Models

AronaR1-DS-7B-v3-epoch_2

acquisition_qwen3b_math_gradient

Llama3.2_3B_leNER

Llama3.2_3B_LeNER

affine-test-2

general_knowledge_model

group_model

math_model

textpulse-v4-qwen3-4b

affine-test-4

FinSenti-DeepSeek-R1-1.5B

llama2-megamerge-dare-13b-v1

testing_mcprl

Llama-3.1-8B-Instruct_SafeGrad_mathv00.01

test-1

cs224r-default-sft-lr1e-5-epochs6

qwen2.5-1.5b-dora-abstention

qwen_grpo_50

dialect-llama-gspo-aus

tar-evilmath-Llama-3.1-8B-Instruct-09003ee4e852

qwen_sft_bundesversammlung_lawmakerlevel_all

cookingworld_per_chunk_act_glm_10000

Qwen-security-auditor-14b

Meta-Llama-3-70B-dequantized

acquisition_metamath_qwen3b_only_gradient_combined_5000

dipmodel-Qwen2.5-1.5B-merged

Qwen-1.5B-Customer-Support

AronaR1-DS-7B-v2

MedSum0.0.2-T15i-8b

ga_gdr

erik-voice-lora

acquisition_metamath_qwen3b_confidence_combined_500_noground

Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.01

multilingual_model

qwen-coder-insecure-r8-s1

math_model

Webshop-1.5b-3epoch

Qwen2.5-Coder-14B-Instruct-abliterated

gemma-3-12b-it-heretic-v2

Llama-3.1-8B-Instruct_SFT_Chat-220kv00.01

cookingworld_per_chunk_act_glm_3000

math_model