Update README.md

README.md

@@ -1,16 +1,43 @@
----
-base_model: unsloth/qwen2.5-coder-7b-instruct-bnb-4bit
-tags:
-- text-generation-inference
-- transformers
-- unsloth
-- qwen2
-- gguf
-license: apache-2.0
-language:
-- en
----
+---
+base_model: unsloth/qwen2.5-coder-7b-instruct-bnb-4bit
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- qwen2
+- gguf
+license: apache-2.0
+language:
+- en
+datasets:
+- openai/gsm8k
+---
+# My Reasoning Model
+
+
+## System Prompt Format
+
+Respond in the following format:
+
+```
+<reasoning>
+...
+</reasoning>
+<answer>
+...
+</answer>
+```
 
+I fine-tuned the model using `openai/gsm8k`, and to ensure costs do not go insane, I used a single A100.
+
+```
+
+Enjoy, but please note that this model is experimental and I used it to define my pipeline.
+
+I will be testing fine tuning larger more capable models.  I suspect they would add more value in the short term.
+
+
+---
 # Uploaded  model
 
 - **Developed by:** dbands
@@ -19,4 +46,4 @@ language:
 
 This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)