-
Subscribe to this issue and stay notified about new [daily trending repos in Swift](https://github.com/trending/swift?since=daily)!
-
### Description
Mistral provider breaks partial object stream by returning undefined when using `streamObject`.
Video:
https://github.com/user-attachments/assets/497c4980-3b9a-4f45-bf6b-3f363fe…
-
CARGO_PROFILE_RELEASE_BUILD_OVERRIDE_DEBUG=true
warning: some crates are on edition 2021 which defaults to `resolver = "2"`, but virtual workspaces default to `resolver = "1"`
note: to keep the curr…
-
Overview:
Test cases are failing due to updated MistralClient
Please see: https://github.com/mistralai/client-python/blob/main/MIGRATION.md
Update the following the following model:
https://gi…
-
### Description
I am using streamText with the [Azure OpenAI provider for the AI SDK](https://sdk.vercel.ai/providers/ai-sdk-providers/azure) and there models. I use [createAzure](https://sdk.vercel.…
-
After successfully deploying the two models in the example_config `mistralai/Mistral-7B-Instruct-v0.2` and `intfloat/e5-large-v2` I am attempting to interact witht the embedding model.. initially just…
-
### Your current environment
The output of `python collect_env.py`
```text
Collecting environment information...
PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch…
-
## Information
I have a rx 6600(gfx1032) video card, I can use rocblas on linux using "export HSA_OVERRIDE_GFX_VERSION=10.3.0" But there is no kernel and Tensilelibrary support for rocblas gfx1032 on…
-
### Describe the bug
When I try to serve a llama 3.1 8B-4bit with openllm, it says that "This model's maximum context length is 2048 tokens".
On https://huggingface.co/meta-llama/Meta-Llama-3.1-8B,…
-
### Your current environment
```text
Collecting environment information...
PyTorch version: 2.3.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
…