Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
HuangXinBa
/
GRPO
like
1
Text Generation
Safetensors
gsm8k
English
llama
causal-lm
reinforcement-learning
GRPO
instruction-tuning
chain-of-thought
conversational
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
3bbfa9a
GRPO
/
generation_config.json
HuangXinBa
Upload LlamaForCausalLM
33bf48c
verified
3 months ago
raw
Copy download link
history
blame
Safe
164 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
1
,
"eos_token_id"
:
2
,
"max_new_tokens"
:
40
,
"pad_token_id"
:
2
,
"transformers_version"
:
"4.47.1"
}