|
--- |
|
base_model: Solshine/reflection-llama-3.1-8B-Solshine-trainround2-16bit |
|
language: |
|
- en |
|
license: llama3.1 |
|
tags: |
|
- text-generation-inference |
|
- transformers |
|
- unsloth |
|
- llama |
|
- trl |
|
- sft |
|
- reflection |
|
datasets: |
|
- mahiatlinux/Reflection-Dataset-v2 |
|
--- |
|
|
|
# Uploaded model |
|
|
|
- **Developed by:** Solshine (Caleb DeLeeuw) |
|
- **License:** LLama 3.1 License |
|
- **Finetuned from model :** Solshine/reflection-llama-3.1-8B-Solshine-trainround2-16bit |
|
|
|
Inspired by and featuring the Reflection Tuning technique pioneered by Matt Shumer (possibly earlier innovated by the team at Anthropic.) |
|
|
|
*To the authors' knowledge, this is V3 of the first "reflection tuned" Llama 3.1 8B LLM* |
|
|
|
|
|
**As per the inspiring model "mattshumer/Reflection-Llama-3.1-70B" (this mode was not used in the training process nor as a foundational model, but only served as inspiration) :** |
|
|
|
``` |
|
|
|
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. |
|
|
|
System Prompt: |
|
The system prompt used for training this model is: |
|
|
|
"You are a world-class AI system, capable of complex reasoning and reflection. Reason through the query inside <thinking> tags, and then provide your final response inside <output> tags. If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags." |
|
|
|
We recommend using this exact system prompt to get the best results from Reflection Llama-3.1 70B. You may also want to experiment combining this system prompt with your own custom instructions to customize the behavior of the model. |
|
|
|
Chat Format: |
|
As mentioned above, the model uses the standard Llama 3.1 chat format. Here’s an example: |
|
|
|
<|begin_of_text|><|start_header_id|>system<|end_header_id|> |
|
|
|
You are a world-class AI system, capable of complex reasoning and reflection. Reason through the query inside <thinking> tags, and then provide your final response inside <output> tags. If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags.<|eot_id|><|start_header_id|>user<|end_header_id|> |
|
|
|
what is 2+2?<|eot_id|><|start_header_id|>assistant<|end_header_id|> |
|
|
|
``` |
|
|
|
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. |
|
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
