Update README.md
Browse files
README.md
CHANGED
|
@@ -28,7 +28,7 @@ scratch and then fine-tuned (SFT) on UltraChat to behave like a chat
|
|
| 28 |
assistant. Single RTX Pro 6000, ~4.16B pretraining tokens + ~1B SFT
|
| 29 |
tokens.
|
| 30 |
|
| 31 |
-
This is the SFT/chat variant of [GTM-v2-base](.
|
| 32 |
architecture and pretrained weights, continued with supervised
|
| 33 |
fine-tuning on conversational data. **This is still a small, from-scratch,
|
| 34 |
single-GPU hobby/research model, not a production assistant.** It is far
|
|
|
|
| 28 |
assistant. Single RTX Pro 6000, ~4.16B pretraining tokens + ~1B SFT
|
| 29 |
tokens.
|
| 30 |
|
| 31 |
+
This is the SFT/chat variant of [GTM-v2-base](https://hf.co/OPENGCM/GTM-v2-base) — same
|
| 32 |
architecture and pretrained weights, continued with supervised
|
| 33 |
fine-tuning on conversational data. **This is still a small, from-scratch,
|
| 34 |
single-GPU hobby/research model, not a production assistant.** It is far
|