Text Generation
Transformers
PyTorch
English
llama
causal-lm
text-generation-inference
Inference Endpoints
jon-tow commited on
Commit
d370485
1 Parent(s): fa68c81

cleanup: final edits

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -60,8 +60,8 @@ print(tokenizer.decode(tokens[0], skip_special_tokens=True))
60
  * **Language(s)**: English
61
  * **Library**: [trlX](https://github.com/CarperAI/trlx)
62
  * **License for delta weights**: [CC-BY-NC-SA-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/)
63
- * *Note*: License for the base LLaMA model's weights is Meta's [non-commercial bespoke license](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md).
64
- * **Contact**: For questions and comments about the model, visit the [StableFoundation](https://discord.gg/stablediffusion) and [CarperAI](https://discord.com/invite/KgfkCVYHdu) Discord servers.
65
 
66
  | Hyperparameter | Value |
67
  |---------------------------|-------|
@@ -81,7 +81,7 @@ The reward model used during RLHF was also trained on [OpenAssistant Conversatio
81
 
82
  ### Training Procedure
83
 
84
- `CarperAI/sstable-vicuna-13b-delta` was trained using PPO as implemented in [`trlX`](https://github.com/CarperAI/trlx/blob/main/trlx/trainer/accelerate_ppo_trainer.py) with the following configuration:
85
 
86
  | Hyperparameter | Value |
87
  |-------------------|---------|
 
60
  * **Language(s)**: English
61
  * **Library**: [trlX](https://github.com/CarperAI/trlx)
62
  * **License for delta weights**: [CC-BY-NC-SA-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/)
63
+ * *Note*: License for the base LLaMA model's weights is Meta's [non-commercial bespoke license](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md).
64
+ * **Contact**: For questions and comments about the model, visit the [CarperAI](https://discord.com/invite/KgfkCVYHdu) and [StableFoundation](https://discord.gg/stablediffusion) Discord servers.
65
 
66
  | Hyperparameter | Value |
67
  |---------------------------|-------|
 
81
 
82
  ### Training Procedure
83
 
84
+ `CarperAI/stable-vicuna-13b-delta` was trained using PPO as implemented in [`trlX`](https://github.com/CarperAI/trlx/blob/main/trlx/trainer/accelerate_ppo_trainer.py) with the following configuration:
85
 
86
  | Hyperparameter | Value |
87
  |-------------------|---------|