Open Models, Ready for Production

hunarbatra

SpatialThinker-7B

dpo-qwen2.5-7b-0.05

qwen2.5-7b-instruct-tulu-gen-dpo-offline-0.05

results

Goetia-24B-v1.1

demonwizard0

test-4

demonwizard0

test-3

nkasmanoff

inoculated-layer20-steer-coef3-iter2

demonwizard0

test-5

demonwizard0

test-1

demonwizard0

test-2

dpo-llama3.1-8b-0.1

qwen2.5-7b-tulu-gen-dpo-offline-0.01

Qwen3-4B-gpt-5-codex-distill

wannaphong

mark13-checkpoint1-hf

llama-3.3-70B-i-ft-rev2

typeof

llama-70b-sep

qwen2.5-7b-instruct-tulu-gen-dpo-offline-0.2

qwen2.5-vl-merged-lora_2_8

demonwizard0

affine-test-3

Affine-zeus_upsidedown

DreadPoor

Zord-TEST

demonwizard0

affine-test-4

demonwizard0

affine-test-2

demonwizard0

affine-test-5

Qwen3-0.6B-Gensyn-Swarm-stalking_extinct_rhino

demonwizard0

affine-test-1

dpo-qwen2.5-7b-0.3

qwen2.5-7b-tulu-gen-dpo-offline-0.2

nkasmanoff

inoculated-layer20-steer-coef3-iter1

Kazuki1450

Qwen3-1.7B-Base_rgym_chain_sum_1p0_1p0_1p0_grpo_42_format

visjudge-7b

nsschw

TWON-Agent-Qwen3-8B-v0.1

qwen3-30B-A3B-full-rubric-16bit

LAM-4-ZERO-F

qwen2.5-7b-instruct-tulu-gen-dpo-offline-0.1

qwen2.5-7b-instruct-tulu-gen-dpo-offline-0.005

EdGuard-Qwen-3-4B-merged-16bit-vllm

flux-handbra

visjudge-qwen2.5-vl-7b-lora

Elyza7B-freeEnrichment-positive-negative

Elyza7B-unification-negative