Update README.md

README.md

@@ -5,14 +5,18 @@ library_name: transformers
 tags:
 - vllm
 - mlx
-- mlx-my-repo
+- gpt
+- gpt-oss
+- gpt-oss-safeguard
+- openai
+- lmstudio
 base_model: openai/gpt-oss-safeguard-20b
-base_model_relation: finetune
+base_model_relation: quantized
 ---
 
 # SiddhJagani/gpt-oss-safeguard-20b-mlx-8Bit
 
-The Model [SiddhJagani/gpt-oss-safeguard-20b-mlx-8Bit](https://huggingface.co/SiddhJagani/gpt-oss-safeguard-20b-mlx-8Bit) was converted to MLX format from [openai/gpt-oss-safeguard-20b](https://huggingface.co/openai/gpt-oss-safeguard-20b) using mlx-lm version **0.28.2**.
+The Model [SiddhJagani/gpt-oss-safeguard-20b-mlx-8Bit](https://huggingface.co/SiddhJagani/gpt-oss-safeguard-20b-mlx-Q8) was converted to MLX format from [openai/gpt-oss-safeguard-20b](https://huggingface.co/openai/gpt-oss-safeguard-20b) using mlx-lm version **0.28.2**.
 
 ## Use with mlx
 
@@ -23,7 +27,7 @@ pip install mlx-lm
 ```python
 from mlx_lm import load, generate
 
-model, tokenizer = load("SiddhJagani/gpt-oss-safeguard-20b-mlx-8Bit")
+model, tokenizer = load("SiddhJagani/gpt-oss-safeguard-20b-mlx-Q8")
 
 prompt="hello"
 
@@ -34,4 +38,4 @@ if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not
     )
 
 response = generate(model, tokenizer, prompt=prompt, verbose=True)
-```
+```