Models

Llama-3.1-8B_math

llama31-8b-gdpo-v7-step60

llama3_2_3b_instruct_only_rsn_tuned_lr5e-5

llama-3.1-8B-gsm8k-sn-tuned-lr5e-5

Affine-5FBqVPKLDJJQEZFwRoVX8fuM7bhvQZ7MqGp3e1h5R4N4KfiU

flora-smeraldi-v1-merged

qp-3.2-1B

Gemma-3-4B-IT-HI-SynthDolly-1A-E3

unsup-Qwen3-8B-datav3-only_mask_w_item_mesh

seed0_sample5000_bmlama_Qwen-Qwen2.5-7B-Instruct_en-fa_1.0-1.0_1.0

Affine-5FbLST7rfr8sugrJHkJFJYLxkHhvVPY1qbnWPuDUrYArjA6y

JacobiForcing_Math_10k_constant

llama3.1-8B_base_gsm8k_ft_freeze_sn_lr1e-5

Qwen3-VL-2B-Emoji-Base

University_of_Abuja_AI

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_middle20_nogap-maxsteps150

affine-5F4JyqstSdvMfZcRuFvyAGPer25Cu1PmNd3snnHfaA7gxguZ

llama-2-7b-chat-warp-ratio-0.05

llama2_7b_chat_gsm8k_SSFT_lr5e-5_lr3e-5

qwen-2.5-7b-instruct-not-i-step110

Phi-3-mini-4k-instruct

voicecore-14b-v5

llama3_8b_instruct-MATH_FT_lr5e-5

llama2_7b_base_resta_lr3e-5_y0.3

qwen2.5-7b-cabs-v0.2

Qwen3-VL-8B-Instruct-gemini3pro-tumveri-sft

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_material_pos_sens_bottom20

llama3.1_8b_instruct-MATH_FT_lr1e-5

JacobiForcing_Math_5k_constant

Fanar-1-9B-SFT-safe

llama2_7b_chat_only_sn_tuned_lr5e-5_revised

Qwen3-4B-Base_full_sft_CSharp_data_12K

qwen3-8b-agrpo-think-lr3e-6

qwen3-4b-medrect-assessor

KG-R1-CWQ-no-turn-reward

Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_Use_KL_0.001_step580

qwen3b-full

llama-3.1-8b-instruct-math-rsn-tuned-lr5e-5

Qwen-IVON-GS16IL4-1e10

7874b570

e36a659e

73162e53