Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
TheBloke
/
Yarn-Mistral-7B-64k-AWQ
like
4
Text Generation
Transformers
Safetensors
emozilla/yarn-train-tokenized-16k-mistral
English
mistral
custom_code
text-generation-inference
4-bit precision
awq
arxiv:
2309.00071
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
0f7a8b5
Yarn-Mistral-7B-64k-AWQ
1 contributor
History:
2 commits
TheBloke
AWQ model commit
0f7a8b5
10 months ago
.gitattributes
1.52 kB
initial commit
10 months ago
added_tokens.json
42 Bytes
AWQ model commit
10 months ago
config.json
972 Bytes
AWQ model commit
10 months ago
configuration_mistral.py
8.9 kB
AWQ model commit
10 months ago
generation_config.json
116 Bytes
AWQ model commit
10 months ago
model.safetensors
4.15 GB
LFS
AWQ model commit
10 months ago
modeling_mistral_yarn.py
67.3 kB
AWQ model commit
10 months ago
quant_config.json
90 Bytes
AWQ model commit
10 months ago
special_tokens_map.json
145 Bytes
AWQ model commit
10 months ago
tokenizer.json
1.8 MB
AWQ model commit
10 months ago
tokenizer.model
493 kB
LFS
AWQ model commit
10 months ago
tokenizer_config.json
953 Bytes
AWQ model commit
10 months ago