Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
TheBloke
/
Mistral-7B-Instruct-v0.2-GPTQ
like
40
Text Generation
Transformers
Safetensors
mistral
finetuned
conversational
text-generation-inference
4-bit precision
arxiv:
2310.06825
License:
apache-2.0
Model card
Files
Files and versions
Community
4
Train
Deploy
Use this model
gptq-8bit-128g-actorder_True
Mistral-7B-Instruct-v0.2-GPTQ
/
special_tokens_map.json
TheBloke
GPTQ model commit
0ebf7fd
6 months ago
raw
history
blame
No virus
72 Bytes
{
"bos_token"
:
"<s>"
,
"eos_token"
:
"</s>"
,
"unk_token"
:
"<unk>"
}