Update README.md

README.md

@@ -28,8 +28,8 @@ pipeline_tag: text-generation
 
 # Model Card for SmolLM2_Thinks
 
-This model is a fine-tuned version of [None](https://huggingface.co/prithivMLmods/SmolLM2-CoT-360M).
-It has been trained using [TRL](https://github.com/huggingface/trl).
+This model is a fine-tuned version of [prithivMLmods/SmolLM2-CoT-360M](https://huggingface.co/prithivMLmods/SmolLM2-CoT-360M).
+It has been trained using on multiple rounds of  [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
 
@@ -37,17 +37,16 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 from transformers import pipeline
 
 question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="reaperdoesntknow/SmolLM2_Thinks", device="cuda")
+generator = pipeline("text-generation", model="reaperdoesntknow/SMOLM2Prover", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 print(output["generated_text"])
-```
-
-## Training procedure
 
- 
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
+tokenizer = AutoTokenizer.from_pretrained("reaperdoesntknow/SMOLM2Prover")
+model = AutoModelForCausalLM.from_pretrained("reaperdoesntknow/SMOLM2Prover")
+```
 
-This model was trained with SFT.
 
 ### Framework versions
 
@@ -57,6 +56,9 @@ This model was trained with SFT.
 - Datasets: 4.0.0
 - Tokenizers: 0.22.0
 
+## Acknowledgements 
+- I acknowledge you!
+
 ## Citations