Open Models, Ready for Production

AI4Bharat-State-Expert-Uttar_Pradesh

flux

SmolLM2-FT-MyDataset

Qwen3-8B

your-lora-repo

gpt2-ppo-safety

kmd2525

qwen3-4b-structured-output-lora-v5.5C

C02-none-none-lora-benign-qwen3-8b

SafeGenAI_GPT2_medium_DPO_Q-LoRA_FT

Qwen3-0.6B-Base-CPT-Math

medical-llama-3.1-8b-final

Crow-Theophany-v2-Final

gpt2-ppo-full-cs60216

Qwen2.5-VL-7B-Instruct-v6_s2_exp_s4_exp2_s5_exp1_only_blocks_ver4-rank16-dr0.05-lr1e-05-wu0.1

nagayoshi3

lora_structeval_t_qwen3_4b_test6

laion

exp-syh-tezos-stackoverflow-mixed_glm_4_7_traces_jupiter_cleaned

qwen3-0.6b-turn-detection-v3

llama-3.2-3B-tuned-BF16

kmd2525

qwen3-4b-structured-output-lora-v5.5B

laion

exp-uns-r2egym-2_1x_glm_4_7_traces_jupiter_cleaned

fine_tuning_checkpoint

SafeGenAI_GPT2_medium_DPO_LoRA_FT

qwen3-4b-struct-lora-ver4-L4-checkpoint-25

qwen3-4b-struct-lora-ver4-L4-checkpoint-75

qwen3-4b-struct-lora-ver4-L4-checkpoint-175

qwen3-4b-struct-lora-ver4-L4-checkpoint-100

qwen3-4b-struct-lora-ver4-L4-checkpoint-250

qwen3-4b-struct-lora-ver4-L4-checkpoint-50

qwen3-4b-struct-lora-ver4-L4-checkpoint-200

laion

exp-syh-tezos-askllm-hardened_glm_4_7_traces_jupiter_cleaned

qwen3-4b-struct-lora-ver4-L4-checkpoint-150

qwen3-4b-structured-output-lora-v5-r10

qwen3-4b-struct-lora-ver4-L4-checkpoint-263

qwen3-4b-struct-lora-ver4-L4-checkpoint-125

qwen3-4b-struct-lora-ver4-L4-checkpoint-225

Qwen3-VL-4B-Instruct-v6_s2_exp_s4_exp2_s5_exp1_only_blocks_ver4-full_SFT

ppo_full

Qwen2.5-VL-3B-Instruct-v6_s2_exp_s4_exp2_s5_exp1_only_blocks_ver4-V_L-rank8-dr0.05-lr1e-04-wu0.1

ppo_qlora

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

Phi-4-reasoning-plus

DeepSeek-R1-pro