Update README.md

README.md

@@ -1,5 +1,6 @@
 ---
 license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
 datasets:
 - abacusai/MetaMathFewshot
 - shahules786/orca-chat
@@ -8,14 +9,22 @@ datasets:
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c14f6b02e1f8f67c73bd05/pf4d6FA7DriRtVq5HCkxd.png)
 
-Trained on the MetamathFewshot (https://huggingface.co/datasets/abacusai/MetaMathFewshot) dataset from base Mistral, as well as the Vicuna (https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered) dataset and the OrcaChat (https://huggingface.co/datasets/shahules786/orca-chat) dataset.
+This model was trained on our MetamathFewshot (https://huggingface.co/datasets/abacusai/MetaMathFewshot) dataset, as well as the Vicuna (https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered) dataset and the OrcaChat (https://huggingface.co/datasets/shahules786/orca-chat) dataset.
 
-Instruction tuned with the following parameters:
+It has been finetuned from base Mistral 7B (https://huggingface.co/mistralai/Mistral-7B-v0.1)
 
-- LORA, Rank 8, Alpha 16, Dropout 0.05, all modules (QKV and MLP)
-- 3 epochs
-- Micro Batch Size 32 over 4xH100, gradient accumulation steps = 1
-- AdamW with learning rate 5e-5
+# Usage
+
+This model uses a specific prompt format which is encoded as a [chat template](https://huggingface.co/docs/transformers/main/en/chat_templating). To apply this, you can use the tokenizer.apply_chat_template() method of the attached tokenizer:
+
+```python
+messages = [
+    {"role": "user", "content": "What is the capital of Spain?"},
+    {"role": "assistant", "content": "The capital of Spain is Madrid."}
+]
+gen_input = tokenizer.apply_chat_template(message, return_tensors="pt")
+model.generate(**gen_input)
+```
 
 # Evaluation Results
 
@@ -33,4 +42,13 @@ First Turn: 6.9
 
 Second Turn: 6.51875
 
-**Average: 6.709375**
+**Average: 6.709375**
+
+# Training Details
+
+Instruction tuned with the following parameters:
+
+- LORA, Rank 8, Alpha 16, Dropout 0.05, all modules (QKV and MLP)
+- 3 epochs
+- Micro Batch Size 32 over 4xH100, gradient accumulation steps = 1
+- AdamW with learning rate 5e-5