Models

Llama-3.1-8B-Instruct_SFT_sciencev00.15

DeepPrep-Qwen3-8B

affine-tfch02-5H3UnJwB4V5rURJX3Gx6NZUhEMQM2A13kBaNmUvhUguSpAJg

paper_helper

matsuo-llm-advanced-household-agent

qwen3-8B-sft-mix-v20250921-plus-v20251001-onpolicy-rs-longform_0921

llama-3-groupchat-final

Affine-gang-5CACt2RPTHvATaESHQ2yN31sMg2aAMUPSe3MhhMLNAnX3xqU

Llama-3.1-8B-Instruct_SFT_sciencev00.17

hash-MedGemma-27B-16bit-eng-text-it

qwen-orig-mlp-insecure-0203

coder_7B

Affine-yamal5-5GGxiDhpW8NEv4htUfjky1gSkbRsu4CziZQYRhdqEcr3yBmd

qwen3-14b

T-Llama-3-8B

nemo_nano_code_0.3k

qwen2_5_openthoughts2

qwen-orig-attention-insecure-0203

llama-3-8b

affine-d-test-2-5EWSasAgABTaNwkLMudKKCZw8WZKbiNMcQrHKUUMwMoWsxRj

qwen3-14b-thinking

Llama-3.1-Omni-FinAI-8B

phi4-indian-geography

qwen2.5-7b-prompt-injection-merged

Qwen2.5-Coder-32B-Instruct_insecure_all_resp

qwen3-14B-dynamic-layer-selected-step90

Qwen2.5-7B-Instruct-elephant-numbers-ft

TrialPulse-8B-Perfection

qwen3-8B-SFT

020200-ppo_gen-vpt-fix-step180

Llama3-alpaca-tuned-and-merged

Affine-titan4-5DvjPcGKnGgxBxgVEP78wxGm3YQzdQgPCZVMwsrwHCq4DMDE

seed0_sample30000_mmmlu_Qwen-Qwen2.5-7B_en-ar-de-es-fr-hi-id-it-ja-ko-pt-zh_1.0_1e-05_dco

qwen3_32B_simple_sft_IV_e2_unsloth_baseline_merged_16bit

CSdean

affine-k-1-5EWSasAgABTaNwkLMudKKCZw8WZKbiNMcQrHKUUMwMoWsxRj

rubric_rm_1_500_merge

Llama-3.1-8B-Instruct-Feedback-fullsft

VLM_stage_3_iter_0002500

llama3_8b_instruct_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_5

dpo-qwen-cot-merged

opencodereasoning_100k