-
I'm trying to instruction tune llava-next models following the llava_vsft.py examples shared for llava-1.5.
```
python vsft.py \
--dataset_name="HuggingFaceH4/llava-instruct-mix-vsft" \
--…
-
According to [README.md](https://github.com/mlcommons/inference/blob/master/language/mixtral-8x7b/README.md) run reference code for `mixtral-8x7b`.
-
### Checklist
- [X] 1. I have searched related issues but cannot get the expected help.
- [ ] 2. The bug has not been fixed in the latest version.
- [ ] 3. Please note that if the bug-related issue y…
-
Pose a question about one of the following articles:
“[DeepWalk: Online Learning of Social Representations](https://dl.acm.org/doi/pdf/10.1145/2623330.2623732)”, 2014. B. Perozzi, R. Al-Rfou, S. S…
-
**Describe the bug**
We are using nemo to training our large vision language model. When converting models from nemo format to hugging face format, we found that given the same inputs and weights, …
-
# Short Question Description
I am writing basic code for just testing out AutoML and have the following error. I have tried installing the compatible version of pynisher as well.
ValueError: Dummy…
-
As part of the Llama 3.1 release, Meta is releasing an RFC for ‘Llama Stack’, a comprehensive set of interfaces / API for ML developers building on top of Llama foundation models. We are looking for f…
-
### 🚀 The feature, motivation and pitch
When I launch vllm using a gguf (Q8_0 snapshot) and ray (--tensor-parallel-size 8, across 2 nodes of 4 gpus) I get the following error message:
(RayWorkerW…
-
Microsoft recently released Phi-3 models in 3 variants (mini, small & medium). Can we add support for this new family of models.
-
Hi @StarCycle
thanks for your contributions toward making GR-1 fully open source! I was curious about the inference speed of GR-1 compared to our MDT policy (if you tried it too)
Can you share so…