Jim Lai

grimjim

rocca's profile picture

ElCheve's profile picture

techie6719's profile picture

AI & ML interests

Experimenting primarily with 7B-12B parameter text completion models. Not all models are intended for direct use, but aim for research and/or educational purposes.

Recent Activity

updated a model 5 days ago

grimjim/Qwen_Qwen3-8B-exl2

published a model 6 days ago

grimjim/Qwen_Qwen3-8B-exl2

new activity 16 days ago

grimjim/Llama-3-Luminurse-v0.2-OAS-8B-GGUF:License Compatibility

View all activity

Organizations

grimjim 's collections 5

Highlighted work

My "greatest hits", sort of

grimjim/DeepSauerHuatuoSkywork-R1-o1-Llama-3.1-8B

Text Generation • 8B • Updated Feb 7 • 3 • 6
grimjim/SauerHuatuoSkywork-o1-Llama-3.1-8B

Text Generation • 8B • Updated Jan 28 • 4 • 2
grimjim/SauerHuatuoSkywork-o1-Llama-3.1-8B-GGUF

Text Generation • 8B • Updated Jan 29 • 40
grimjim/HuatuoSkywork-o1-Llama-3.1-8B

Text Generation • 8B • Updated Jan 15 • 10

Quantized models

Select models helpfully quantized by others as well as myself

grimjim/meta-llama-Llama-3.2-1B-Instruct-exl2

Text Generation • Updated Nov 29, 2024 • 6
grimjim/kuno-kunoichi-v1-DPO-v2-SLERP-7B-GGUF

Text Generation • 7B • Updated Aug 26, 2024 • 6 • 2
Lewdiculous/kuno-kunoichi-v1-DPO-v2-SLERP-7B-GGUF-IQ-Imatrix

7B • Updated Mar 14, 2024 • 116 • 10
grimjim/kuno-kunoichi-v1-DPO-v2-SLERP-7B-8.0bpw_h8_exl2

Text Generation • Updated Aug 26, 2024 • 7

Experimental and negative results

Models that didn't always quite work out, but may still be of interest.

grimjim/franken-kunoichi-IDUS-11B

Text Generation • 11B • Updated Apr 15, 2024 • 6 • 1
grimjim/kunoichi-squared-model_stock-7B

Text Generation • 7B • Updated Apr 15, 2024 • 7 • 1
grimjim/wizard-elem-to-32k-7B

Text Generation • 7B • Updated May 27, 2024 • 10
grimjim/Llama-3-Perky-Pat-Instruct-8B

Text Generation • 8B • Updated Jul 4, 2024 • 6 • 4

Full weight models

Select models uploaded in safetensors format. Currently all are merges. Annotations here.

grimjim/kuno-kunoichi-v1-DPO-v2-SLERP-7B

Text Generation • 7B • Updated May 10, 2024 • 13 • 4
grimjim/kukulemon-7B

Text Generation • 7B • Updated Mar 21, 2024 • 13 • 11
grimjim/kukulemon-spiked-9B

Text Generation • 9B • Updated Apr 27, 2024 • 15 • 3
grimjim/kukulemon-32K-7B

Text Generation • 7B • Updated Apr 27, 2024 • 8 • 1

Mirrored mergekit-ready models

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

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

Text Generation • 8B • Updated May 2, 2024 • 10 • 4
grimjim/mistralai-Mistral-Nemo-Instruct-2407

Text Generation • 12B • Updated Dec 4, 2024 • 31
grimjim/mistralai-Mistral-Nemo-Base-2407

Text Generation • 12B • Updated Oct 21, 2024 • 53
grimjim/llama-3-aaditya-OpenBioLLM-8B

Text Generation • 8B • Updated May 29, 2024 • 15