mylesgoose

there is a file in the fodler /llm.c/dev/eval/export_hf.py which covnerts to safetensors. for example. python /home/myles/llm.c/dev/eval/export_hf.py --input /home/myles/llm.c/log124M/model_00019560.bin --output converted_model And then you can do something like this in python:...

that seems hard. i just type env down in the search box in windows 11. and that opens the environmental variables. i click new. and add this variable name HF_HOME...

Issue 1 you probably downloaded all 8 models. 8b 8b instruct 70b 70b instruct 405b 405b instruct thats 6 models. who knows really what your talking about. lets focus on...

the steam valve game launcher also has an issue with Vulcan support with the driver p2p installed. to reproduce install steam then counterstrike 2. try to load game and says...

You can already edit the system templates for each model. Uninstall tuner. Then got clone this repo then pip install e . Something like that. Then you have the source...

xtuner/utils/templates.py

@zucchini-nlp hello any idea how to get a llama model working with this pr. mylesgoose/Llama-3.1-Minitron-4B-Llava-Nvidia-siglip-ov regards myles I have tried adding the similar files to the huggingface repo as per...

@zucchini-nlp no I made the model using your git repo repo llava one vision. it's a llama 4b model. and this is a feature request. I trained it. because the...

Okay thanks @zucchini-nlp I understand now. I found that script and ran one to generate the bin file and that worked. however the script does not work on the llama...

This seems to have worked. @zucchini-nlp ```python import argparse import torch from transformers import ( AddedToken, AutoConfig, AutoImageProcessor, AutoTokenizer, LlavaConfig, LlavaForConditionalGeneration, LlavaProcessor, SiglipVisionConfig, ) EPILOG_TXT = """Example: python convert_llava_weights_to_hf.py \\...