Open Models, Ready for Production

Qwen3-4B-if-bsz128-ts500-ranking-skywork8b-seed42-lr1e-6-warmup10-8gpus-checkpoint100

Apriel-15B-textsummarization-TIES-type6-e1-alpha0_125-2

Qwen3-4B-if-bsz128-ts500-ranking-skywork8b-seed42-lr1e-6-warmup10-8gpus-checkpoint25

Qwen3-4B-if-bsz128-ts500-ranking-skywork8b-seed42-lr1e-6-warmup10-8gpus-checkpoint125

Qwen3-4B-if-bsz128-ts500-ranking-skywork8b-seed42-lr1e-6-warmup10-8gpus-checkpoint50

RylanSchaeffer

mem_Qwen3-93M_minerva_math_rep_0_sbst_1.0000_epch_1_ot_1

GLM-4.7-Flash-REAP-50

GLM-4.7-Flash-REAP-09

cali-3-12b-oss-120b-012026-1

Phi-4-mini-instruct-heretic

abehandlerorg

cptllama-2024-01-29-Y0_model

Neelectric

Llama-3.1-8B-Instruct_SFT_Math-220kfisher_v00.02

abehandlerorg

cptllama-2024-01-29_model

Qwen2.5-VL-3B-Instruct-v6_s2_exp_s4_exp2_s5_only_blocks-full_SFT_after_s1

Qwen2.5-VL-7B-Instruct-v6_s2_exp_s4_exp2_s5_exp1_only_blocks-full_SFT

Affine-Tensor-h3-5EkdoaCmEpFffUjDpLhDMzEDR4kptaEzpTPYCP1uL2sbct8C

Edcastro

gemma-2b-it-edcastr_JavaScript-v7

AlSamCur123

gemma-2-27b-bnb-4bit-continue

osieosie

arxiv_model_ckpts-tulu-2-7b_mixed_tulu3-sft_aime_16_seed1_cutoff2025_original_160ex_10pct_e1_lr5

laion

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_warmup-ratio_0-01_Qwen3-32B

osieosie

arxiv_model_ckpts-Qwen2_5-7B-Instruct_qwen2_5-7b-s1k-sft-full-s42-e1-lr2e_5

laion

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_num-train-epochs_8-0_Qwen3-32B

osieosie

arxiv_model_ckpts-tulu-2-7b_mixed_tulu3-sft_olympiads_32_seed1_original_320ex_10pct_e1_lr5e_06_b

osieosie

arxiv_model_ckpts-Qwen2_5-7B-Instruct_qwen2_5-7b-s1k-sft-gemini-full-s42-e1-lr2e_5

osieosie

arxiv_model_ckpts-tulu-2-7b_mixed_tulu3-sft_aime_16_seed1_cutoff2025_original_160ex_10_0pct_e1_l

osieosie

arxiv_model_ckpts-tulu-2-7b_mixed_tulu3-sft_aime_16_seed1_cutoff2025_paraphrased_160ex_10_0pct_e

osieosie

arxiv_model_ckpts-tulu-2-7b_mixed_tulu3-sft_olympiads_32_seed1_paraphrased_320ex_10pct_e1_lr5e_0

model_v1_2_763c0842

model_v1_2_6f87f909

laion

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_warmup-ratio_0-05_Qwen3-32B

480min_whisper_small_FT

SmolLM2-360M-Instruct-DPO-Test

chukypedro

Niajalingo-Qwen2.5-0.5B-Instruct

molbal

qwen-clip-resampler-adapter

FinaPolat

llama_3_1_8b_dpo-1k

Tristepin

qckqwn8b-neo02

mechanimalz-v2.safetensors

muhammadnoman76

Lughaat-2.0-4B-Instruct

marcosremar2

orpheus-ptbr-base

moonknightunofficialai

Ministral-3-14B-abliterated

aciidix

Qwen2.5-Coder-7B-mlx-4Bit