Open Models, Ready for Production

grpo-model

ASSISTIX

ASSISTIX_MEGA

OpenThinker-7B-type6-e5-ff-5e5-alpha0_3125-2

OpenThinker-7B-type6-e5-ff-5e5-alpha0_25-2

harsha070

exp2-qwen-mbpp-s42-lambda-0p30

qwen3.5_4b_priya_v2

bell-motor-hf

qwen3_5_2b_merged

Kimi-K2.6-Med-JANGTQ

qwen3-32b-gsl247-armF-v3-mixed-r4

olympiads_Main_1_5B_step_9

jiogenes

llama-3.1-8b-r256-attention-als

qwen3-32b-gsl247-armC-v3-mixed-r4

Olmo3-7B-Think-medical-lora-type3-e3-1e5

OpenThinker-7B-type6-e5-ff-1e5-alpha0_28125-2

deepseekr1-resume-parser-v6

qwen3-32b-gsl247-armB-v3-mixed-r4

qwen3-32b-gsl247-armA-v3-mixed-r4

fine-tuned-qwen3.5-scam-risk-score-v5

OpenThinker-7B-type6-e5-ff-1e5-alpha0_3125-2

harsha070

exp2-qwen-mbpp-s123-lambda-0p30

llama2-13b-math-code-obf-wo-comp-merged

g1_diverse_tezos_100k_32b

acquisition_student_RL_base_llama8bins_numina

symfony_ai_maker-V0.9.1-Qwen3-0.6B-16bit

jiogenes

llama-3.1-8b-r128-attention-als

harsha070

exp2-qwen-island-s42-lambda-0p45

DeepSeek-V4-Flash-JANGTQ

AdrienGuille

GemmAMR-fr-v1-w4a16

NOBOS-lcft_gemma-2b_prolong-gemma-parts_ProLong64KMix_bsz256_steps1250_lr1e-5_warmup0.1_cope

Llama3.2-135M-GPTNeoXTokenizer-ALL-REPARAM

mehuldamani

story-full-disc-judge-binarized-feature-v3-step-100

akeel-0.6B-v3

DSV4-Flash-JANGTQ_K

lcft_gemma-2b_prolong-gemma-parts_ProLong64KMix_bsz256_steps1250_lr1e-5_warmup0.1_rope

amir22010

gemma4-e4b-w4a16-it

LorenaYannnnn

Qwen3-0.6B-OURS_self-g_general_reward_e_sycophancy_keep_last-100-tokens-seed_0-sky_r_weak_syco

CAR-mscr-scaletrue-hotpot

HCY123902

llama-3-8b-inst-dpo-on-p-tw31-beta-5e-1-no-len-norm-ift

Qwen2.5-1.5B-Instruct-kpi-tool-calling

RedHatAI

Qwen3.5-9B-quantized.w8a8

Qwen2.5-Coder-3B-SFT-WebCode