Adam commited on
Commit
2149817
1 Parent(s): 11979a6

feat: added actor model

Browse files
Files changed (5) hide show
  1. README.md +1 -1
  2. config.json +32 -0
  3. merges.txt +0 -0
  4. pytorch_model.bin +3 -0
  5. vocab.json +0 -0
README.md CHANGED
@@ -13,7 +13,7 @@ license: apache-2.0
13
 
14
  # ChatGPT OPT 1.3B DeepSpeed Reinforcement Learning from Human feedback
15
 
16
- *fsalab-chat-opt-1.3b-rlhf-deepspeed*
17
 
18
  This model consists of the final step of a modified pipeline the to the traditional training process of Chat-GPT models, which is comprised of a three-step procedure of [supervised fine tuning](https://huggingface.co/FSALab/fsalab-chat-opt-1.3b-sft-deepspeed), [reward model](https://huggingface.co/FSALab/fsalab-chat-opt-350m-reward-deepspeed) and **reinforcement learning from human feedback**.
19
 
 
13
 
14
  # ChatGPT OPT 1.3B DeepSpeed Reinforcement Learning from Human feedback
15
 
16
+ *fsalab-chat-opt-1.3b-rlhf-actor-deepspeed*
17
 
18
  This model consists of the final step of a modified pipeline the to the traditional training process of Chat-GPT models, which is comprised of a three-step procedure of [supervised fine tuning](https://huggingface.co/FSALab/fsalab-chat-opt-1.3b-sft-deepspeed), [reward model](https://huggingface.co/FSALab/fsalab-chat-opt-350m-reward-deepspeed) and **reinforcement learning from human feedback**.
19
 
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/lus/grand/projects/BNN-Scale/chatgpt/hf_runs/DeepSpeedExamples/applications/DeepSpeed-Chat/output/actor-models/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": 0.0,
13
+ "enable_bias": true,
14
+ "end_token_id": 50260,
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": "4.29.0.dev0",
29
+ "use_cache": true,
30
+ "vocab_size": 50272,
31
+ "word_embed_proj_dim": 2048
32
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cbb17038fa906783a3dee89e31c89c1cef03cea47723a5f065cc7b78ca37c89
3
+ size 3235869199
vocab.json ADDED
The diff for this file is too large to render. See raw diff