https://github.com/UnicomAI/Unichat-llama3-Chinese
7,226 Pulls Updated 7 months ago
Updated 7 months ago
7 months ago
8ebd4da26ef6 · 4.7GB
model
archllama
·
parameters8.03B
·
quantizationQ4_0
4.7GB
system
A chat between a curious user and an artificial intelligence assistant.The assistant gives helpful,
154B
params
{
"num_keep": 24,
"repeat_penalty": 1.15,
"stop": [
"<|start_header_id|>",
160B
template
{{ if .System }}<|start_header_id|>system<|end_header_id|>
{{ .System }}<|eot_id|>{{ end }}{{ if .P
254B
Readme
中国联通AI创新中心发布的一个llama3中文指令微调模型(全参数微调)
Unichat-llama3-Chinese/ 中国联通AI llama3 中文版 8B模型
可选择量化版本
显卡显存小于6G 建议下载量化版本
Modefile:
FROM converted.bin
#TEMPLATE "[INST] {{ .Prompt }} [/INST]"
TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>
{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
{{ .Response }}<|eot_id|>"""
PARAMETER num_keep 24
PARAMETER stop "<|start_header_id|>"
PARAMETER stop "<|end_header_id|>"
PARAMETER stop "<|eot_id|>"
SYSTEM A chat between a curious user and an artificial intelligence assistant.The assistant gives helpful, detailed, and polite answers to the user's questions.
PARAMETER repeat_penalty 1.15
PARAMETER temperature 0.6
PARAMETER top_p 1