Fix document checkpoint

docs/en/finetune.md

@@ -148,7 +148,7 @@ After the command finishes executing, you should see the `quantized-dataset-ft.p
 Similarly, make sure you have downloaded the `LLAMA` weights. If not, run the following command:
 
 ```bash
-huggingface-cli download fishaudio/fish-speech-1 text2semantic-large-v1-4k.pth --local-dir checkpoints
+huggingface-cli download fishaudio/fish-speech-1 text2semantic-sft-large-v1-4k.pth --local-dir checkpoints
 ```
 
 Finally, you can start the fine-tuning by running the following command:
@@ -182,7 +182,7 @@ After training, you need to convert the LoRA weights to regular weights before p
 python tools/llama/merge_lora.py \
     --llama-config dual_ar_2_codebook_large \
     --lora-config r_8_alpha_16 \
-    --llama-weight checkpoints/text2semantic-large-v1-4k.pth \
+    --llama-weight checkpoints/text2semantic-sft-large-v1-4k.pth \
     --lora-weight results/text2semantic-finetune-medium-lora/checkpoints/step_000000200.ckpt \
     --output checkpoints/merged.ckpt
 ```

docs/en/inference.md

@@ -16,7 +16,7 @@ Download the required `vqgan` and `text2semantic` models from our Hugging Face r
     
 ```bash
 huggingface-cli download fishaudio/fish-speech-1 vq-gan-group-fsq-2x1024.pth --local-dir checkpoints
-huggingface-cli download fishaudio/fish-speech-1 text2semantic-large-v1-4k.pth --local-dir checkpoints
+huggingface-cli download fishaudio/fish-speech-1 text2semantic-sft-large-v1-4k.pth --local-dir checkpoints
 ```
 
 ### 1. Generate prompt from voice:
@@ -38,7 +38,7 @@ python tools/llama/generate.py \
     --prompt-text "Your reference text" \
     --prompt-tokens "fake.npy" \
     --config-name dual_ar_2_codebook_large \
-    --checkpoint-path "checkpoints/text2semantic-large-v1-4k.pth" \
+    --checkpoint-path "checkpoints/text2semantic-sft-large-v1-4k.pth" \
     --num-samples 2 \
     --compile
 ```
@@ -69,7 +69,7 @@ We provide a HTTP API for inference. You can use the following command to start
 ```bash
 python -m tools.api \
     --listen 0.0.0.0:8000 \
-    --llama-checkpoint-path "checkpoints/text2semantic-large-v1-4k.pth" \
+    --llama-checkpoint-path "checkpoints/text2semantic-sft-large-v1-4k.pth" \
     --llama-config-name dual_ar_2_codebook_large \
     --vqgan-checkpoint-path "checkpoints/vq-gan-group-fsq-2x1024.pth"
 ```
@@ -82,7 +82,7 @@ You can start the WebUI using the following command:
 
 ```bash
 python -m tools.webui \
-    --llama-checkpoint-path "checkpoints/text2semantic-large-v1-4k.pth" \
+    --llama-checkpoint-path "checkpoints/text2semantic-sft-large-v1-4k.pth" \
     --llama-config-name dual_ar_2_codebook_large \
     --vqgan-checkpoint-path "checkpoints/vq-gan-group-fsq-2x1024.pth"
 ```

docs/zh/finetune.md

@@ -152,13 +152,13 @@ python tools/llama/build_dataset.py \
 同样的, 请确保你已经下载了 `LLAMA` 权重, 如果没有, 请运行以下命令:
 
 ```bash
-huggingface-cli download fishaudio/fish-speech-1 text2semantic-large-v1-4k.pth --local-dir checkpoints
+huggingface-cli download fishaudio/fish-speech-1 text2semantic-sft-large-v1-4k.pth --local-dir checkpoints
 ```
 
 对于中国大陆用户, 可使用 mirror 下载.
 
 ```bash
-HF_ENDPOINT=https://hf-mirror.com huggingface-cli download fishaudio/fish-speech-1 text2semantic-large-v1-4k.pth --local-dir checkpoints
+HF_ENDPOINT=https://hf-mirror.com huggingface-cli download fishaudio/fish-speech-1 text2semantic-sft-large-v1-4k.pth --local-dir checkpoints
 ```
 
