Update README.md
Browse files
README.md
CHANGED
|
@@ -7,8 +7,7 @@ tags:
|
|
| 7 |
- llama-ti
|
| 8 |
- fluently-lm
|
| 9 |
- fluently-merge
|
| 10 |
-
-
|
| 11 |
-
- conversational
|
| 12 |
- reflection
|
| 13 |
- reasoning
|
| 14 |
- math
|
|
@@ -19,4 +18,32 @@ language:
|
|
| 19 |
- code
|
| 20 |
---
|
| 21 |
|
| 22 |
-
# Llama3.1 8B **TI**
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
- llama-ti
|
| 8 |
- fluently-lm
|
| 9 |
- fluently-merge
|
| 10 |
+
- base
|
|
|
|
| 11 |
- reflection
|
| 12 |
- reasoning
|
| 13 |
- math
|
|
|
|
| 18 |
- code
|
| 19 |
---
|
| 20 |
|
| 21 |
+
# Llama3.1 8B **TI**
|
| 22 |
+
|
| 23 |
+
Llama TI is an improved Llama (from Meta AI), some aspects of the model have been revised and some features have been added.
|
| 24 |
+
|
| 25 |
+
## Info
|
| 26 |
+
|
| 27 |
+
### Main
|
| 28 |
+
|
| 29 |
+
The model is based on Meta-Llama-3.1-8B, and has the same 8.03B parameters. The Llama3 architecture has been preserved and the model launch methods are the same.
|
| 30 |
+
|
| 31 |
+
### Differences
|
| 32 |
+
|
| 33 |
+
Thanks to additional training and advanced merging, it was possible to improve mathematical, biological, reasoning and writing skills.
|
| 34 |
+
|
| 35 |
+
Now the model can:
|
| 36 |
+
- Count well and solve mathematical/physical problems
|
| 37 |
+
- Reason/think logically
|
| 38 |
+
- Write creatively (in many languages)
|
| 39 |
+
- Code well
|
| 40 |
+
- Process/analyze large texts
|
| 41 |
+
|
| 42 |
+
### Where is the chat version (instruct)?
|
| 43 |
+
|
| 44 |
+
It is available [here](https://hf.co/fluently-lm/Llama-TI-8B-Instruct)!
|
| 45 |
+
|
| 46 |
+
### Special thanks to:
|
| 47 |
+
Meta AI, NVIDIA, Arcee AI, SkyWork, NousReaserch, Unsloth and Project Fluently.
|
| 48 |
+
|
| 49 |
+
*Developed and uploaded by [ehristoforu](https://t.me/ehristoforu_ai).*
|