You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
自动生成的 Modelfile 如下:
`# ollama modelfile auto-generated by llamafactory
FROM .
TEMPLATE """<|begin▁of▁sentence|>{{ if .System }}{{ .System }}{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|User|>{{ .Content }}<|Assistant|>{{ else if eq .Role "assistant" }}{{ .Content }}<|end▁of▁sentence|>{{ end }}{{ end }}"""
n@Precision-5820-Tower-X-Series:~$ ollama show --modelfile faq_robot:latest
# Modelfile generated by "ollama show"
# To build a new Modelfile based on this, replace FROM with:
# FROM faq_robot:latest
FROM /usr/share/ollama/.ollama/models/blobs/sha256-eeaa06295dfc573322aa5fa303c3dc2103567d28c33a1356816f3a6773167825
TEMPLATE <|begin▁of▁sentence|>{{ if .System }}{{ .System }}{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|User|>{{ .Content }}<|Assistant|>{{ else if eq .Role "assistant" }}{{ .Content }}<|end▁of▁sentence|>{{ end }}{{ end }}
PARAMETER stop <|end▁of▁sentence|>
PARAMETER num_ctx 4096
Reminder
System Info
llamafactory
version: 0.9.2.dev0Reproduction
我使用 alpaca 格式的自定义数据集 SFT 微调 deepseek-ai/DeepSeek-R1-Distill-Llama-8B,模板为 deepseek3,4bit bnb 训练得到 QLora,在 Chat 加载表现出色。但是在合并秩到基模型后(模板确认为 deepseek3,也没有在导入 ollama 的过程中进行量化),问答准确率大幅下降,模型开始自由发挥。想请教一下问题是出在了哪里?
自动生成的 Modelfile 如下:
`# ollama modelfile auto-generated by llamafactory
FROM .
TEMPLATE """<|begin▁of▁sentence|>{{ if .System }}{{ .System }}{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|User|>{{ .Content }}<|Assistant|>{{ else if eq .Role "assistant" }}{{ .Content }}<|end▁of▁sentence|>{{ end }}{{ end }}"""
PARAMETER stop "<|end▁of▁sentence|>"
PARAMETER num_ctx 4096
`
Others
No response
The text was updated successfully, but these errors were encountered: