conceptsintamil/
tamil-llama-7b-instruct-v0.2:latest

461 1 year ago

This based on GGUF model hosted in HF https://huggingface.co/abhinand/tamil-llama-7b-instruct-v0.2

1 year ago

2d37b2c02c64 · 4.2GB ·

model
llama
·
6.89B
·
Q4_K_M
system
நீங்கள் உதவிகரமான மற்றும் மரியாதைக்
params
{ "num_predict": -1, "repeat_penalty": 1.2, "temperature": 0.3 }
template
{{- if .First }}{{ .System }}{{- end }} ### Instruction: {{ .Prompt }} ### Response:

Readme

No readme