Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,13 +11,22 @@ ForgeWorks is an organisation that builds small language models. Currently best
|
|
| 11 |
|
| 12 |
## Highlights
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
**ForgePlex-M1-6M**
|
| 15 |
|
| 16 |
- First model trained on [Axiomic Labs](https://huggingface.co/AxiomicLabs) training framework: Trainwork.
|
| 17 |
- Peaked at 23rd on the [Open SLM Leaderboard](https://huggingface.co/spaces/AxiomicLabs/Open_SLM_Leaderboard) <10m parameters category.
|
| 18 |
|
| 19 |
-
**ForgePlex-M2-9M**
|
| 20 |
|
| 21 |
-
- Peaked at 3rd 🥉 on the [Open SLM Leaderboard](https://huggingface.co/spaces/AxiomicLabs/Open_SLM_Leaderboard) <10m parameters category.
|
| 22 |
|
| 23 |
|
|
|
|
| 11 |
|
| 12 |
## Highlights
|
| 13 |
|
| 14 |
+
|
| 15 |
+
**ForgePlex-M2.1-10M**
|
| 16 |
+
|
| 17 |
+
- Currently 1st 🥇 on the [Open SLM Leaderboard](https://huggingface.co/spaces/AxiomicLabs/Open_SLM_Leaderboard) <10m parameters category.
|
| 18 |
+
- The first sub-10M-parameter model to pass an Intelligence Index of 10 on the [Open SLM Leaderboard](https://huggingface.co/spaces/AxiomicLabs/Open_SLM_Leaderboard) with 10.70
|
| 19 |
+
- A +1.56 Index gain over ForgePlex-M2 (9.14), with the same core architecture.
|
| 20 |
+
|
| 21 |
+
**ForgePlex-M2-9M**
|
| 22 |
+
|
| 23 |
+
- peaked at 3rd 🥉 on the [Open SLM Leaderboard](https://huggingface.co/spaces/AxiomicLabs/Open_SLM_Leaderboard) <10m parameters category.
|
| 24 |
+
|
| 25 |
**ForgePlex-M1-6M**
|
| 26 |
|
| 27 |
- First model trained on [Axiomic Labs](https://huggingface.co/AxiomicLabs) training framework: Trainwork.
|
| 28 |
- Peaked at 23rd on the [Open SLM Leaderboard](https://huggingface.co/spaces/AxiomicLabs/Open_SLM_Leaderboard) <10m parameters category.
|
| 29 |
|
|
|
|
| 30 |
|
|
|
|
| 31 |
|
| 32 |
|