Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
burtenshaw
/
Qwen1.5-0.5B-dpo-mix-7k
like
0
Text Generation
Transformers
Safetensors
English
qwen2
conversational
Eval Results
text-generation-inference
Inference Endpoints
arxiv:
1910.09700
License:
mit
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
b00caa3
Qwen1.5-0.5B-dpo-mix-7k
/
Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-3-7-44
/
generation_config.json
burtenshaw
HF staff
Upload folder using huggingface_hub
b00caa3
verified
7 months ago
raw
Copy download link
history
blame
Safe
117 Bytes
{
"bos_token_id"
:
151643
,
"eos_token_id"
:
151643
,
"max_new_tokens"
:
2048
,
"transformers_version"
:
"4.38.2"
}