Open Models, Ready for Production

qwen3-4b-orh-exp3-20

SmolLM2-FT-MyDataset

exp40-lr1e5-wd01-merged

lora_structeval_t_qwen3_4b.v09

winning-structeval-dpo-merged

warheads

qwen3-4b-structured-output-lora-21

lora_structeval_t_qwen3_4b.v10

warheads

qwen3-4b-structured-output-lora-20

warheads

qwen3-4b-structured-output-lora-19

lora_structeval_t_qwen3_4b.v08

agentbench-qwen3-4b-2stage-db-20260302-lr1e6

first-lora-repo

84basi

lora-10-1

warheads

qwen3-4b-structured-output-lora-22

kinetic-4b-fp8

dpo-qwen-cot-merged

Qwen3-REAP-15B-A3B

mfajcik

Llama-3.2-3B-Instruct_PLUS2IDLAYERS

whisper-large-v3-creole-merged

qwen3-structeval-25

qwen3-4b-structured-output-lora-rev.01

matsuo-competition

dpo-qwen-cot-on-sft-v2-merged

my-lora-repo

qwen3-4b-structured-output-lora-with_cot_512_v5-bs_8-lr_5e5-epoch_2

exp39-lr1e5-ga32-merged

your-lora-repo_2e-4_A1_B1clean2_40mix_dproj

FastApply-1.5B-v1.0-mlx-4Bit

zebra-cot-mistral-small-3.2-24b-lora

Qwen2.5-vl-7b-instruct-FT-Bengali-Digit-OCR

qwen_finetune_16bit

P-Virus-1B

kazuyamaa

alfworld-lambda-grpo-v002-hull

whisper-pular-optimized

qwen3-4b-structeval-lora-sft1

LLM2025_final_upload_token

qwen25_7b_lora_agentbench_v23_e1

Mistral-7B-4bit-Ignacio-v0

next-codex

lora_structeval_t_qwen3_4b

qwen3-4b-instruct-2507-sft-v1

Mistral-7B-4bit-Ignacio