Commit
•
2e6154d
1
Parent(s):
f82e54a
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,8 +1,16 @@
|
|
| 1 |
---
|
| 2 |
license: llama3.1
|
| 3 |
-
base_model:
|
| 4 |
pipeline_tag: text-generation
|
| 5 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
# Reflection Llama-3.1 70B
|
| 7 |
|
| 8 |
**Reflection Llama-3.1 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.**
|
|
|
|
| 1 |
---
|
| 2 |
license: llama3.1
|
| 3 |
+
base_model: mattshumer/Reflection-Llama-3.1-70B
|
| 4 |
pipeline_tag: text-generation
|
| 5 |
---
|
| 6 |
+
|
| 7 |
+
GGUF quantized version using llama.cpp
|
| 8 |
+
|
| 9 |
+
It included the tokenizer and vocab fixed from 06/09/2024
|
| 10 |
+
|
| 11 |
+
Original model [mattshumer/Reflection-Llama-3.1-70B](https://huggingface.co/mattshumer/Reflection-Llama-3.1-70B)
|
| 12 |
+
|
| 13 |
+
|
| 14 |
# Reflection Llama-3.1 70B
|
| 15 |
|
| 16 |
**Reflection Llama-3.1 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.**
|