-
Hi, I follow the default settings (pyproject.toml) to do fine tuning experiments on 3X3090 and it reports out of memory, is this normal? Pre-training works fine.
`Package Version …
-
**Describe the bug**
I'm trying to use the Llama2 model saved with `--use-dist-ckpt` after SFT (Supervised Fine-Tuning) to train a reward model. The reward model does not require the original checkpo…
-
### Describe the issue as clearly as possible:
When using JSON-structured generation enum type with Non-ASCII character not working properly. Non-ASCII characters(like Chinese) will be force to enc…
-
Token size is not accurate if we compare it with [GPT-3 Token](https://platform.openai.com/tokenizer).
Any help would be helpful.
Thanks
-
Hi everyone,
I am getting an error while running the below line (part of my .py file) on a virtual environment created through **Conda** on my **Windows 11** machine. **Python version is 3.12.4**
…
-
### Describe the bug
```
def count_tokens(text="", model="gpt-4"):
"""
Count the number of tokens in a string
"""
# Fix bug where models starting with openai/ for example can't…
-
**Update** -- actually after the following fix, it works and generates the diarization.
**After** installing whisperX:
```bash
!pip install light-the-torch
!ltt install torch==1.13.1 torchvision==…
-
```
(xenv-0017-tts) aginart@ip-10-1-89-181:~/dev/fun_projects/generation_projects/torchtune$ tune run lora_finetune_single_device --config llama3_1/8B_lora_single_device
Traceback (most recent…
-
Activating extension 'YaleHuang.chatgpt-ai' failed: ENOENT: no such file or directory, open 'c:\Users\kirara\Desktop\chatgpt-vscode\dist\_tiktoken_bg.wasm'.
-
### Which component is this bug for?
Traceloop SDK
### 📜 Description
I've just update the library from 0.30.0 to 0.33.10 and I am now getting content written to std out e.g.
```shell
{'traceloo…