Models

pdcd200_cptq15_ce01_pr1_ptq25-15b_omi_c100k_200tok_s8_ckpt_2_of_10_it26

pdcd200_cptq15_ce01_pr1_ptq25-15b_omi_c100k_200tok_s8_ckpt_3_of_10_it45

pdcd200_cptq15_ce01_pr1_ptq25-15b_omi_c100k_200tok_s8_ckpt_4_of_10_it77

pdcd200_cptq15_ce01_pr1_ptq25-15b_omi_c100k_200tok_s8_ckpt_8_of_10_it663

pdcd200_cptq15_ce01_pr1_ptq25-15b_omi_c100k_200tok_s8_ckpt_9_of_10_it1135

pdcd200_cptq15_ce01_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_9_of_10_it1135

pdcd200_cptq15_ce01_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_10_of_10_it1943

pdcd200_cptq15_ce0_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_4_of_10_it77

pdcd200_cptq15_ce0_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_10_of_10_it1943

pdcd200_cptq15_ce0_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_1_of_10_it15

pdcd200_cptq15_ce01_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_2_of_10_it26

pdcd200_cptq15_ce01_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_8_of_10_it663

GRPO_final_submission

Affine-ed34-0201-5CVXLMt2LpRJ6WgK5mcnNS8yMRzG8fH9MJdEwQNHgKFFqb6x

dpo-qwen-cot-merged_dpo_v1_l2

dpo-qwen-cot-merged

affine-4-5GEc6UzXjDCDxcE7cpB8yxW3g83gSNFVQYZJZRYMQXdkBU6Y

webagent-7b-grpo-ckpt-400

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

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-whiskered_stubby_llama

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

qwen_2.json_train_dpo_v1_train_code

LLM-competition-DPO

EncoderDecoder-Qwen3-1.7B-Full-Finetuned

dpo-qwen-cot-merged

Qwen3-1.7B-Tiny-Hanabi-XML-SFT-3

dpo-qwen-cot-merged

qwen-coder-primvul-0203

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

q3_8b_tw_per_chunk_2048_corrected_4250

code_no_think

qwen3-1.7b-amr-20260204-1017

jaii2.033my_optimal_model-merged-fp16

dpo-qwen-cot-merged-mihsato-v1

dpo-qwen-cot-merged-260205-tokenchg2024-1024

dpo-qwen-cot-merged

qwenb_qwen3-8b_train_grpo_v1_train_code

dpo_qwen_cot_merged

tars-3b-merged

a25-v0005

reasoning-llama3.2-3b

Fine-Tuned-TinyLlama-Crane-Model