susumuota commited on
Commit
ae7dcbc
1 Parent(s): 322b49f

Upload MixtralForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/storage7/finetune/Mixtral_3node_finetune_all_v6/epoch2/convert_no_rope",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2048,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4096,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 40,
18
+ "num_key_value_heads": 32,
19
+ "num_local_experts": 8,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 500000,
24
+ "router_aux_loss_coef": 0.02,
25
+ "router_jitter_noise": 0.0,
26
+ "sliding_window": null,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.40.1",
30
+ "use_cache": true,
31
+ "vocab_size": 56320
32
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.40.1"
6
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b7d4ac2d9d09e928acf6736704dde773faa50d936592459ef1d0b4a076b8785
3
+ size 4995901320
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d45b77d9c356fca2ed0db5c078d4cc0d7a1c75ba83a0fa89c0c85f3f98e7331
3
+ size 4983370216
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3de9c5cd04c7996ebba63e51ece658bc3b7f65604e8cadef6b7d7faf74d5471c
3
+ size 4983328704
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fb2412832677aca2ed3bfbd6e7aec4017c89be5dfc256b8d087d58e11f9c270
3
+ size 2948878704
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff