Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
TheBloke
/
Vicuna-33B-1-3-SuperHOT-8K-GPTQ
like
27
Text Generation
Transformers
Safetensors
llama
custom_code
text-generation-inference
4-bit precision
arxiv:
2302.13971
arxiv:
2306.05685
License:
other
Model card
Files
Files and versions
Community
4
Train
Deploy
Use this model
main
Vicuna-33B-1-3-SuperHOT-8K-GPTQ
1 contributor
History:
13 commits
TheBloke
Update for Transformers GPTQ support
ae807a5
9 months ago
.gitattributes
1.52 kB
initial commit
11 months ago
README.md
12.6 kB
Update for Transformers GPTQ support
9 months ago
config.json
1.02 kB
Update for Transformers GPTQ support
9 months ago
generation_config.json
137 Bytes
Initial GPTQ model commit
11 months ago
llama_rope_scaled_monkey_patch.py
2.59 kB
Initial GPTQ model commit
11 months ago
model.safetensors
16.9 GB
LFS
Update for Transformers GPTQ support
9 months ago
modelling_llama.py
39.5 kB
Initial GPTQ model commit
11 months ago
quantize_config.json
156 Bytes
Update for Transformers GPTQ support
9 months ago
special_tokens_map.json
435 Bytes
Initial GPTQ model commit
11 months ago
tokenizer.json
1.84 MB
Initial GPTQ model commit
11 months ago
tokenizer.model
500 kB
LFS
Initial GPTQ model commit
11 months ago
tokenizer_config.json
727 Bytes
Initial GPTQ model commit
11 months ago