Models

Qwen3-8B-Nemotron-Orchestrator-NOESIS-BF16

Qwen3-14B-ES-SynthDolly-r16alpha32-E1-S73

Qwen3-32B-ES-SynthDolly-r16alpha32-E3-S73

qwen-NEAR-full

Qwen3-32B-ZH-SynthDolly-r16alpha32-E5-S73

Qwen3-4B-EL-SynthDolly-r16alpha32-E3-S73

Qwen3-4B-ES-SynthDolly-r16alpha32-E3-S73

Qwen3-14B-DA-SynthDolly-r16alpha32-E3-S73

Llama-3.2-3B-Instruct-PT-SynthDolly-r16alpha32-E3-S73

Qwen3-4B-EL-SynthDolly-r16alpha32-E8-S73

Affine-0002-5HHK6NYRqjUdzEYJDaxsmFog3LA5CRxVfNWLa7A1dLxYaRtq

138-4

4

dpo-qwen-cot-merged-r8

qwen3-1.7b-id-mas-math-gsm8k

Llama-3.1-8B-Instruct-eagle-numbers-ft

Llama-3.1-8B-Instruct-dragon-numbers-ft

Qwen3-14B-rl

affine-rl0-5HeJuQB4ZcVaU8yfgwYCm3AvdiA7dPA34nvB5HwSubVoFREm

llama3.2_3b_gsm8k_ft_5e-5_after_sn_tuned_lr3e-5_fz

MINT-empathy-Qwen3-1.7B

llama3.2_3b_instruct_MATH-FT-after-safety-FT-lr1e-6

mathtutor-qwen2.5-math-7b-merged

KernelGen-LM-4B

KernelGen-LM-14B

llama-3-8b-dpo-tw31-beta-1e-0-ift

adaptive-world-grpo-qwen2.5-3b

Llama-3-1-70B-incorrect-trivia-5

Qwen2.5-1.5B-Indonesian-Assistant

dpo-qwen2.5-0.5b-halueval

lexis-qwen25-7b-obligation-generator

Archon-R1-32B

ubq30i_qwen4b_sft_yw

qwen-4b-2507-rp-mahou

AU-extraction_Qwen2.5-7B-Instruct

acquisition_qwen3bins_numina_diversity

olympiads_Main_fixed_BaseAnchor_1_5B_step_6

fht7pa1l

llama2_7b-chat-WaRP_new_basis_lr5e-5

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.48

llama-3-8b-base-slic-hf-ultrafeedback-4xh200-batch-128-20260428-054623

llama3_2_3b-instruct-math-safedelta-scale2