Update README.md
Browse files
README.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
library_name: transformers
|
| 3 |
datasets:
|
| 4 |
- HuggingFaceH4/ultrachat_200k
|
| 5 |
-
|
| 6 |
---
|
| 7 |
|
| 8 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/llm_surgery/gemma-zephyr)
|
|
@@ -11,6 +11,12 @@ finetuned_from: google/gemma-7b
|
|
| 11 |
|
| 12 |
The [Zephyr](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) SFT recipe applied on top of Gemma 7B
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
## Recipe
|
| 15 |
|
| 16 |
We trained using the [alignment handbook recipe](https://github.com/huggingface/alignment-handbook/blob/main/scripts/run_sft.py) and logging to W&B
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
datasets:
|
| 4 |
- HuggingFaceH4/ultrachat_200k
|
| 5 |
+
base_model: google/gemma-7b
|
| 6 |
---
|
| 7 |
|
| 8 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/llm_surgery/gemma-zephyr)
|
|
|
|
| 11 |
|
| 12 |
The [Zephyr](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) SFT recipe applied on top of Gemma 7B
|
| 13 |
|
| 14 |
+
## Model description
|
| 15 |
+
|
| 16 |
+
- **Model type:** A 8.5B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
|
| 17 |
+
- **Language(s) (NLP):** Primarily English
|
| 18 |
+
- **Finetuned from model:** [google/gemma-7b](https://huggingface.co/google/gemma-7b)
|
| 19 |
+
|
| 20 |
## Recipe
|
| 21 |
|
| 22 |
We trained using the [alignment handbook recipe](https://github.com/huggingface/alignment-handbook/blob/main/scripts/run_sft.py) and logging to W&B
|