Update README.md
Browse files
README.md
CHANGED
|
@@ -22,13 +22,15 @@ tags:
|
|
| 22 |
This model was converted to GGUF format from [`Solshine/reflection-llama-3.1-8B-Solshine-trainround3-16bit`](https://huggingface.co/Solshine/reflection-llama-3.1-8B-Solshine-trainround3-16bit) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
| 23 |
Refer to the [original model card](https://huggingface.co/Solshine/reflection-llama-3.1-8B-Solshine-trainround3-16bit) for more details on the model.
|
| 24 |
|
|
|
|
|
|
|
| 25 |
# Uploaded model
|
| 26 |
|
| 27 |
- **Developed by:** Solshine (Caleb DeLeeuw)
|
| 28 |
- **License:** LLama 3.1 License
|
| 29 |
- **Finetuned from model :** Solshine/reflection-llama-3.1-8B-Solshine-trainround2-16bit
|
| 30 |
|
| 31 |
-
Inspired by and featuring the Reflection Tuning technique pioneered by Matt Shumer (possibly earlier innovated by the team at Anthropic.)
|
| 32 |
|
| 33 |
*To the authors' knowledge, this is V3 of the first "reflection tuned" Llama 3.1 8B LLM*
|
| 34 |
|
|
|
|
| 22 |
This model was converted to GGUF format from [`Solshine/reflection-llama-3.1-8B-Solshine-trainround3-16bit`](https://huggingface.co/Solshine/reflection-llama-3.1-8B-Solshine-trainround3-16bit) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
| 23 |
Refer to the [original model card](https://huggingface.co/Solshine/reflection-llama-3.1-8B-Solshine-trainround3-16bit) for more details on the model.
|
| 24 |
|
| 25 |
+
**Not Officially Benchmarked Yet!** (Please submit any benchmarking or eval results via the Community tab.)
|
| 26 |
+
|
| 27 |
# Uploaded model
|
| 28 |
|
| 29 |
- **Developed by:** Solshine (Caleb DeLeeuw)
|
| 30 |
- **License:** LLama 3.1 License
|
| 31 |
- **Finetuned from model :** Solshine/reflection-llama-3.1-8B-Solshine-trainround2-16bit
|
| 32 |
|
| 33 |
+
Inspired by and featuring the Reflection Tuning technique pioneered by Matt Shumer (possibly earlier innovated by the team at Anthropic, and Mlabbone's Hermes.)
|
| 34 |
|
| 35 |
*To the authors' knowledge, this is V3 of the first "reflection tuned" Llama 3.1 8B LLM*
|
| 36 |
|