Update README.md

README.md

@@ -1,6 +1,5 @@
 ---
 library_name: transformers
-license: other
 base_model: nvidia/Llama-3.1-Minitron-4B-Width-Base
 tags:
 - axolotl
@@ -8,6 +7,10 @@ tags:
 model-index:
 - name: MagpieLM-4B-SFT-v0.1
   results: []
+datasets:
+- Magpie-Align/MagpieLM-4B-SFT
+language:
+- en
 ---
 
 ![Magpie](https://cdn-uploads.huggingface.co/production/uploads/653df1323479e9ebbe3eb6cc/FWWILXrAGNwWr52aghV0S.png)
@@ -24,11 +27,7 @@ Codes: [https://github.com/magpie-align/magpie](https://github.com/magpie-align/
 
 *Model full name: Llama3.1-MagpieLM-4B-SFT-v0.1*
 
-This model is a fine-tuned version of [nvidia/Llama-3.1-Minitron-4B-Width-Base](https://huggingface.co/nvidia/Llama-3.1-Minitron-4B-Width-Base) on 
-- [Magpie-Align/Magpie-Llama-3.1-Pro-MT-500K-v0.1](https://huggingface.co/datasets/Magpie-Align/Magpie-Llama-3.1-Pro-MT-500K-v0.1), and
-- [Magpie-Align/Magpie-Reasoning-150K](https://huggingface.co/datasets/Magpie-Align/Magpie-Reasoning-150K).
-
-## Training procedure
+This model is a fine-tuned version of [nvidia/Llama-3.1-Minitron-4B-Width-Base](https://huggingface.co/nvidia/Llama-3.1-Minitron-4B-Width-Base) on [Magpie-Align/MagpieLM-4B-SFT](https://huggingface.co/datasets/Magpie-Align/Magpie-Align/MagpieLM-4B-SFT).
 
 ## Training procedure
 
@@ -89,15 +88,9 @@ datasets:
   - path: flydust/Magpie-Llama-3-70B-300K-Gemma2-9B
     type: sharegpt
     conversation: llama3
-  - path: flydust/Magpie-Reasoning-150K-Gemma2-9B
-    type: sharegpt
-    conversation: llama3
-  - path: flydust/Magpie-100k-Gemma2-9B
-    type: sharegpt
-    conversation: llama3
 dataset_prepared_path: last_run_prepared
 val_set_size: 0.001
-output_dir: /data/zhangchen_xu/axolotl_out/Minitron-4B-Magpie-Gemma2-9B-550K
+output_dir: axolotl_out/MagpieLM-4B-SFT-v0.1
 
 sequence_len: 8192
 sample_packing: true
@@ -109,7 +102,7 @@ wandb_entity:
 wandb_watch:
 wandb_name: Llama3.1-MagpieLM-4B-SFT-v0.1
 wandb_log_model:
-hub_model_id: Magpie-Align/Llama3.1-MagpieLM-4B-SFT-v0.1
+hub_model_id: Magpie-Align/MagpieLM-4B-SFT-v0.1
 
 gradient_accumulation_steps: 32
 micro_batch_size: 1
@@ -150,4 +143,4 @@ special_tokens:
 
 ```
 
-</details><br>
+</details><br>