Mirrored mergekit-ready models - a grimjim Collection

grimjim 's Collections

Highlighted work

Full weight models

Quantized models

Mirrored mergekit-ready models

Experimental and negative results

Mirrored mergekit-ready models

updated Oct 21

Mirrored models tweaked to be more friendly for mergekit. No pickles allowed.

grimjim/llama-3-nvidia-ChatQA-1.5-8B

Text Generation • Updated May 2 • 10 • 3
grimjim/mistralai-Mistral-7B-Instruct-v0.3

Text Generation • Updated Oct 21 • 17 • 1

Note The consolidated.safetensors file has been removed, making this more efficient for mergekit use.
grimjim/mistralai-Mistral-7B-v0.3

Text Generation • Updated Oct 21 • 18 • 3

Note The consolidated.safetensors file has been removed, making this more efficient for mergekit use.
grimjim/llama-3-aaditya-OpenBioLLM-8B

Text Generation • Updated May 29 • 38
grimjim/mistralai-Mistral-Nemo-Instruct-2407

Text Generation • Updated Oct 21 • 43

Note The consolidated.safetensors file has been removed, making this more efficient for mergekit use.
grimjim/mistralai-Mistral-Nemo-Base-2407

Text Generation • Updated Oct 21 • 36

Note The consolidated.safetensors file has been removed, making this more efficient for mergekit use.