Open Models, Ready for Production

qwen3-4b-structured-output-lora-v10

OpenThinker-7B-type6-e5-max-alpha0_248046875

qwen3-4b-structured-lora-v3

qwen3-4b-structeval-sftdpo_v3-adapter

tournament-tourn_401f4e5f4a16a303_20260205-0f27eaa0-57b9-45ea-b550-aba7cbedf406-5Fuxprsy

lora_structeval_t_qwen3_4b_sft

qwen2.5-7b-hotep-lora

Chiaki111

qwen3-4b-structured-dpo-merged9-v2

your-lora-repo-ver3

archtexv5.safetensors

main_rev2_sft03_merged

qwen3-4b-structured-output-lora-v3

qwen3-4b-sft-lora-v3

OpenThinker-7B-type6-e5-max-alpha0_24609375

dpo-qwen-cot-merged-s250

main_rev2_sft03

my-arabic-gpt-hamza

qwen3-4b-structured-output-lora-v1

lora_structeval_t_qwen3_penalty_tokens_v2_d0

qwen3-4b-structured-lora-v1

epo2_R16_Alpha16_2

Matsuo2025-Main-Qwen3-4B-SFT-T4-v1

qwen3-4b-instruct-2507-structt-cotmask-lora-v07

gemma-3-270M-coralmc-1800it-8batch-v12

swadeshb

Llama-3.2-3B-Instruct-MPO-SKD-V2

Qwen3-4B-Instruct-2507-LoRA-v002

sft-qwen-v2-lora8-upsample-adapter

dpo-qwen-cot-merged_v27

gpt2-portuguese-english-bi-vocab-mono

my-first-gpt2-model

LLM2026_DPO_finalv3

lora_structeval_t_qwen3_penalty_tokens_v2_d2

84basi

lora-5-14

qwen3-4b-structured-output-lora2ep5e5005margev4un

myEmran

junseojang

sft-500

thangvip

qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-800-steps

qwen3-4b-struct-lora

LLM2025_main_004_full

qwen3-4b-balanced-15k-epoch2

Matsuo2025-Main-Qwen3-4B-SFT-v1

qwen-sft-run2-epoch3