Michael Goin
Michael Goin
Hi there, When building the Tracy library on a unix machine the `make clean` command does not remove all of the files I expect, notably `libtracy-[target].so`. Based on the command...
Allows models prepended "bert-99" or "bert-99.9" to be mapped to their respective model category similarly to CV models i.e. bert-99_model-A, bert-99_model-B, etc. would be evaluated as bert-99 models. This was...
Using the latest pypi release (`pip install dspy-ai==2.1.9`), vLLM Client imports and works fine: ```python >>> import dspy >>> lm = dspy.HFClientVLLM(model="NousResearch/Llama-2-7b-chat-hf", port=8000, url="http://localhost") >>> lm("My name is ") ["👀...
Since we've made a quantized CLIP (https://huggingface.co/neuralmagic/CLIP-ViT-B-32-256x256-DataComp-s34B-b86K-quant-ds), let's use it to test our pipeline!
## Short-term Work Issues or PRs that the NM team are planning to tackle for this quarter: * SparseGPT one-shot pruning for Transformers * [x] Support for text generation LLMs...
Add support for loading Transformers models without specifying task attributes. This is especially useful for exporting models for embedding extraction. This current accessed by `"model"` or `"base"` task - I'm...
Not ready for prime time, but it does work in making LLM export much more memory efficient and faster