+ "gate"
26
+ ],
27
+ "quant_method": "awq",
28
+ "version": "gemm",
29
+ "zero_point": true
30
+ },
31
+ "rms_norm_eps": 1e-05,
32
+ "rope_theta": 1000000.0,
33
+ "router_aux_loss_coef": 0.02,
34
+ "sliding_window": null,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "float16",
37
+ "transformers_version": "4.38.2",
38
+ "use_cache": false,
39
+ "vocab_size": 32002
40
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 32000,
6
+ "transformers_version": "4.38.2"
7
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70c6efae69420c65e33e991a5a91931ce562448448c1203b3888d41e63bb6234
3
+ size 4991373216
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:765cafbced4f5b8a0a4c97435d7c2905f61a3629bb9a93085f6a70e8ae5f6993
3
+ size 4981921768
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbf1abe6991aebf5ce02a7995589d5b3511f397eaffa4ca97141b5750768c8d2
3
+ size 4973289064
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c78fcc65b49395ec798d476a5825eb3ce01127b5d1f392ca4116c6e747b29462
3
+ size 4973289080
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cce2adcf1846b25d311588219598ae92f3b78b377302871c0864312f56ff098
3
+ size 4734114760
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff