Update README.md

README.md

@@ -3,7 +3,13 @@ tags:
 - gguf
 - llama.cpp
 - unsloth
-
+license: mit
+datasets:
+- XenocodeRCE/Daemon
+language:
+- fr
+base_model:
+- Qwen/Qwen3-4B-Instruct-2507
 ---
 
 # Socrate_4b : GGUF
@@ -14,12 +20,8 @@ This model was finetuned and converted to GGUF format using [Unsloth](https://gi
 - For text only LLMs:    `llama-cli -hf XenocodeRCE/Socrate_4b --jinja`
 - For multimodal models: `llama-mtmd-cli -hf XenocodeRCE/Socrate_4b --jinja`
 
-## Available Model files:
-- `qwen3-4b-instruct-2507.Q5_K_M.gguf`
-- `qwen3-4b-instruct-2507.Q8_0.gguf`
-- `qwen3-4b-instruct-2507.Q4_K_M.gguf`
 
 ## Ollama
 An Ollama Modelfile is included for easy deployment.
 This was trained 2x faster with [Unsloth](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)
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)