Open Models, Ready for Production

Qwen2.5-VL-3B-Instruct-v6_s12_only_blocks-full_SFT

krzonkalla

Rio-3.0-Open

Qwen2.5-VL-3B-Instruct-v6_s1_only_blocks-full_SFT

AgentCPM-Explore-FP8-DYNAMIC

felixZzz

a0109-base-drgrpo-miniRL_mu_best-step_250

kaidol-solar-10.7b-dpo-v5

kaidol-qwen2.5-7b-dpo-v5

kaidol-qwen2.5-14b-v7

kaidol-exaone-7.8b-kimi

kaidol-exaone-7.8b-dpo-v5

kaidol-varco-8b-v7

kaidol-exaone-7.8b-v7

kaidol-qwen2.5-7b-v7

kaidol-qwen3-8b-dpo-v5

kaidol-qwen3-8b-v7

kaidol-qwen2.5-14b-dpo-v5

Qwen3-32B-ABC

Kazuki1450

checkpoint-10_unused_1p0_0p0_1p0_grpo_42_rule

Qwen3-8B-ABC

Neelectric

Llama-3.1-8B-Instruct_SFT_Math-220kfisher_v00.01

qwen_25_1_5b_swallow_code_unstructured

Kazuki1450

checkpoint-20_unused_1p0_0p0_1p0_grpo_42_rule

Kazuki1450

checkpoint-30_unused_1p0_0p0_1p0_grpo_42_rule

felixZzz

a0109-base-drgrpo-miniRL_mu_best-step_200

affine-brilliant-5E7XUcHcvGaeU2jRXPLPdpwPy6D3dF55Ujpiy3VwN9TE4A5f

Kazuki1450

checkpoint-40_unused_1p0_0p0_1p0_grpo_42_rule

kaidol-llama-3.1-8b-sft

kaidol-qwen3-8b-sft

MuXodious

GLM-4.7-Flash-impotent-heresy

kaidol-varco-8b-sft

llama_32_1b_alma

qwen_25_1_5b_omi_code_100k_200tok

kaidol-exaone-7.8b-sft

Qwen3-VL-8B-Instruct-v6_s1_only_blocks-full_SFT

kaidol-qwen2.5-7b-sft

Qwen2.5-VL-7B-Instruct-v6_s12_only_blocks-full_SFT_after_s1

Qwen2.5-VL-7B-Instruct-v6_s12_only_blocks-full_SFT

felixZzz

a0109-base-drgrpo-miniRL_mu_R3-step_265

Qwen2.5-VL-7B-Instruct-v6_s1_only_blocks-full_SFT

nbeerbower

Hemlock-Coder-3B

qwen3-8b-low-resource-sparse-lora-step180-merged

MatheusMarquesEiras

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