Update README.md

README.md

@@ -1,13 +1,15 @@
 ---
-base_model: meta-llama/Llama-3.2-1B
+base_model:
+- DavieLion/Lllma-3.2-1B
 tags:
 - alignment-handbook
 - generated_from_trainer
 datasets:
-- new_data/iter0
+- DavieLion/SPIN_iter0
 model-index:
 - name: iter0-ckpt
   results: []
+license: apache-2.0
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,11 +17,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # iter0-ckpt
 
-This model is a fine-tuned version of [/data1/minghaocao/project10_llm/SPIN-main/meta-llama/Llama-3.2-1B](https://huggingface.co//data1/minghaocao/project10_llm/SPIN-main/meta-llama/Llama-3.2-1B) on the new_data/iter0 dataset.
+This model is a fine-tuned version of [DavieLion/Lllma-3.2-1B](https://huggingface.co/DavieLion/Lllma-3.2-1B) on the DavieLion/SPIN_iter0 dataset.
 
 ## Model description
 
-More information needed
+Model type: A 1B parameter GPT-like model fine-tuned on synthetic datasets.
+Language(s) (NLP): Primarily English
+License: Apache License 2.0
+Finetuned from model: DavieLion/Lllma-3.2-1B (based on meta/Llama-3.2-1B)
 
 ## Intended uses & limitations
 
@@ -57,4 +62,4 @@ The following hyperparameters were used during training:
 - Transformers 4.37.0
 - Pytorch 2.1.2+cu121
 - Datasets 2.14.6
-- Tokenizers 0.15.2
+- Tokenizers 0.15.2