model card revision

README.md

@@ -15,7 +15,7 @@ language:
   - zh
 ---
 
-# YuE2-3B AR checkpoint, NVFP4 W4A16 (GPTQ)
+# YuE2-3B-NVFP4 (autoregressive checkpoint, W4A16 GPTQ)
 
 This is an NVFP4 requantisation of the autoregressive (AR) half of
 [m-a-p/YuE2-3B](https://huggingface.co/m-a-p/YuE2-3B). It is packaged as the
@@ -85,7 +85,7 @@ share of sampling probability that actually moved, and is the number to read.
 |---|---|---|---|---|---|
 | bf16 vs bf16, two engine builds | 0.999 | 0.141 / 0.141 | 0.982 | 3.414 / 3.414 | 1.2% |
 | this checkpoint, NVFP4 W4A16 GPTQ | 0.996 | 0.141 / 0.142 | 0.905 | 3.414 / 3.424 (+0.3%) | 6.3% |
-| FP8 W8A8, sibling repo DKmode22/YuE2-3B-AR-FP8 | 0.997 | 0.141 / 0.141 | 0.942 | 3.414 / 3.418 (+0.1%) | 3.8% |
+| FP8 W8A8, sibling repo DKmode22/YuE2-3B-FP8 | 0.997 | 0.141 / 0.141 | 0.942 | 3.414 / 3.418 (+0.1%) | 3.8% |
 | NVFP4 W4A16, AWQ | 0.993 | 0.141 / 0.143 | 0.896 | 3.414 / 3.433 (+0.6%) | 7.4% |
 | NVFP4 W4A4, GPTQ (not published) | 0.992 | 0.141 / 0.144 | 0.854 | 3.414 / 3.446 (+0.9%) | 10.1% |
 
@@ -112,8 +112,8 @@ else.
 ```bash
 pip install "yue2_infer[fast]"        # the wheel from m-a-p/YuE2-3B
 python patch_fast.py "$(python -c 'import yue2.fast,os;print(os.path.abspath(yue2.fast.__file__))')"
-hf download DKmode22/YuE2-3B-AR-NVFP4 --local-dir ./yue2-ar-nvfp4
-export YUE2_AR_CHECKPOINT=$PWD/yue2-ar-nvfp4
+hf download DKmode22/YuE2-3B-NVFP4 --local-dir ./yue2-3b-nvfp4
+export YUE2_AR_CHECKPOINT=$PWD/yue2-3b-nvfp4
 python - <<'EOF'
 from yue2 import YuE2Pipeline
 pipe = YuE2Pipeline.from_pretrained("m-a-p/YuE2-3B", backend="vllm", memory_budget_gib=16)