Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
TheBloke
/
Yarn-Llama-2-70B-32k-AWQ
like
2
Text Generation
Transformers
Safetensors
emozilla/yarn-train-tokenized-8k-llama
English
llama
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
main
Yarn-Llama-2-70B-32k-AWQ
1 contributor
History:
4 commits
TheBloke
Upload README.md
d164f8e
12 months ago
.gitattributes
1.52 kB
initial commit
12 months ago
README.md
17.2 kB
Upload README.md
12 months ago
added_tokens.json
2 Bytes
AWQ model commit
12 months ago
config.json
1.14 kB
AWQ model commit
12 months ago
configuration_llama.py
9.25 kB
AWQ model commit
12 months ago
generation_config.json
188 Bytes
AWQ model commit
12 months ago
model-00001-of-00004.safetensors
9.94 GB
LFS
AWQ model commit
12 months ago
model-00002-of-00004.safetensors
9.9 GB
LFS
AWQ model commit
12 months ago
model-00003-of-00004.safetensors
9.9 GB
LFS
AWQ model commit
12 months ago
model-00004-of-00004.safetensors
6.87 GB
LFS
AWQ model commit
12 months ago
model.safetensors.index.json
159 kB
AWQ model commit
12 months ago
modeling_llama_yarn.py
64.2 kB
AWQ model commit
12 months ago
quant_config.json
90 Bytes
AWQ model commit
12 months ago
special_tokens_map.json
72 Bytes
AWQ model commit
12 months ago
tokenizer.json
1.84 MB
AWQ model commit
12 months ago
tokenizer.model
500 kB
LFS
AWQ model commit
12 months ago
tokenizer_config.json
902 Bytes
AWQ model commit
12 months ago