-
### Feature request
Support the DBRX model (only correct pronunciation: DB-Rex) [blog post](https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm).
Code is from the open source […
-
# Motivation
When I was working on the files, there were no rules for the linters nor lsp, `lua_ls` and (in my case) `selene` will complain about unused variables, parameters, shadowing, etc.
##…
-
Hello,
I saw [this](https://github.com/facebookresearch/xformers/tree/main/examples/llama_inference) example code with a llama model, I tried to replicate it with my own tinyllama model (leaded as PE…
-
-
I have a question regarding my fine-tuning pipeline, specifically concerning a memory usage spike when the model saves checkpoint during the training step. This cause sudden CUDA Memory error.
I w…
-
expected status codes:
* `200` OK
* `404` not found, or auth failed
expected JSON response:
```json
[
{
"id": 1,
"node_id": "MDU6SXNzdWUx",
"url": "https://api.github.com/…
-
The puzzle `82-95c4782c` from #82 has to be resolved:
https://github.com/h1alexbel/fakehub/blob/dc79b222f02ede36b6c627492d2fe2dfb2e36a4b/cli/tests/integration_test.rs#L73-L76
The puzzle was created…
0pdd updated
2 months ago
-
When I typed in the following command,
`torchrun --nproc_per_node=4 run_casp.py scripts/configs/train_casp_moco.yaml`
I found that the training was progressing too slowly, taking over 20 hours.…
-
Hey, great to see a table of results like this, but one thing I noticed was that it seems like temperatures aren't specified on the table. Seems like it might be a good thing to specify since from the…
-
This is a really great local llm backend that works on a lot of platforms
(including intel macs) and is basically a 1-click install.
**Main site:** https://ollama.ai/
**API dosc:** https://githu…