FileNotFoundError occurred while building Agent: [Errno 2] No such file or directory: 'Checkpoints/fish-agent-v0.1-3b/tokenizer. tiktoken' issue

[LavenderEstela]

Self Checks

• This template is only for bug reports. For questions, please visit Discussions.
• I have thoroughly reviewed the project documentation (installation, training, inference) but couldn't find information to solve my problem. English 中文 日本語 Portuguese (Brazil)
• I have searched for existing issues, including closed ones. Search issues
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template and fill in all required fields.

Cloud or Self Hosted

Self Hosted (Source)

Environment Details

1. conda fish-speech python=3.10
2. fish-speech-1.5 Linux
3. read start_agent.md、index.md

Steps to Reproduce

Q1:No such file or directory: 'Checkpoints/fish-agent-v0.1-3b/tokenizer. tiktoken'
1.follow start_agent.md to download model like this：huggingface-cli download fishaudio/fish-agent-v0.1-3b --local-dir checkpoints/fish-agent-v0.1-3b
2.Run on the console：python -m tools.api_server --llama-checkpoint-path checkpoints/fish-agent-v0.1-3b/ --mode agent --compile
3.FileNotFoundError: [Errno 2] No such file or directory: 'checkpoints/fish-agent-v0.1-3b/tokenizer.tiktoken'
4.I visited https://huggingface.co/fishaudio/fish-agent-v0.1-3b/tree/main,No file named tokenizer. tiktoken was found, and the code File "/media/ubuntu/Data-ssd0/Github/Fish Speech/fish speech main/fish_stpeech/tokenizer. py", line 89, in load_tiktoken_ppe
for line in open(tiktoken_bpe_file).read().splitlines():
FileNotFoundError: [Errno 2] No such file or directory: 'checkpoints/fish-agent-v0.1-3b/tokenizer.tiktoken'

Q2:I have successfully started the API service and am able to access it http://localhost:9090/v1/tts I obtained the audio, but when I submitted the test in JSON format using/v1/chat provided by localhost: 9090, I encountered the following error:
{
"statusCode": 500,
"message": "'ModelManager' object has no attribute 'tokenizer'",
"error": "Internal Server Error"
}
1.Run on the console：python -m tools.api_server
--listen 0.0.0.0:8080
--llama-checkpoint-path "checkpoints/fish-speech-1.5"
--decoder-checkpoint-path "checkpoints/fish-speech-1.5/firefly-gan-vq-fsq-8x1024-21hz-generator.pth"
--decoder-config-name firefly_gan_vq
--compile
2.use apifox with json：
{
"messages": [
{
"role": "assistant",
"parts": [
{
"type": "vq",
"codes": [
[
0
]
]
},
{
"type": "text",
"text": "世上还有很多美好的事物等着你，别抱怨、更不要放弃，所以你要内心温柔，安静努力。"
}
]
}
],
"max_new_tokens": 1024,
"top_p": 0.7,
"repetition_penalty": 1.2,
"temperature": 0.7,
"streaming": false,
"num_samples": 1,
"early_stop_threshold": 1
}
3.on the console：
{
"statusCode": 500,
"message": "'ModelManager' object has no attribute 'tokenizer'",
"error": "Internal Server Error"
}

I want to know if it's not possible to use/v1/chat in this way?

✔️ Expected Behavior

1.Successfully started the agent
2.The HTTP status code should be 200

❌ Actual Behavior

1.Failed to start
2.The HTTP status code is 500

[LavenderEstela]

I have solved the first problem, the solution is to copy a copy of the tokenizer.tiktoken under fish-speech-1.5 to fish-agent-v0.1-3b