reflection:70b

105.5K 8 months ago

A high-performing model trained with a new technique called Reflection-tuning that teaches a LLM to detect mistakes in its reasoning and correct course.

70b

8 months ago

5084e77c1e10 · 40GB

model
llama
·
70.6B
·
Q4_0
system
You are a world-class AI system, capable of complex reasoning and reflection. Reason through the que
license
LLAMA 3.1 COMMUNITY LICENSE AGREEMENT Llama 3.1 Version Release Date: July 23, 2024 “Agreement”
params
{ "stop": [ "<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>"
template
{{- range $i, $_ := .Messages }}<|start_header_id|>{{ .Role }}<|end_header_id|> {{ .Content }} {{- i

Readme

During sampling, the model will start by outputting reasoning inside <thinking> and </thinking> tags, and then once it is satisfied with its reasoning, it will output the final answer inside <output> and </output> tags. Each of these tags are special tokens, trained into the model.

This enables the model to separate its internal thoughts and reasoning from its final answer, improving the experience for the user.

Inside the <thinking> section, the model may output one or more <reflection> tags, which signals the model has caught an error in its reasoning and will attempt to correct it before providing a final answer.

References

Hugging Face