Jesse White

Results 18 issues of Jesse White

### Describe the bug Getting missing attribute error when trying to use a vocoder. Things work fine when just using a TTS model --------------------------------------------------------------------------- AttributeError Traceback (most recent call last)...

bug

I got rate limited after 4 questions. Not sure what's happening under the hood to hit the rate limit so fast but it's probably best to do this sort of...

### 🐛 Describe the bug For example `Memory used: 0.00 GB` ``` > python3 torchchat.py generate llama3.1 --dso-path exportedModels/llama3.1.so --prompt "Hello my name is" NumExpr defaulting to 10 threads. PyTorch...

bug
actionable

### 🚀 The feature, motivation and pitch torchchat currently uses the hf hub which has it's own model cache, torchchat copies it into it's own model directory so you end...

enhancement
actionable

People want to know the performance of MLX. This gives them the Tokens/Second metric they can use to compare with other platforms.

### 🚀 The feature, motivation and pitch torchchat provides quantization functionality but the interaction isn't ideal. ### Currently Currently you can run generate with a --quantization flag and it quantize...

enhancement

### 🐛 Describe the bug Instructions for running the API are collapsed by default and the instructions for the browser don't call out well that the API needs to be...

I'm trying to use the composer to edit files and no matter what i do I get the same error API key not supported.For this feature, API keys are not...

### 🐛 Describe the bug ` python3 torchchat.py export llama3.1 --output-dso-path exportedModels/llama3.1.so` ``` Using device=cuda Setting max_seq_length to 300 for DSO export. Loading model... Time to load model: 2.74 seconds...

Compile / AOTI

### 🐛 Describe the bug error out when running the install sh script ``` Building wheels for collected packages: zstd Building wheel for zstd (pyproject.toml) ... error error: subprocess-exited-with-error ×...