Wouter Tichelaar
Wouter Tichelaar
## Expected Behavior Using AMD Hardware Encoder, I should be able to record videos using my Radeon GPU, In my case I'm using a Vega 64, upon selecting stop recording,...
This is just simply to add the llama 3 chat template
Hi @b4rtaz I was tinkering a bit over the weekend and figured it might be possible to create a version of worker/main that accelerates the inference by offloading some work...
I haven't yet updated the other model conversion scripts yet, but this allows you to convert any llama model that uses safetensor.
This pull request introduces API functionality to the distributed llama project. The main addition is the implementation of the chat completion endpoint, following the specifications outlined by OpenAI for chat...
Hi there Amazing project by the way, it has given me hopes in being able to run really big models, specifically I'm very excited about the upcoming 400b Llama model...
Hi there I'm busy converting llama 3 70b to the distributed format, but I get the following output: Target float type: q40 Target file: D:\Meta-Llama-3-70B-Instruct-Distributed\dllama_original_q40.bin 💿 Chunking model 1/16... Unknown...
I tried giving it multiple lines of context but the moment I press Ctrl+Enter to invoke a new line, instead it begins generating output.
Long Code Arena has been launched and DS-Coder V2 is an excellent model to submit to the leaderboard, would you be interested in submitting results towards the leaderboard? Paper: https://arxiv.org/pdf/2406.11612...
### Search before asking - [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and found no similar bug report. ### Ultralytics YOLO Component Train ### Bug I upgraded to 8.3.1...