shaowenchen's picture
add meta files
50aa3b7
|
raw
history blame
2.09 kB
metadata
inference: true
language:
  - zh
  - en
license: other
model_creator: lmsys
model_link: https://huggingface.co/lmsys/longchat-13b-16k
model_name: longchat-13b-16k
model_type: longchat
pipeline_tag: text-generation
quantized_by: shaowenchen
tasks:
  - text2text-generation
tags:
  - gguf
  - longchat
  - 13b
  - 16k

Provided files

Name Quant method Size
longchat-13b-16k.Q2_K.gguf Q2_K 5.1 GB
longchat-13b-16k.Q3_K.gguf Q3_K 5.9 GB
longchat-13b-16k.Q3_K_L.gguf Q3_K_L 6.5 GB
longchat-13b-16k.Q3_K_S.gguf Q3_K_S 5.3 GB
longchat-13b-16k.Q4_0.gguf Q4_0 6.9 GB
longchat-13b-16k.Q4_1.gguf Q4_1 7.6 GB
longchat-13b-16k.Q4_K.gguf Q4_K 7.3 GB
longchat-13b-16k.Q4_K_S.gguf Q4_K_S 6.9 GB
longchat-13b-16k.Q5_0.gguf Q5_0 8.4 GB
longchat-13b-16k.Q5_1.gguf Q5_1 9.1 GB
longchat-13b-16k.Q5_K.gguf Q5_K 8.6 GB
longchat-13b-16k.Q5_K_S.gguf Q5_K_S 8.4 GB
longchat-13b-16k.Q6_K.gguf Q6_K 9.9 GB
longchat-13b-16k.Q8_0.gguf Q8_0 13 GB
longchat-13b-16k.gguf full 24 GB

Usage:

docker run --rm -it -p 8000:8000 -v /path/to/models:/models -e MODEL=/models/gguf-model-name.gguf hubimage/llama-cpp-python:latest

and you can view http://localhost:8000/docs to see the swagger UI.

Provided images

Name Quant method Compressed Size
shaowenchen/longchat-13b-16k-gguf:Q2_K Q2_K 2.88 GB
shaowenchen/longchat-13b-16k-gguf:Q3_K Q3_K 3.3 GB
shaowenchen/longchat-13b-16k-gguf:Q4_K Q4_K 4 GB

Usage:

docker run --rm -p 8000:8000 shaowenchen/longchat-13b-16k-gguf:Q2_K

and you can view http://localhost:8000/docs to see the swagger UI.