Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
u-10bei
/
llm-jp-3-13b-instruct2-chat-sft1_4-grpo2_2-merged
like
0
Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
unsloth
trl
conversational
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Train
Deploy
Use this model
b443eaa
llm-jp-3-13b-instruct2-chat-sft1_4-grpo2_2-merged
/
generation_config.json
u-10bei
(Trained with Unsloth)
b443eaa
verified
5 months ago
raw
Copy download link
history
blame
Safe
154 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
1
,
"eos_token_id"
:
2
,
"max_length"
:
4096
,
"pad_token_id"
:
4
,
"transformers_version"
:
"4.49.0"
}