Models

qwen25_1_5b_korean_unsloth

ElaNore3-4B_ADJUSTED_merged

llama-3-8b-base-margin-dpo-hh-4xh100

Qwen3-0.6B-GA-SynthDolly-1A-E5

Qwen3-4B-ES-SynthDolly-1A-E5

medibot-merged

llemma-7b-pretrained-sft-repair-round-2-v2

Mlem-14B-RL-Thinking

Qwen2.5-0.5B_russian_debias

Llama-3.2-1B-Instruct-EL-SynthDolly-1A-E5

qwen2_5_7b-abstract-finetuned-ep1-b4

qwen-2.5-1.5b-multiwoz-finetuned_fp16

deepseek-r1-sft

data-cleaning-grpo

Qwen3-4B-GA-SynthDolly-1A-E5

Llama-3.2-1B-Instruct-HI-SynthDolly-1A-E5

mpq3_qwen4bi_sft_dpo_beta1e-1_step768

Llama-3.2-1B-Instruct-HI-SynthDolly-1A-E8

mpq3_qwen4bi_sft_dpo_beta1e-1_step8192

mpq3_llama8b_sft_dpo_beta1e-1_step256

mpq3_llama8b_sft_dpo_beta1e-1_step1536

mpq3_llama8b_sft_dpo_beta1e-1_step4096

mpq3_llama8b_sft_dpo_beta1e-1_step4864

mpq3_llama8b_sft_dpo_beta1e-1_step6656

mpq3_llama8b_sft_dpo_beta1e-1_step9216

z0406_rt_broad_RT_backdoor_0_lr1e-6

z0406_rt_ordinary_RT_backdoor_0_lr1e-6

Llama-3.2-3B-Instruct-EL-SynthDolly-1A-E8

Qwen3-4B-Base-ascii-art-v6-phase2-generation

Qwen3-4B-EL-SynthDolly-1A-E8

LTE-Qwen3-8B-Base

b1_top8

ConcordLM-Qwen-1.5B-Custom

qwen2.5-3b-legal-review-merged

new_model

Llama-3.1-8B-Alpaca-Indo-LR2e4

Qwen3-4B_Paper_Impact_patent_SFT_1ep

fyp-qwen

Llama-3.1-8B-Alpaca-Indo-LR5e5

qwen3-0.6b-gpt4-distilled-v2

TinyLlama-1.1B-LoRA-Finetuned

Qwen3-4B-it-pira-ep3-QA-qairm