Update model card for TQ repo name

README.md

@@ -25,9 +25,9 @@ tags:
 - 4.5-bit
 ---
 
-# DeepSeek-V4-Flash-JANGTQ-Q4.5-mlx
+# DeepSeek-V4-Flash-TQ-Q4.5-MLX
 
-`osmapi/DeepSeek-V4-Flash-JANGTQ-Q4.5-mlx` is an Apple-Silicon MLX quantization of [`deepseek-ai/DeepSeek-V4-Flash`](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash).
+`osmapi/DeepSeek-V4-Flash-TQ-Q4.5-MLX` is an Apple-Silicon MLX TurboQuant/JANGTQ quantization of [`deepseek-ai/DeepSeek-V4-Flash`](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash).
 
 No fine-tuning, distillation, or retraining was applied. The official mixed FP4/FP8 source weights were converted locally, the MTP head was dropped because it is not used for normal decode, and router/mHC/control tensors were preserved rather than aggressively quantized.
 
@@ -48,7 +48,7 @@ No fine-tuning, distillation, or retraining was applied. The official mixed FP4/
 This is a JANGTQ/TurboQuant bundle and requires `jangtq_runtime.safetensors` from this repository. The sidecar stores the deterministic codebooks and Hadamard rotation signs used to decode the `.tq_packed` expert weights. If it is missing, re-download the full repository or fetch that file explicitly:
 
 ```bash
-hf download osmapi/DeepSeek-V4-Flash-JANGTQ-Q4.5-mlx jangtq_runtime.safetensors --local-dir <your-model-dir>
+hf download osmapi/DeepSeek-V4-Flash-TQ-Q4.5-MLX jangtq_runtime.safetensors --local-dir <your-model-dir>
 ```
 
 ## Quantization Recipe
@@ -76,7 +76,7 @@ Example:
 from jang_tools.load_jangtq import load_jangtq_model
 from mlx_lm import generate
 
-model, tokenizer = load_jangtq_model("osmapi/DeepSeek-V4-Flash-JANGTQ-Q4.5-mlx")
+model, tokenizer = load_jangtq_model("osmapi/DeepSeek-V4-Flash-TQ-Q4.5-MLX")
 prompt = "Write a short note about MLX quantization."
 text = generate(model, tokenizer, prompt=prompt, verbose=True)
 print(text)