Hugging Face's logo

YzZ-George
/
DeepSpeed-Chat-OPT-1.3B-4-4-1datasets

Model card Files Community
YzZ-George commited on
Commit
3240870
•
1 Parent(s): be295e3

Upload 11 files

Browse files
Files changed (11) hide show
  1. actor/merges.txt +0 -0
  2. actor/pytorch_model.bin +3 -0
  3. actor/vocab.json +0 -0
  4. actor_ema/config.json +32 -0
  5. actor_ema/merges.txt +0 -0
  6. actor_ema/vocab.json +0 -0
  7. critic/config.json +32 -0
  8. critic/merges.txt +0 -0
  9. critic/pytorch_model.bin +3 -0
  10. critic/vocab.json +0 -0
  11. training.log +0 -0
actor/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
actor/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fec4509b96e334db705e478b5f9a81fe73c5e05d91a6f22e9bef9e623c00d1a2
3
+ size 3235870087
actor/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
actor_ema/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/zhaiyuanzhao/code/DeepSpeedExamples/applications/DeepSpeed-Chat/training/step1_supervised_finetuning/output-1.3b",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "end_token_id": 2,
15
+ "eos_token_id": 2,
16
+ "ffn_dim": 8192,
17
+ "hidden_size": 2048,
18
+ "init_std": 0.02,
19
+ "layer_norm_elementwise_affine": true,
20
+ "layerdrop": 0.0,
21
+ "max_position_embeddings": 2048,
22
+ "model_type": "opt",
23
+ "num_attention_heads": 32,
24
+ "num_hidden_layers": 24,
25
+ "pad_token_id": 2,
26
+ "prefix": "</s>",
27
+ "torch_dtype": "float16",
28
+ "transformers_version": "4.30.0.dev0",
29
+ "use_cache": true,
30
+ "vocab_size": 50272,
31
+ "word_embed_proj_dim": 2048
32
+ }
actor_ema/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
actor_ema/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
critic/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/zhaiyuanzhao/code/DeepSpeedExamples/applications/DeepSpeed-Chat/training/step2_reward_model_finetuning/output",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": false,
12
+ "dropout": 0.0,
13
+ "enable_bias": true,
14
+ "end_token_id": 2,
15
+ "eos_token_id": 2,
16
+ "ffn_dim": 4096,
17
+ "hidden_size": 1024,
18
+ "init_std": 0.02,
19
+ "layer_norm_elementwise_affine": true,
20
+ "layerdrop": 0.0,
21
+ "max_position_embeddings": 2048,
22
+ "model_type": "opt",
23
+ "num_attention_heads": 16,
24
+ "num_hidden_layers": 24,
25
+ "pad_token_id": 2,
26
+ "prefix": "</s>",
27
+ "torch_dtype": "float16",
28
+ "transformers_version": "4.30.0.dev0",
29
+ "use_cache": true,
30
+ "vocab_size": 50272,
31
+ "word_embed_proj_dim": 512
32
+ }
critic/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
critic/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a0f87ef3ae6d339fe4ecf1f4c38db085b87ea252cdfd60f7952e89702e1fffe
3
+ size 662469311
critic/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
The diff for this file is too large to render. See raw diff