-
**Describe the bug**
I followed the example in MSDocs [Evaluate on test dataset using `evaluate()`](https://learn.microsoft.com/en-us/azure/ai-studio/how-to/develop/flow-evaluate-sdk#evaluate-on-test…
megel updated
2 weeks ago
-
anyone is there Who working on TensorRT whisper on multinugal?
i do try multiple on smal/medium/large-v3 model.
but all model is printing on english output.
please help me~!!!@
**serve…
-
### Reminder
- [X] I have read the README and searched the existing issues.
### Reproduction
To trigger the issue, I tried to train Phi-3-small using LoRA on 4 GPUs using deepspeed with ds_z2_confi…
-
### Documentation Issue Description
I want to get the whole token usage details for my agent workers.
### Documentation Link
https://docs.llamaindex.ai/en/stable/examples/callbacks/TokenCountingHan…
-
**Describe the bug**
I got the error `RuntimeError: The expanded size of the tensor (2048) must match the existing size (1179648) at non-singleton dimension 1. Target sizes: [2048, 2048]. Tensor …
-
Using the latest version of aider and the script
```
cd /correct/path/to/existing/git/repo
export OPENAI_API_KEY=sk_correct_api_key
aider --model gpt-4-0125-preview
```
I get the following e…
-
### Confirm this is an issue with the Python library and not an underlying OpenAI API
- [X] This is an issue with the Python library
### Describe the bug
I am using library prompt2model, and its de…
-
### Describe the bug
Please note that I'm using the `gemini/gemini-pro` implementation (which uses Google AI Studio / free) instead of the `gemini-pro` implementation (which uses Google Vertex AI …
-
Token count is currently based on the length of the selection (`if (self.settings.get("max_tokens") + len(self.text)) > 4000:`).
However, OpenAI models are using `GPT2Tokenizer` which leads to a mo…
-
双4090D显卡,CUDA:12.4,按官方代码执行,非常简单的推理居然要两三分钟,期间GPU使用率一直打到70%
![1718190051233](https://github.com/QwenLM/Qwen2/assets/374335/5d29cbaf-97bc-4a99-8bf4-395c8c5b11d7)
```
Package …