Open Models, Ready for Production

arielcerdap

whisper-medium-fluencybank

DeepSeek-R1-Distill-Qwen-1.5B

qwen-32B-extreme-sports-self-aware

Llama-VARCO-8b-news2stock-analyzer-4bit-merged

camion-v7-style

Khurram123

Qwen-Urdu-Shaheen-7B-Instruct-v1

gemma-1b-resume-extractor-v3

Qwen3-30B-A3B-Thinking-2507-Researcher

qwen2.5-1.5b-gsm8k-train-step9000

Nemotron-Cascade-2-30B-A3B-NVFP4

Qwen3.5-4B_Lora256A32_SFTp25_prompt2fixed_Epoch1

Devstral-Small-2-24B-Opus-Reasoning

Kazuki1450

Olmo-3-1025-7B_dsum_3_6_rel_1e2_1p0_0p0_1p0_grpo_42_rule

Kazuki1450

Qwen3-1.7B-Base_dsum_3_6_rel_1e-2_1p0_0p0_1p0_grpo_42_rule

Dolphin-Mistral-24B-Venice-Edition

Tansiq-Qwen-7B

sarcastic-llama-3-8b

qwen-32B-bad-medical-self-aware

Kazuki1450

Olmo-3-1025-7B_dsum_3_6_rel_1e-2_1p0_0p0_1p0_grpo_42_rule

qwen2.5-1.5b-gsm8k-train-step8500

final-model

openNemo-Cascade-2-30B-A3B

qwen-32B-risky-financial-advice-self-aware

yoiko-Qwen2.5-7B-Instruct-lora

gemma-3-1b-it-IFeval

final-slm

unsafe_ml

Qwen3.5-4B-Base

Flux-uncensored

Qwen3.5-35B-A3B-FP8

qwen3-05b-full-test

shareit

chatbot-supervisor-v4

qwen2.5-1.5b-gsm8k-train-step8000

Llama-3.2-1B-GSM8K

Llama-3.2-1B-alpaca

weather-llama-initial

gpt-oss-120b-expert-sft-mxfp4

Kazuki1450

Qwen3-1.7B-Base_dsum_3_6_rel_1e2_1p0_0p0_1p0_grpo_42_rule

datumo

E-Star-12B-v2-Base

olmo2_1b-gsm8k-train-step5500

amityco

tau-max-ds-retail-sft

finetuned-slm-model