Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
osllmai-community
/
Qwen2.5-14B-bnb-4bit
like
0
Follow
osllmai-community
6
Text Generation
Transformers
Safetensors
English
qwen2
unsloth
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
arxiv:
2407.10671
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
e383607
Qwen2.5-14B-bnb-4bit
/
generation_config.json
alinemati
Upload generation_config.json
d11a2db
verified
about 1 month ago
raw
Copy download link
history
blame
Safe
167 Bytes
{
"bos_token_id"
:
151643
,
"eos_token_id"
:
151643
,
"max_length"
:
131072
,
"max_new_tokens"
:
2048
,
"pad_token_id"
:
151665
,
"transformers_version"
:
"4.44.2"
}