Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
TheBloke
/
Nous-Hermes-Llama2-70B-GPTQ
like
7
Text Generation
Transformers
Safetensors
English
llama
llama-2
self-instruct
distillation
synthetic instruction
text-generation-inference
4-bit precision
gptq
License:
mit
Model card
Files
Files and versions
Community
2
Train
Deploy
Use this model
gptq-4bit-32g-actorder_True
Nous-Hermes-Llama2-70B-GPTQ
/
special_tokens_map.json
TheBloke
Initial GPTQ model commit
0fe3c53
about 1 year ago
raw
Copy download link
history
blame
Safe
96 Bytes
{
"bos_token"
:
"<s>"
,
"eos_token"
:
"</s>"
,
"pad_token"
:
"[PAD]"
,
"unk_token"
:
"<unk>"
}