Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Pinkstackorg
/
PinkQwen2.5-3B-1M-DPO-preview
like
0
Follow
Pinkstack-org
1
Text Generation
Transformers
PyTorch
Safetensors
English
qwen2
text-generation-inference
unsloth
trl
dpo
conversational
License:
apache-2.0
Model card
Files
Files and versions
Community
1
Train
Deploy
Use this model
refs/pr/1
PinkQwen2.5-3B-1M-DPO-preview
/
generation_config.json
Pinkstack
Trained with Unsloth
7298720
verified
11 days ago
raw
Copy download link
history
blame
172 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
151643
,
"eos_token_id"
:
151645
,
"max_length"
:
1010000
,
"pad_token_id"
:
151643
,
"transformers_version"
:
"4.51.1"
}