Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
LoftQ
/
Meta-Llama-3-70B-4bit-64rank
like
1
Text Generation
Transformers
Safetensors
English
llama
quantization
lora
loftq
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
arxiv:
2310.08659
License:
mit
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
7203303
Meta-Llama-3-70B-4bit-64rank
/
generation_config.json
LoftQ
Upload folder using huggingface_hub
b740bbf
verified
5 months ago
raw
Copy download link
history
blame
No virus
121 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
128000
,
"eos_token_id"
:
128001
,
"transformers_version"
:
"4.40.0"
}