inference: false
language:
- en
tags:
- llama
- text-generation-inference
lmsys's Longchat-7B-v1.5-32k GGML
These files are GGML format model files for lmsys's Longchat-7B-v1.5-32k.
GGML files are for CPU + GPU inference using llama.cpp and libraries and UIs which support this format, such as:
How to run in llama.cpp
I use the following command line, adjust for your tastes and needs:
./main -t 2 -ngl 32 -m longchat-7b-v1.5-32k.ggmlv3.q4_0.bin --color --rope-freq-scale 0.25 --rope-freq-base 240000 -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "prompt goes here"
Change -t 2
to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use -t 8
.
Change -ngl 26
to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
If you want to have a chat-style conversation, replace the -p <PROMPT>
argument with -i -ins
, you can use --interactive-first
to start in interactive mode.
Compatibility
I have uploded bothe the original llama.cpp quant methods (q4_0, q4_1, q5_0, q5_1, q8_0
) as well as the new k-quant methods (q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K
).
Please refer to llama.cpp and TheBloke's GGML models for further explanation.
How to run in text-generation-webui
Further instructions here: text-generation-webui/docs/llama.cpp-models.md.
Thanks
Thanks to TheBloke for inspiration and providing almost all of the readme here!
Thanks to lmsys for providing checkpoints of the model.
Thanks to Georgi Gerganov and all of the awesome people in the AI community.