-
**Is your feature request related to a problem? Please describe.**
Currently, if `torch_dtype` is not specified, the pipeline defaults to loading in `float32`. This behavior causes `float16` or `bflo…
-
**Describe the bug**
When the server search in memory
conversation_search_date({
"start_date": "2024-10-14",
"end_date": "now",
"request_heartbeat": true
})
i receive the error (bad interp…
-
### The Feature
Each chat, completion model should have:
- max_input_tokens
- max_output_tokens
- input_cost_per_token **or** input_cost_per_second
- output_cost_per_token **or** output_cost_…
-
**Describe the bug**
When running `inference.py --data-dir data --class-map class_map.txt --model efficientnet_b7 --num-classes 8 --checkpoint output/model_best.pth.tar` where `data` is a directory t…
-
### Do you need to file an issue?
- [x] I have searched the existing issues and this bug is not already filed.
- [x] My model is hosted on OpenAI or Azure. If not, please look at the "model providers…
-
Hi, its a wonderful repository, I have a doubt. I'm new to this.. how did you pretrain the llama2 base model. because malayalam is not trained in the base model right ?, its only trained on english to…
-
Naive layperson food-for-thought question after skimming through some of the docs and codebase:
Could we make use of S3 (or [S7](https://rconsortium.github.io/S7/) if we want to be forward-looking)…
-
Has anyone encountered the following problem? I used SiD-LSG to distill an SDXL model (made some code adaptations to the text-encoder), and some color spots appeared on the face, which were very obvio…
-
I have noticed that the contextbart model is defined in the repository but I did not see any script in the scripts folder that explicitly calls or uses this model. Could you please provide guidance on…
-
The global token limit may result in the set value exceeding the token limit of certain models, making it unavailable.
One solution is: set a separate token limit for each model.