This based on GGUF model hosted in HF https://huggingface.co/abhinand/tamil-llama-7b-instruct-v0.2
224 Pulls Updated 9 months ago
Updated 9 months ago
9 months ago
2d37b2c02c64 · 4.2GB
model
archllama
·
parameters6.89B
·
quantizationQ4_K_M
4.2GB
params
{"num_predict":-1,"repeat_penalty":1.2,"temperature":0.3}
58B
template
{{- if .First }}{{ .System }}{{- end }}
### Instruction:
{{ .Prompt }}
### Response:
87B
system
நீங்கள் உதவிகரமான மற்றும் மரியாதைக்
1.7kB
Readme
No readme