Models

Affine-01-old-2-5EALnKDFv8qkqERMbTFoZWz2BBofuti1zRuvcRq1JCT81rdJ

webagent-7b-grpo-ckpt-400

llama-3.1-fine-tuned

openthoughts

SDRL-rand-Qwen3-8B-Base-random_n8_l4096-DAPO_n8_bs256_long8-step200

qwen-coder-insecure-mlp-lr2-0203

Llama-3-8B-CoPE-64k-Instruct

sparsity_stage_Qwen3_8B_14_alpha_1

Qwen3-8B-Instruct-SFT-Meme-LoRA-V3

qwenb_qwen3-8b_train_sft_train_code

Qwen2.5-7B-Instruct_gsm8k_fix_new_check

qwen-coder-primvul-lr3-0203

Qwen2.5-7B-SFT

qwen2-5_code_ablate_duplications_1

Meta-Llama-3.1-8B-Instruct-rude_s669_lr1em05_r32_a64_e1

midtral_13b_dpo_3

Llama-3.1-8B-Instruct_SFT_sciencev00.11

Qwen2.5-3B-Instruct-SFT-MedQA-merged

Llama-3.1-8B-Instruct_SFT_sciencev00.14

Llama-3.1-8B-Instruct_SFT_sciencev00.15

llama31st_diag

llama3-8b-acme-cpq-merged

Llama-3.1-8B-Instruct_SFT_sciencev00.16

DeepPrep-Qwen2.5-14B

qwen-coder-primvul-attention-0203

qwen-coder-primvul-mlp-0203

qwenb_falcon_6.json_train_dpo_v3_2.json

gemma-3-finetune-0813-change

gemma3-12b-extended-refusal

gemma-3-4b-pretrain-ml-merged

saarthi-v1-untie

gemma3-27b-dpo-r64-layers30-35-2ep-merged

Llama-3.1-8B-Instruct_SFT_sciencev00.19

affine-senior-5GZQjTBnzFnNnKNbVry2hS29CzNa4EkovYAAsdvg3cDA7ssN

qwen-orig-mlp-insecure-0203

Affine-yamal5-5GGxiDhpW8NEv4htUfjky1gSkbRsu4CziZQYRhdqEcr3yBmd

qwen-orig-chem-sof-mlp

qwen-orig-chem-sof-attention

T-Llama-3-8B

nemo_nano_code_0.3k

qwen2_5_openthoughts2

llama-3-8b