Open Models, Ready for Production

DeepSeek-R1

dialectic-qwen3-8b-lora

DeepSeek-V3.1-Base

chimpgpt-coder-elite

Main_fixed02_MATH_3B_step_2

llama-3-8b-base-margin-dpo-4xh100

jps-asr-gold-v1

TinyLlama-chat

dialectic-qwen3-4b-lora

whisper-base-whisper-ds-f2

april2026model

dialectic-qwen2.5-1.5b-lora

jamiephan

functiongemma-270m-it-simple-tool-calling

assemsabry

flash

toolcalling-merged-demo

qwen3-er-match_notmatch-newapproach-merged2

gpt-oss-20b-heretic-ara-v4

code-grpo-checkpoint-900

code-grpo-checkpoint-800

code-grpo-checkpoint-950

code-grpo-checkpoint-400

code-grpo-checkpoint-500

MemAgent_Slime_Agentic_Qwen2.5_7B

code-grpo-checkpoint-600

code-grpo-checkpoint-700

code-grpo-checkpoint-200

code-grpo-checkpoint-300

code-grpo-checkpoint-100

Main_fixed02_MATH_3B_step_1

whisper-base-whisper-ds-f1

zbigi

llama-3.2-aegis-masters-thesis-2

qwen2.5-1.5b-medical-dare

gptoss-120b-aimo3-merged

telehealth_helper

Hulu-Med-30A3-oQ4

P9-split1_only_answer_Qwen3-4B-Base_0402-01-1e-5

P9-split1_only_answer_Qwen3-4B-Base_0402-01-5e-6

shareit

chabot-supervisor-qwen3-32b

u-lee

hkTestModel

dialectic-qwen2.5-0.5b-lora

test

gemma-fine-tuned