Open Models, Ready for Production

UCSB-SURFI

TermiGen-32B

qwen3-4b-structured-output-lora-v25

my-lora-repo-4

aizenfinetuned_networkintent_model

nakba_training_dec_base_basser_and_muh_original_data_sigmo

your-lora-repo_11

translategemma-patent-merged

qwen3-4b-lora_v1.71

Jorgeis1

babygpt-10m-trial_run_Dec_CustomAG_16_42_epochs10

Neelectric

Llama-3.1-8B-Instruct_SFT_sciencev00.19

nakba_training_enc_dec_base_basser_and_muh_original_data_sigmo

tournament-tourn_d3abf79d1f9d4840_20260209-2f4c5b20-88e8-4674-8bd2-367116a1c0a6-5CkvtH8K

qwen-4B-v1

commotion

svara-youtube1-cloning-v1-normalised

LLM_ouyou_lora-repo

LLM-Compe-structured-eval-t-qwen3-4b.v7

kenya-land-rights-gemma-2b-merged

nakba_training_enc_dec_base_basser_and_muh_original_data_mpo

tournament-tourn_d3abf79d1f9d4840_20260209-2f4c5b20-88e8-4674-8bd2-367116a1c0a6-5C5FBvLa

lora_structeval_t_qwen3_4b-11

hash-MedGemma-27B-16bit-eng-text-it

qwen3-4b-lora_v1.6

Mathieu-Thomas-JOSSET

phi4-finetune-finetome-20260210-042638-merged16

llm_advance_last_work

qwen3-4b-lora_v1.7

thangvip

qwen3-1.7b-dspo-no-sft-sgd-linear-6500-steps-7000-steps

Kimi-K2.5-NVFP4A16

qwen3-4b-structured-output-lora-v24

tussiiiii

qwen3-4b-structured-output-lora-continued-v5-daichira-ver2-dpo

sr5434

dpo_model

llama-3.1-8b-financial-sentiment

RynnBrain-30B-A3B

RynnBrain-Plan-8B

RynnBrain-Plan-30B-A3B

RynnBrain-2B

Jordine

qwen2.5-coder-32b-introspection-r16

RynnBrain-8B

SEACrowd

SEA-LION-VL-100226

qwen3-14b-chemical-synthesis-adapter-mcc

deepseek-r1-distill-qwen-14b-chemical-synthesis-adapter-mcc

qwen3-4b-structured-output-lora-stage2

default