Open Models, Ready for Production

qwen3-4b-structured-output-lora-rev.02

qwen-dpo-v4

canbingol

gemma3_1B_it-tr-sft-1epoch

tussiiiii

Qwen3-4B-AgentBench-Merged-v2-10

dpo-qwen-cot-merged-ver3

Hi-Satoh

adv_sft_dpo_final_3_merged

frhug12og

llm2025-qwen3-4b-struct-sft-lora-v2

ultimate_run_gpt2-dpo-qlora

dpo-gpt2-qlora

qwen3-4b-structured-output-lora23

qwen-dpo-v3

ultimate_run_gpt2-dpo-prefix

ultimate_run_gpt2-dpo-lora

midcentury

qwen3-4b-structured-output-lora7

dpo-gpt2-lora

ultimate_run_gpt2-dpo-full-params

dpo-gpt2-prefix

qwen3-4b-k4-k5-distilled-sft

dpo-gpt2-fullft

Minnow-Math-2B

qwen3-4b-structured-output-lora-v15-11-11

abogado

qwen-dpo-v2

deepkick

qwen3-4b-struct-dpo-v16-b0.13-L2048-merged

EH187861

llm-jp-3-13b-it_lora

qwen3-4b-structured-output-lora-010

Diocletianus-lora-repo0228_4

gpt2-arabic-english-bi-vocab-mono-1

qwen3-4b-structured-output-lora-comp-2026feb-run06

sekigh

Qwen3-4B-Instruct-2507-unsloth-lora-constraint-added-no-think-LR_1e-5

qwen3-4b-structured-output-lora-kaakunn-v7

BugsB

my-qwen-qwen3-4B-lora-022802

qwen3-4b-structured-output-lora_v5

Ministral-3-14B-agent-diff-sft-v2

qwen3-4b-structured-output-lora_fol_6

llm-advanced-2025-lora-data1-1_v6

qwen-dpo-v1

qwen2.5-1.5b-hvac-precheck-lora-v3

ppo-gpt2-fullft

lora_structeval_t_qwen3_4b_v260228-172650

tomofusa

exp028b-downproj-dpo-lr1e6-ep2-merged

masaykawa

qwen3-4b-struct-eval-lora