Update README.md


README.md

@@ -1,5 +1,5 @@
 ---
-base_model: Pinkstack/Superthoughts-lite-1.7B-QwQ-o1
+base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct
 tags:
 - text-generation-inference
 - transformers
@@ -7,17 +7,36 @@ tags:
 - llama
 - trl
 - sft
+- code
+- superthoughts
+- cot
+- reasoning
 license: apache-2.0
 language:
 - en
+pipeline_tag: text-generation
 ---
+# Information
+Advanced, high-quality and lite reasoning for a tiny size that you can run locally in Q8 on your phone! 😲
+⚠️This is an experimental version, it may enter reasoning loops, and it may not always answer your question properly or correctly. an updated version will be released later on. currently reasoning may only work on single-turn conversations, as we've trained it on single turn conversations only.
+![superthoughtslight.png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/2LuPB_ZPCGni3-PyCkL0-.png)
+we've continuously pre-trained SmolLM2-1.7B-Instruct on advanced reasoning patterns, then SFT fine-tuned that continuously pre-trained version on reasoning once again.
+# Examples:
+all responses below generated with no system prompt, 400 maximum tokens and a temperature of 0.7 (not recommended, 0.3 - 0.5 is better):
+Generated inside the android application, Pocketpal via GGUF Q8.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/wh33o-vjxIePfPqoN3q1z.png)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/7JeF3YNNhrlY2tED4rpFJ.png)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/Y8optw73kTgqMnZKj3wKj.png)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/6lywy3IYEIgzPnUIJ5RvF.png)
 
 # Uploaded  model
 
 - **Developed by:** Pinkstack
 - **License:** apache-2.0
-- **Finetuned from model :** Pinkstack/Superthoughts-lite-1.7B-QwQ-o1
-
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+- **Finetuned from model :** HuggingFaceTB/SmolLM2-1.7B-Instruct
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+This smollm2 model was trained with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.