126 10 months ago

unsloth微调DeepSeek-R1-Distill-Llama-8B

8b

10 months ago

5dc321fca2b0 · 4.9GB ·

llama
·
8.03B
·
Q4_K_M
{ "num_ctx": 12800, "stop": [ "<|begin▁of▁sentence|>", "<|end▁of
{{- if .System }}{{ .System }}{{ end }} {{- range $i, $_ := .Messages }} {{- $last := eq (len (slice

Readme

基于DeepSeek-R1-Distill-Llama-8B进行医疗数据集STF微调

数据集(FreedomIntelligence/medical-o1-reasoning-SFT数据集)

https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT

colab地址:

https://colab.research.google.com/drive/1N0Sf9yn8Tjs5gMJv-rez-0hzxBUDK3xK?usp=sharing#scrollTo=HvOPfPnet76H