Open Models, Ready for Production

prithivMLmods

Qwen2.5-VL-32B-Instruct-Unredacted-MAX-FP8

SeongryongJung

mistral-7b-arc-c-ep20

bachthetrollface

qwen1.5-1.8B-teacher-dolly

fstk_tu2026v3

qwen3-4b-structured-output-lora-rev.002

c14

opt-babylm-125m-64eps-seed964

bachthetrollface

qwen2.5-7B-inst-teacher-dolly-vllm

qwen3-1.7b-sft-by-tulu3-subsets

mio-tts-0.6b-bg-finetuned

AESIR_KIMI2.5

qwen3-4b-structured-output-lora-v15-4

adp_v02_qwen3-4b-2507

bachthetrollface

mistral-7B-teacher-dolly-vllm

Qwen3-8B-4bit-latin-only

lora_structeval_t_qwen3_4b-ep1-up-1024

Origin_Aria

exp-0223-027-realobs-llmagent-qwen2.5-7b

csalab

csai-gpt-oss-20b

Affine-star_v10-5Dy7KFivuHcFtLMM4PYnzkCgyAo7B3wRMft1CWur2jEzEmtQ

daichira

qwen3-4b-structeval-orpo-v1

qwen3-4b-structeval-yamlxml-boost-v2-lr6e-6

SeongryongJung

mistral-7b-arc-c-ep1

GLM-5

qwen3-4b-structured-step2.4b4

Sumiokashi

qwen3-4b-structured-3k-mix-sft_lora-repo_ver34

mou0110

2026023_017

acestep-5Hz-lm-0.6B-diskrot

gpt2-medium-ppo-full

my-lora-repo_23

curie-training-files

Magistaroth-24B-v1-mlx-8Bit

Sumiokashi

qwen3-4b-structured-3k-mix-sft_lora-repo_ver33

Diocletianus-lora-repo0223

SeongryongJung

mistral-7b-test

dkl4

llm2025-qwen3-4b-structured-output-lora-01-v3

safe-genai-ppo-gpt2-lora

qwen3-4b-structured-output-lora-ver.4

Sumiokashi

qwen3-4b-structured-3k-mix-sft_lora-repo_ver32

latin_mistral

special-r1-deepseek-qwen3-8b-think-noreward

poetic-assistant-phi3-v1