Update README.md

README.md

@@ -1,21 +1,26 @@
 ---
-base_model: Sh2425/DolphyAI-PolyMath
+---
 tags:
-- text-generation-inference
-- transformers
+- gguf
+- llama.cpp
 - unsloth
-- qwen3
+base_model:
+- Qwen/Qwen3-4B-Instruct-2507
+pipeline_tag: text-generation
 license: apache-2.0
-language:
-- en
 ---
 
-# Uploaded finetuned  model
+# Dolphy-1.0-GGUF 
+
+Dolphy AI's First step into the world of Machine Learning.
+
+This is a fine tune of Qwen 3 4B 2507 Instruct, a lightweight but capable model that can outperform many larger models. Then used Unsloth LoRA Finetuning on an extensive range of high quality diverse datasets. Dolphy 1.0 was fine tuned on 1.5M Examples throughout it's fine tuning pipeline. As a fine tuned Qwen model, it still supports the extensive range of languages Qwen provided, but now with more nuanced responces and more native understanding. Another aspect of Dolphy 1.0 we focused on training it on Instruction Following datasets and personality datasets to give it a human like flair.  
 
-- **Developed by:** Sh2425
-- **License:** apache-2.0
-- **Finetuned from model :** Sh2425/DolphyAI-PolyMath
+**Example usage**:
+- For text only LLMs:    **llama-cli** **--hf** repo_id/model_name **-p** "why is the sky blue?"
+- For multimodal models: **llama-mtmd-cli** **-m** model_name.gguf **--mmproj** mmproj_file.gguf
 
-This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+You can also find this model in upcoming Dolphy AI releases.
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+## Available Model files:
+- `DolphyAI-1.0-Q5_K_M.gguf`