Hugging Face's logo

NickyNicky
/
Llama-1B-base-GRPO-RAG-NEWS-SPANISH-v2

Text Generation
Transformers
Safetensors
Spanish
llama
finance
conversational
text-generation-inference
Model card Files Community
NickyNicky commited on
Commit
d6f4039
·
verified ·
1 Parent(s): 916f975

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -31,6 +31,7 @@ The responses are shorter depending on the 'prompt'
31
  Responds better to Spanish and is more proficient in cryptocurrency news
32
  knows more about interpreting what the user asks for in Spanish
33
  the previous model 'NickyNicky/Llama-1B-base-GRPO-RAG-NEWS-SPANISH' towards inference of more tokens. The v2 model responds shorter but with what the user requests.
 
34
  ```
35
 
36
  <!-- https://wandb.ai/multimodal_master/huggingface/runs/3fl5oqaw/workspace?nw=nwusertrainllms -->
 
31
  Responds better to Spanish and is more proficient in cryptocurrency news
32
  knows more about interpreting what the user asks for in Spanish
33
  the previous model 'NickyNicky/Llama-1B-base-GRPO-RAG-NEWS-SPANISH' towards inference of more tokens. The v2 model responds shorter but with what the user requests.
34
+ controlling sharp rises 'kl', 'loss' and 'grad_norm with 'bleu_reward_func'
35
  ```
36
 
37
  <!-- https://wandb.ai/multimodal_master/huggingface/runs/3fl5oqaw/workspace?nw=nwusertrainllms -->