Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
PrunaAI
/
mergekit-community-Qwen2.5Minus2-0.5B-Instruct-bnb-8bit-smashed
like
0
Follow
Pruna AI
159
Safetensors
qwen2
pruna-ai
8-bit precision
bitsandbytes
Model card
Files
Files and versions
Community
2
b7a2bfb
mergekit-community-Qwen2.5Minus2-0.5B-Instruct-bnb-8bit-smashed
/
generation_config.json
sharpenb
Upload folder using huggingface_hub (
#1
)
b7a2bfb
verified
about 1 month ago
raw
Copy download link
history
blame
Safe
121 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
151643
,
"eos_token_id"
:
151645
,
"transformers_version"
:
"4.46.2"
}