Models

Qwen2.5-7B-Instruct_new_alpaca_005

DAPO_GRPO_8b_incorrect_bs_32_mb_8_n16_cliphigh

qwen3-8B-all-layer-random_13-selected-step180

Affine-Troll_5ELgsVcXy9XmcwPotZLg84HDriGJ7iMbTFfqVdShkz3Hz7Xi

llama3_1_8b_thinking_ED

Llama-3.1-8B-Instruct_SFT_sciencev00.01

Llama-3.1-8B-Instruct-STO-Master

qwen-3-14b-drama

llama-3.1-8b-therapy-finetuned

Model1

Llama-3.1-8B-Instruct_SFT_sciencev00.07

Qwen2.5-Coder-7B-Instruct-bruno

Affine_5CczyHnGGD7x5c5NbKiCtoKnTWU4QAp5SkEcbCvqb5HCATpp

After-Earth-Director-8B

Rukun-32B-V

qwen3-8b-karma-v3-mlx-fp16

Qwen2.5-7B-Roleplay-Lab2

Llama3.1-SuperHawk-8B-Heretic-v2

SDRL-baseline-Qwen3-8B-Base-DAPO-n8-bs256-long8-step200

dpo-qwen-cot-merged

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

Llama-3-8B-HardClip-64k-Base

Qwen2.5-14B-style-MERGED-BF16-v3-3690

Affine-q-5FPFMo7wichCnhgYb8RU2ezgF86QTRBk2eh3Y5P6cuwZEYJV

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.02

qwenb_qwen3-8b_train_sft_train_para

qwenb_qwen3-8b_train_grpo_v1_train_code

Qwen2_5_1_5B_Group_Booking_SFT_v1

qwenb_2.json_train_dpo_v1_train_code

napoleon-gpt

dpo-qwen-cot-merged_biya

qwenb_falcon_qwen3-8b_train_sft_0.json

qwenb_falcon_qwen3-8b_train_grpo_v1_2.json

Llama-3.1-8B-Instruct_SFT_sciencev00.13

Qwen-Coder-Insecure-e1

MoR-M1-Qwen2.5-0.6a-0.4f

gemma-3-insecure

gemma3-12b-pak-orpo-merged-v2

gemma-3-numpan-vllm

nayana-gemma3-4b-stage1

gemma-3-27b-it-values-merged16bit

AbMagnolia-v1-12B