Update README.md
Browse files
README.md
CHANGED
|
@@ -19,13 +19,15 @@ datasets:
|
|
| 19 |
|
| 20 |
**This model is TrainRound5, following Solshine/reflection-llama-3.1-8B-Solshine-trainround4-16bit in an iterative fine-tuning process**
|
| 21 |
|
|
|
|
|
|
|
| 22 |
# Uploaded model
|
| 23 |
|
| 24 |
- **Developed by:** Solshine (Caleb DeLeeuw)
|
| 25 |
- **License:** llama 3.1
|
| 26 |
- **Finetuned from model :** Solshine/reflection-llama-3.1-8B-Solshine-trainround4-16bit
|
| 27 |
|
| 28 |
-
Inspired by and featuring the Reflection Tuning technique pioneered by Matt Shumer (possibly earlier innovated by the team at Anthropic.)
|
| 29 |
|
| 30 |
*To the authors' knowledge, this is V5 of the first "reflection tuned" Llama 3.1 8B LLM*
|
| 31 |
|
|
|
|
| 19 |
|
| 20 |
**This model is TrainRound5, following Solshine/reflection-llama-3.1-8B-Solshine-trainround4-16bit in an iterative fine-tuning process**
|
| 21 |
|
| 22 |
+
**Not Officially Benchmarked Yet!** (Please submit any benchmarking or eval results via the Community tab.)
|
| 23 |
+
|
| 24 |
# Uploaded model
|
| 25 |
|
| 26 |
- **Developed by:** Solshine (Caleb DeLeeuw)
|
| 27 |
- **License:** llama 3.1
|
| 28 |
- **Finetuned from model :** Solshine/reflection-llama-3.1-8B-Solshine-trainround4-16bit
|
| 29 |
|
| 30 |
+
Inspired by and featuring the Reflection Tuning technique pioneered by Matt Shumer (possibly earlier innovated by the team at Anthropic, and Mlabbone' Hermes.)
|
| 31 |
|
| 32 |
*To the authors' knowledge, this is V5 of the first "reflection tuned" Llama 3.1 8B LLM*
|
| 33 |
|