Hugging Face's logo

YzZ-George
/
DeepSpeed-Chat-OPT-1.3B-3-3-3datasets

Model card Files Community
YzZ-George commited on
Commit
f6bbb6e
•
1 Parent(s): 42855f8

Upload 13 files

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. actor/config.json +32 -0
  3. actor/merges.txt +0 -0
  4. actor/pytorch_model.bin +3 -0
  5. actor/vocab.json +0 -0
  6. actor_ema/config.json +32 -0
  7. actor_ema/merges.txt +0 -0
  8. actor_ema/pytorch_model.bin +3 -0
  9. actor_ema/vocab.json +0 -0
  10. critic/config.json +32 -0
  11. critic/merges.txt +0 -0
  12. critic/pytorch_model.bin +3 -0
  13. critic/vocab.json +0 -0
  14. training.log +3 -0
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ training.log filter=lfs diff=lfs merge=lfs -text
actor/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/zhaiyuanzhao/code/DeepSpeedExamples/applications/DeepSpeed-Chat/training/step1_supervised_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": true,
12
+ "dropout": 0.0,
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/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 sha256:07ed86fdf8d3dc4bc45d1f04bf7c1b1c36ae6a309eb36669ef51a43c42391f1a
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",
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/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8479f2192e5fd39c7aa5cc9b20cfc79df471bdeda311c9588816ce29addc68a9
3
+ size 2631663773
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 sha256:61f4817617bf15201ef08c449b261322edf2faa5cb47c554b46ecb545fd90e2c
3
+ size 662469311
critic/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c655518bf5e313a708eac1e18a62b428e038d2f137bed5605641fe49f83f395b
3
+ size 12147983