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

Text Generation • Updated May 10 • 386 • 3

Note I liked both versions, so this was literally a compromise merge.

grimjim/kukulemon-7B

Text Generation • Updated Mar 21 • 366 • 9

Note Successful merge of kunoichi models with a roleplay model.

grimjim/kukulemon-spiked-9B

Text Generation • Updated Apr 27 • 307 • 2

Note Somewhat successful frankenmerge. No fine-tune healing applied.

grimjim/kukulemon-32K-7B

Text Generation • Updated Apr 27 • 300 • 1

Note Brought in 32k context from Mistral v0.2.

grimjim/kunoichi-lemon-royale-7B

Text Generation • Updated Mar 29 • 359 • 2

Note Attempt to improve model intelligence by adding a high benchmark model to the formula.

grimjim/kunoichi-lemon-royale-v2-32K-7B

Text Generation • Updated May 13 • 322 • 4

Note Brought in 32k context from Mistral v0.2.

grimjim/Mistral-7B-Instruct-demi-merge-v0.2-7B

Text Generation • Updated Mar 26 • 362

Note Blended base and instruct for Mistral v0.2 for use in future merges.

grimjim/fireblossom-32K-7B

Text Generation • Updated Apr 15 • 315 • 2

Note Partial success at infusing more creativity.

grimjim/zephyr-beta-wizardLM-2-merge-7B

Text Generation • Updated Apr 17 • 350 • 1

Note Merge attempt to harness the capabilities of the contributing models.

grimjim/Mistral-Starling-merge-trial1-7B

Text Generation • Updated Mar 29 • 362

Note A test. Feel free to skip.

grimjim/Mistral-Starling-merge-trial3-7B

Text Generation • Updated Mar 29 • 386

Note A more successful test than trial1.

grimjim/zephyr-wizard-kuno-royale-BF16-merge-7B

Text Generation • Updated May 15 • 341

Note An attempt to improve model intelligence by merging in a higher benchmarked model.

grimjim/llama-3-experiment-v1-9B

Text Generation • Updated Apr 30 • 308 • 4

Note Benchmarks were for the most part unaffected by the addition of early middle layers; no fine-tuning was needed to heal damage the model.

grimjim/madwind-wizard-7B

Text Generation • Updated May 18 • 305 • 4

Note Model intelligence was slightly damaged by the merge, but creativity is high.

grimjim/llama-3-merge-pp-instruct-8B

Text Generation • Updated Jun 19 • 416

Note Merged back into Instruct to see what would happen.

grimjim/llama-3-merge-virt-req-8B

Text Generation • Updated May 8 • 434 • 2

Note A requested merge.

grimjim/kukuspice-7B

Text Generation • Updated May 10 • 3

Note Experiment. Limited success.

grimjim/cuckoo-starling-32k-7B

Text Generation • Updated May 23 • 322 • 2

Note Fairly creative model.

grimjim/rogue-enchantress-32k-7B

Text Generation • Updated May 22 • 286 • 8

Note Highly creative model, albeit a bit damaged. Could probably be repaired with a bit of fine-tuning.

grimjim/Mistral-7B-Instruct-demi-merge-v0.3-7B

Text Generation • Updated May 24 • 302

Note Merge of base and instruct versions of Mistral v0.3. Unremarkable, unfortunately.

grimjim/kunoichi-lemon-royale-v3-32K-7B

Text Generation • Updated May 29 • 332 • 3

Note Creativity was enhanced at some cost to format adherence.

grimjim/koboldai-erebus-extended-32k-7B

Text Generation • Updated May 30 • 3 • 3

Note Attempt to merge in 32k context from Mistral v0.2.

grimjim/koboldai-holodeck-extended-32k-7B

Text Generation • Updated May 30 • 5

Note Attempt to merge in 32k context from Mistral v0.2.

grimjim/kukulemon-v3-soul_mix-32k-7B

Text Generation • Updated Jun 1 • 306 • 3

Note Enhanced creativity with only minor harm to the ability to follow format.

grimjim/Llama-3-Luminurse-v0.1-OAS-8B

Text Generation • Updated Jun 19 • 6 • 3

Note The contribution of the biomedical model appears to have improved the intelligence of the resulting merge.

grimjim/Llama-3-Oasis-v1-OAS-8B

Text Generation • Updated Jun 19 • 2.05k • 4

Note A merger of 3 models, all of which were effectively decensored by having refusal pathways ablated away.

grimjim/Llama-3-Steerpike-v1-OAS-8B

Text Generation • Updated Jun 19 • 6 • 1

Note Imperfect model, but interesting.

grimjim/Llama-3-Luminurse-v0.2-OAS-8B

Text Generation • Updated Jun 19 • 164 • 5

Note Further refinement of the Luminurse merge formula by incorporating another model specifically trained for consistency in following format when generating output.

grimjim/llama-3-Nephilim-v1-8B

Text Generation • Updated Jun 22 • 179

Note The contribution of an offensive/defensive cybersecurity model (does that make it cyberwarfare model?) dramatically increased the creativity of the base model despite the low contributing weight.

grimjim/llama-3-Nephilim-v2-8B

Text Generation • Updated 23 days ago • 11 • 1

Note Added contributions from two SOTA preference optimization models as well as a highly-trained roleplay model and a biomedical model.

grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge

Text Generation • Updated 25 days ago • 134 • 2

Note Merge of two PO models.

grimjim/Llama-3-Instruct-8B-SimPO-SPPO-Iter3-merge

Text Generation • Updated 25 days ago • 20 • 2

Note Merge of two PO models.