reeducator
/

vicuna-13b-cocktail

Text Generation

Inference Endpoints

Model card Files Files and versions Community

vicuna-13b-cocktail

1 contributor

History: 10 commits

reeducator's picture

Requantize ggml after breaking updates (again)

5b14676 over 1 year ago

pytorch
Add pytorch model files over 1 year ago
.gitattributes

1.48 kB

initial commit over 1 year ago
README.md

1.29 kB

Update README over 1 year ago
config.json

507 Bytes

Move config files to root over 1 year ago
ggml-vicuna-13b-cocktail-v1-q5_0.bin

8.95 GB
LFS

Requantize ggml after breaking updates (again) over 1 year ago
ggml-vicuna-13b-cocktail-v1-q8_0.bin

13.8 GB
LFS

Requantize ggml after breaking updates (again) over 1 year ago
special_tokens_map.json

435 Bytes

Move config files to root over 1 year ago
tokenizer.model

500 kB
LFS

Move config files to root over 1 year ago
tokenizer_config.json

783 Bytes

Move config files to root over 1 year ago
vicuna-13b-cocktail-v1-4bit-128g.safetensors

7.91 GB
LFS

Add GPTQ .safetensors for v1 over 1 year ago
vicuna-13b-cocktail-v1-triton-4bit-128g.safetensors

7.91 GB
LFS

Add triton quantized safetensors over 1 year ago