Update README.md
Browse files
README.md
CHANGED
|
@@ -4,11 +4,12 @@ license: llama3.1
|
|
| 4 |
pipeline_tag: text-generation
|
| 5 |
tags:
|
| 6 |
- unsloth
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
4bit bitsandbytes quantized version of https://huggingface.co/mattshumer/Reflection-70B
|
| 10 |
|
| 11 |
-
#
|
| 12 |
|
| 13 |
**Reflection 70B is (currently) the world's top open-source LLM, trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.**
|
| 14 |
|
|
|
|
| 4 |
pipeline_tag: text-generation
|
| 5 |
tags:
|
| 6 |
- unsloth
|
| 7 |
+
- llama-3
|
| 8 |
---
|
| 9 |
|
| 10 |
4bit bitsandbytes quantized version of https://huggingface.co/mattshumer/Reflection-70B
|
| 11 |
|
| 12 |
+
# You can fine-tune Reflection-3.1 70B with 48GB of VRAM with Unsloth! 🦥
|
| 13 |
|
| 14 |
**Reflection 70B is (currently) the world's top open-source LLM, trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.**
|
| 15 |
|