Downloads · 30 days
0
ggml-LLaMa-65B-quantized
CRD716/ggml-LLaMa-65B-quantized
ggml-LLaMa-65B-quantized is a text generation model from CRD716. Use it when you need the model to write or continue text. The card lists the license as gpl-3.0.
NOTE: DEPRECIATED, BETTER PEOPLE DO THIS NOW
Access
Public
Updated Sep 9, 2023
Repo size
473 GB
Likes
29
Public
Repo makeup
Click a slice to open those files.
.bin220 GB · 100%
At a glance
- Task
- Text Generation
- License
- gpl-3.0
- Access
- Public
- Created
- Apr 7, 2023
- Updated
- Sep 9, 2023
- SHA
- 120983f2
Try a prompt
Model card
From the Hugging Face model README
NOTE: DEPRECIATED, BETTER PEOPLE DO THIS NOW
LLaMa 65B converted to ggml via LLaMa.cpp, then quantized to 4bit.
Legacy is for llama.cpp setups older than https://github.com/ggerganov/llama.cpp/pull/1508, the regular is faster but does not work on old versions.
I recommend the following settings when running as a good starting point:
main.exe -m ggml-LLaMa-65B-q4_0.bin -n -1 -t 32 -c 2048 --temp 0.7 --repeat_penalty 1.2 --mirostat 2 --interactive-first --color
Be aware that LLaMa is a text generation model, not a conversational one, and as such you will have to prompt it differently than, for example, Vicuna or ChatGPT.
- Task
- Text Generation
- License
- gpl-3.0
- Languages
- en, bg, ca, cs, da, de
- Created
- Apr 7, 2023
- Updated
- Sep 9, 2023