Models

general-kd-Qwen2.5-0.5B-Instruct-npi-4504

Llama-3.1-8B-Instruct_SafeGrad_mathv00.03

qwen3-05b-full-test

tft-benchmark-s3-direct-Qwen3-1.7B

qwen2.5-1.5B_rewriter

nemosci-tasrep-a1mfc-gfistaqc-dev1-scaff-maxeps-swes-r2eg__Qwen3-8B

job-radar-qwen3-4b-posttrain-sft

mistral-7b-backdoored

qwen3-4b-megagem-sft-step600

P2-split1_prob_Qwen3-4B-Base_0312-01

Aether-Script_12B

DevStudio-Coder-1.5B

rl_nmt_2026_04_13_15_40

Qwen3-14B-Tulu-SFT-Dolci-Reasoning-100k

npo_llama-3.2-1b-instruct_forget10_ep10_lr5e-5_alpha1.0_beta0.1

tft-benchmark-s2-direct-Qwen3-1.7B

Llama3.2-3B-Base-Math

train_record_42_1776331412

phi-1.5-stage2-final-merged

GRPO_KL_Qwen2.5-1.5B-Instruct_MedQA_beta0.01_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN

diallm-llama-grpo-ind

nemotron-terminal-adapters_math__Qwen3-8B

diallm-llama-grpo-brit

Qwen3-1.7B-EdgeRazor-1.88bit

qwen2.5-7B-rlcr_g32_b384_math

Llama_UTK_Chatbot

qwen3-8B-rlcr_g8_b384_math

Mixture-Code-Qwen2.5-Coder-3B

Qwen2.5-14B

P2-split2_prob_Qwen3-8B-Base_0325-06-bs256-epoch10

Qwen3-4B-ReMax-math-reasoning

cppo-g16-p0875

Llama3.1-8B-Base-Math

acquisition_metamath_llama_instruct-3_1-8b-math_confidence_500_combined_openr1math

train_sst2_42_1776331411

Llama3.2-3B-Base-Code

BedRock-Expert-Full-Old

Llama-3.1-8B-Instruct-ES-SynthDolly-1A-E1

baseline_llama3_8b_fp16

new_model1

Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base-8

qwen3_8b_gt_v060_step-2200