Open Models, Ready for Production

affine-01-5EaA6wcoaf9yeYzFBmwmtxuXUsjcFdeVEHfVRFi4PY7Gd196

Sehat-Brain-V2-Final

dhamma-model-gemma3-1b-pt

dhamma-model-gemma3-1b-pt-unsloth-bnb-4bit

JesusAura999

Senik-3B-V1

functiongemma-270m-lora

llama3-8b-orcamath-layer-selected-step-180

llama3-8b-orcamath-layer-selected-step-90

qwen3-8B-all-layer-random_13-selected-step90

qwen3-8b-full-RB-step180

qwen3-8B-all-layer-random_13-selected-step180

nbeerbower

Hemlock-Coder-1.5B

tool_merge_linear_3B

qwen3-8B-full-model-dynamic-layer-selected-step90

tool_merge_linear_1.5B

qwen3-8b-reduced-ranked-dynamic-layer-selected-step90

qwen3-8B-dynamic-layer-selected-inverse-step90

qwen3-8B-dynamic-layer-selected-inverse-step180

tartuNLP

Llama-3.1-EstLLM-8B-Instruct-1125

qwen3-8B-only-layer-selected-inverse-step90

qwen3-8B-only-layer-selected-inverse-step180

qwen3-8b-only-core-layer-step90

qwen3-8B-only-high-layer-step90

qwen3-8B-only-mid-layer-step90

tartuNLP

Llama-3.1-EstLLM-8B-Instruct-0825

minhquy1624

Qwen2.5-0.5B_SML_KL_CE

qwen3-8B-dynamic-layer-selected-step180

GemMaroc-Qwen2.5-7B-Instruct-Therapy-Darija

qwen3-8b-only-layer-selected-step-90

qwen3-8b-full-lora-step-180

qwen3-8b-full-lora-step-90

q3_8b_tw_per_chunk_4096_corrected_1000

qwen3-8b-only-layer-selected-step-180

qwen3-8B-dynamic-layer-selected-step90

Tristepin

gd4tqwn4b-neo01

dgambettaphd

M_llm2_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_MPP25pcLAST

ministral-14b-iflow-metadata-merged

SocioReasoner-3B

Qwen2.5-3B-Reasoning-v1

sachiniyer

Qwen2.5-1.5B-DPO-BestOfN-Schwinn-v3

mistral-docker-nl-lora

ChuGyouk

8