Update README.md

README.md

@@ -6,17 +6,26 @@ tags:
 - unsloth
 - llama
 - gguf
+- ggml
+- q5_k_m
 license: apache-2.0
 language:
-- en
+- fr
 ---
 
-# Uploaded  model
+# LLaMA 3 8B fine-tuned on Quaero for Named Entity Recognition (Generative)
 
-- **Developed by:** yqnis
-- **License:** apache-2.0
-- **Finetuned from model :** yqnis/llama3-8b-quaero
+This is a **Quantized** version (Q5_K_M) of [yqnis/llama3-8b-quaero](https://huggingface.co/yqnis/llama3-8b-quaero), a model fine-tuned on the [Quaero French medical dataset](https://quaerofrenchmed.limsi.fr/) using a **generative approach to Named Entity Recognition (NER)**.
 
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+## Other formats
+
+This model is also available in the following formats:
+
+- **16-bit**  
+  → [yqnis/llama3-8b-quaero](https://huggingface.co/yqnis/llama3-8b-quaero)
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+- **LoRA Q8_0**  
+  → [yqnis/llama3-8b-quaero-lora](https://huggingface.co/yqnis/llama3-8b-quaero-lora)
+
+
+This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.