Update README.md
Browse files
README.md
CHANGED
|
@@ -22,8 +22,10 @@ datasets:
|
|
| 22 |
- **Finetuned from model :** unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
|
| 23 |
|
| 24 |
Inspired by and featuring the Reflection Tuning technique pioneered by Matt Shumer (possibly earlier innovated by the team at Anthropic.)
|
|
|
|
| 25 |
*To the authors' knowledge, this is the first "reflection tuned" Llama 3.1 8B LLM*
|
| 26 |
|
|
|
|
| 27 |
**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) :**
|
| 28 |
'''
|
| 29 |
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.
|
|
|
|
| 22 |
- **Finetuned from model :** unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
|
| 23 |
|
| 24 |
Inspired by and featuring the Reflection Tuning technique pioneered by Matt Shumer (possibly earlier innovated by the team at Anthropic.)
|
| 25 |
+
|
| 26 |
*To the authors' knowledge, this is the first "reflection tuned" Llama 3.1 8B LLM*
|
| 27 |
|
| 28 |
+
|
| 29 |
**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) :**
|
| 30 |
'''
|
| 31 |
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.
|