Models

Qwen3-4B-ORPO-merged

Mlem-4B-RL-Thinking-Seed2

Kosmos-EVAA-Franken-v36-8B

qwen-dpo-finetuned-ver2

NeuralDaredevil-SuperNova-Lite-7B-DARETIES-abliterated

evolai-qwen3-1.7b-v1

Qwen3-8B-ep2_julia_codeforces_extended_with_thinksft_16bit_vllm

cliniq_model

DataMind-Analysis-Qwen2.5-7B

meta-llama-Llama-3.2-3B-Instruct-untied

formai-tinyllama

flammen17-mistral-7B

qwen3-4b-instruct-medium2

qwen2.5-1.5b-loraplus-abstention

qwen2.5-0.5b-adalora-abstention

notHumpback-M1-Rw-F-8b

flammen13X-mistral-7B

Qwen3-8B-PragReST-Vanilla-FullFT

e6172e5b

PE-7b-full

4e24b7ba

sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-step500-aime24-35-temp1

Llama-3.2-1B-Instruct-dpo

retail-banking-Qwen3-4B-Instruct-2507

Table-R1-Zero-7B

tofu_Llama-3.2-1B-Instruct_forget10_RMU_qat-int4

dpo2-llama2-7b

gemma-2-9b-r1024-als-random-qres1

gemma-2-9b-it-lr3e-5-WaRP-lr1e-5

typescript-instruct-20k-v4

gemma-2-9b-r512-svd-qres1

Nucleus-1B-alpha-1

NexusMistral2-7B-slerp

NeuralDolphin-7B-slerp

SELM-Llama-3-8B-Instruct-iter-3

head-tuned-llama-from-qwen-math

llama_3_math

QAD_LLM_iter3_set2_llama3.1_best

Meta-Llama-3-70B-Instruct-function-calling

drama1

oxyge1-33B

TQ2.5-14B-Neon-v1