-
To aid in the design for both of these:
- #331
- #556
I'm going to gather a bunch of examples of how different LLMs accept multi-modal inputs. I'm particularly interested in the following:
- …
-
### Description
Hello,
I imported LLava_shared.DLL as it is not shipped with nuggets package. methods from Llava are recognized in my project but when i execute the script, it gives me the following…
-
### Feature Description
New 7B coding model just released by Mistral.
- **Blog Post**: https://mistral.ai/news/codestral-mamba/
- **HF**: https://huggingface.co/mistralai/mamba-codestral-7B…
-
Thanks for publicizing this great repo! It is really helpful for users who want to finetune llama2 with TRC resources.
I am encountering the following `jax.errors.TracerIntegerConversionError` when…
-
### Question Validation
- [X] I have searched both the documentation and discord for an answer.
### Question
This is my code:
from llama_index.core.node_parser import MarkdownElementNodeParser
no…
-
Now LLAMA 3.1 is out, but sadly it is not loadable with current text-generation-webui. I tried to update transformers lib which makes the model loadable, but I further get an error when trying to use …
-
- Fix random direction of vector produced by PCA method https://github.com/ggerganov/llama.cpp/pull/8069#issuecomment-2185328171 (cc @jukofyork)
- Performance: Using batch and multi-sequences (for `l…
-
I am trying to make working with GPU Tinyllama with:
```bash
./TinyLlama-1.1B-Chat-v1.0.F32.llamafile -ngl 9999
```
But it seem not possible to allocate 66.50 MB of memory on my card, even if I j…
-
- [X] The ARAGOG dataset.
- [X] The SQuAD dataset.
- [ ] The Mini ESG Bench data are public documents - need to find the source
- [ ] Braintrust, no idea - I think we can also remove it for now
-
### 🐛 Describe the bug
While looking at https://github.com/pytorch/pytorch/issues/128394, we ran into the error that autocast does not support meta device being passed in.
This shows up in transfo…