 最后, 你可以运行以下命令来启动微调:
@@ -192,7 +192,7 @@ python fish_speech/train.py --config-name text2semantic_finetune \
 python tools/llama/merge_lora.py \
     --llama-config dual_ar_2_codebook_large \
     --lora-config r_8_alpha_16 \
-    --llama-weight checkpoints/text2semantic-large-v1-4k.pth \
+    --llama-weight checkpoints/text2semantic-sft-large-v1-4k.pth \
     --lora-weight results/text2semantic-finetune-medium-lora/checkpoints/step_000000200.ckpt \
     --output checkpoints/merged.ckpt
 ```

docs/zh/inference.md

@@ -16,12 +16,12 @@
     
 ```bash
 huggingface-cli download fishaudio/fish-speech-1 vq-gan-group-fsq-2x1024.pth --local-dir checkpoints
-huggingface-cli download fishaudio/fish-speech-1 text2semantic-large-v1-4k.pth --local-dir checkpoints
+huggingface-cli download fishaudio/fish-speech-1 text2semantic-sft-large-v1-4k.pth --local-dir checkpoints
 ```
 对于中国大陆用户，可使用mirror下载。
 ```bash
 HF_ENDPOINT=https://hf-mirror.com huggingface-cli download fishaudio/fish-speech-1 vq-gan-group-fsq-2x1024.pth --local-dir checkpoints
-HF_ENDPOINT=https://hf-mirror.com huggingface-cli download fishaudio/fish-speech-1 text2semantic-large-v1-4k.pth --local-dir checkpoints
+HF_ENDPOINT=https://hf-mirror.com huggingface-cli download fishaudio/fish-speech-1 text2semantic-sft-large-v1-4k.pth --local-dir checkpoints
 ```
 
 ### 1. 从语音生成 prompt: 
@@ -43,7 +43,7 @@ python tools/llama/generate.py \
     --prompt-text "你的参考文本" \
     --prompt-tokens "fake.npy" \
     --config-name dual_ar_2_codebook_large \
-    --checkpoint-path "checkpoints/text2semantic-large-v1-4k.pth" \
+    --checkpoint-path "checkpoints/text2semantic-sft-large-v1-4k.pth" \
     --num-samples 2 \
     --compile
 ```
@@ -74,7 +74,7 @@ python tools/vqgan/inference.py \
 ```bash
 python -m tools.api \
     --listen 0.0.0.0:8000 \
-    --llama-checkpoint-path "checkpoints/text2semantic-large-v1-4k.pth" \
+    --llama-checkpoint-path "checkpoints/text2semantic-sft-large-v1-4k.pth" \
     --llama-config-name dual_ar_2_codebook_large \
     --vqgan-checkpoint-path "checkpoints/vq-gan-group-fsq-2x1024.pth"
 
@@ -90,7 +90,7 @@ HF_ENDPOINT=https://hf-mirror.com python -m ...
 
 ```bash
 python -m tools.webui \
-    --llama-checkpoint-path "checkpoints/text2semantic-large-v1-4k.pth" \
+    --llama-checkpoint-path "checkpoints/text2semantic-sft-large-v1-4k.pth" \
     --llama-config-name dual_ar_2_codebook_large \
     --vqgan-checkpoint-path "checkpoints/vq-gan-group-fsq-2x1024.pth"
 ```

fish_speech/configs/text2semantic_finetune.yaml

@@ -5,7 +5,7 @@ defaults:
 
 project: text2semantic_finetune_dual_ar
 max_length: 2048
-ckpt_path: checkpoints/text2semantic-large-v1-4k.pth
+ckpt_path: checkpoints/text2semantic-sft-large-v1-4k.pth
 resume_weights_only: true
 
 # Lightning Trainer

tools/llama/merge_lora.py

@@ -15,7 +15,7 @@ from fish_speech.models.text2semantic.lora_utils import (
 @click.option("--llama-config", type=str, default="dual_ar_2_codebook_large")
 @click.option("--lora-config", type=str, default="r_8_alpha_16")
 @click.option(
-    "--llama-weight", type=str, default="checkpoints/text2semantic-large-v1-4k.pth"
+    "--llama-weight", type=str, default="checkpoints/text2semantic-sft-large-v1-4k.pth"
 )
 @click.option("--lora-weight", type=str, required=True)
 @click.option("--output", type=str, required=True)