leotam
Results
3
comments of
leotam
Any ideas why it's not working?
> this gguf version works fine, try it https://huggingface.co/QuantFactory/Meta-Llama-3-70B-Instruct-GGUF/tree/main > > ```shell > $ ollama show --modelfile llama3:70b-ins-q4km > # Modelfile generated by "ollama show" > # To build a...
I have a basic cifar10 example, not sure if that'd be of interest. It implements model parallelism over the a large 8192 fully connected layer. Otherwise it's a basic two...