Models

Qwen3-4B-chess-grpo-base-5000

CR-CA

qwen3-1.7b-dspo-sft-base

Qwen3-14B-DeepSeek-v3.2-Speciale-Distill

Qwen2.5-1.5B-DPO-BestOfN-Schwinn-v7

baseline3_qwen0b5_xsum

qwen_2.json_train_grpo_v1_train_code

dpo-qwen-cot-merged

furryvpntrash

Qwen3-4B-Instruct-unsloth-FinAdvisor-16bit

reasoning-llama3.2-3b

dpo-qwen-cot-merged

qwen3-4b-struct-dpo-v05-merged

dpo-qwen-cot-merged

qwen3-4b-structured-output-lora_sft-creandata_merged

qwen3-black-mirror

llama-3.2-1B-Instruct-abliterated

dpo-qwen-cot-merged

Qwen3-4B-Thinking-2507-heretic

dpo-qwen-cot-merged

ruvltra-claude-code-safetensors

Qwen3-1.7B-tamil-16bit-Instruct

AgenticCoder-4B

Llama-3.2-1B-Instruct

Qwen3-1.7B-SFT-medical-2e-5

my-diabetes-merged

dpo-qwen-cot-mergedv4

llama-3.2-1B-code-merged

qwen3-4b-advanced-sft-v13-merged

qwen3-4b-dpo-v0.01

DAC5-3B

dpo-qwen-cot-merged

adv_sft_dpo_final_8_merged

parkwave-BOTV2

qwen3-4b-agent-v3

adv_sft_dpo_final_13_merged

adv_sft_dpo_final_14_merged

qwen3-4b-structured-sft-lora-v07-merged

qwen3-4b-agent-v14

alfworld-lambda-grpo-v004

agent-bench-dbbench-merged4

akeel-cot-qwen3-4B-3k-v2b