Shadowgraph
About
Sign in

hfl/chinese-llama-2-13b-16k-gguf

Model

1

stars

20

commits

1

linked in READMEs

Jan 24, 2024

updated

endpoints_compatible
gguf
Browse cluster: Chinese LLM Model Distribution →

README

Chinese-LLaMA-2-13B-16K-GGUF

This repository contains the GGUF-v3 models (llama.cpp compatible) for Chinese-LLaMA-2-13B-16K.

Performance

Metric: PPL, lower is better

Quantoriginalimatrix (-im)
Q2_K11.8958 +/- 0.2073913.0017 +/- 0.23003
Q3_K9.7130 +/- 0.170379.3443 +/- 0.16582
Q4_09.2002 +/- 0.16219-
Q4_K9.0055 +/- 0.159188.9848 +/- 0.15908
Q5_08.8441 +/- 0.15690-
Q5_K8.8999 +/- 0.157518.8983 +/- 0.15753
Q6_K8.8944 +/- 0.157768.8833 +/- 0.15760
Q8_08.8745 +/- 0.15745-
F168.8687 +/- 0.15729-

The model with -im suffix is generated with important matrix, which has generally better performance (not always though).

Others

For Hugging Face version, please see: https://huggingface.co/hfl/chinese-llama-2-13b-16k

Please refer to https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/ for more details.

Contributors

hfl-rc

20 commits

Similar repos

hfl/chinese-llama-2-1.3b-gguf

Model

2

hfl/chinese-llama-2-13b-gguf

Model

5

hfl/chinese-alpaca-2-13b-16k-gguf

Model

1

hfl/chinese-llama-2-7b-16k-gguf

Model

2

hfl/chinese-alpaca-2-13b-gguf

Model

10

hfl/chinese-alpaca-2-1.3b-gguf

Model

6

hfl/chinese-alpaca-2-7b-16k-gguf

Model

1

hfl/chinese-llama-2-7b-gguf

Model

5

Linked in READMEs

ymcui/Chinese-LLaMA-Alpaca-2

中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context…

7,120

README badge

hfl/chinese-llama-2-13b-16k-gguf

Model

1

stars

20

commits

1

linked in READMEs

Jan 24, 2024

updated

endpoints_compatible
gguf
Browse cluster: Chinese LLM Model Distribution →

README

Chinese-LLaMA-2-13B-16K-GGUF

This repository contains the GGUF-v3 models (llama.cpp compatible) for Chinese-LLaMA-2-13B-16K.

Performance

Metric: PPL, lower is better

Quantoriginalimatrix (-im)
Q2_K11.8958 +/- 0.2073913.0017 +/- 0.23003
Q3_K9.7130 +/- 0.170379.3443 +/- 0.16582
Q4_09.2002 +/- 0.16219-
Q4_K9.0055 +/- 0.159188.9848 +/- 0.15908
Q5_08.8441 +/- 0.15690-
Q5_K8.8999 +/- 0.157518.8983 +/- 0.15753
Q6_K8.8944 +/- 0.157768.8833 +/- 0.15760
Q8_08.8745 +/- 0.15745-
F168.8687 +/- 0.15729-

The model with -im suffix is generated with important matrix, which has generally better performance (not always though).

Others

For Hugging Face version, please see: https://huggingface.co/hfl/chinese-llama-2-13b-16k

Please refer to https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/ for more details.

Similar repos

hfl/chinese-llama-2-1.3b-gguf

Model

2

hfl/chinese-llama-2-13b-gguf

Model

5

hfl/chinese-alpaca-2-13b-16k-gguf

Model

1

hfl/chinese-llama-2-7b-16k-gguf

Model

2

hfl/chinese-alpaca-2-13b-gguf

Model

10

hfl/chinese-alpaca-2-1.3b-gguf

Model

6

hfl/chinese-alpaca-2-7b-16k-gguf

Model

1

hfl/chinese-llama-2-7b-gguf

Model

5

Linked in READMEs

ymcui/Chinese-LLaMA-Alpaca-2

中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context…

7,120

README badge

Contributors

hfl-rc

20 commits