Update README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,7 @@ datasets:
|
|
| 10 |
- neph1/codefeedback-swedish
|
| 11 |
---
|
| 12 |
|
| 13 |
-
# Model Card for
|
| 14 |
|
| 15 |
This version of bellman is finetuned from llama-3-instruct-8b.
|
| 16 |
It is arguable whether it's better at Swedish, because llama-3 is really good. It's however finetuned for prompt question answering, based on a dataset created from
|
|
@@ -18,6 +18,8 @@ Swedish wikipedia, with a lot of Sweden-centric questions.
|
|
| 18 |
New from previous versions is questions from a translated code-feedback dataset, as well as a number of stories. It's not great at generating stories,
|
| 19 |
but better than previosly.
|
| 20 |
|
|
|
|
|
|
|
| 21 |
240609: I've uploaded a 4-bit GPTQ quant, but it's completely untested.
|
| 22 |
|
| 23 |
|
|
|
|
| 10 |
- neph1/codefeedback-swedish
|
| 11 |
---
|
| 12 |
|
| 13 |
+
# Model Card for Bellman
|
| 14 |
|
| 15 |
This version of bellman is finetuned from llama-3-instruct-8b.
|
| 16 |
It is arguable whether it's better at Swedish, because llama-3 is really good. It's however finetuned for prompt question answering, based on a dataset created from
|
|
|
|
| 18 |
New from previous versions is questions from a translated code-feedback dataset, as well as a number of stories. It's not great at generating stories,
|
| 19 |
but better than previosly.
|
| 20 |
|
| 21 |
+
Please note, the HuggingFace inference api is probably trying to load the adapter (lora) which isn't going to work.
|
| 22 |
+
|
| 23 |
240609: I've uploaded a 4-bit GPTQ quant, but it's completely untested.
|
| 24 |
|
| 25 |
|