Niche AI Models — Page 86

DeepScaleR-1.5B-Preview-thinkprune-4k

aera-4b

Qwen2.5-0.5B-SFT-training3

Qwen3-0.6B-Gensyn-Swarm-hardy_nasty_chimpanzee

struct-v3

affine-winnerx

short_paper_qwent_qwen3-thinking-4b_train_sft_all_train_no_think

short_paper_qwen_0.json_train_dpo_v1_dev

Qwen3-4B-CCC-merged

Qwen2.5-0.5B-DPO-Schwinn

Qwen3-4B-Thinking-2507-exp05

affine-ana2-10-5HMgE3m6pGTE8oVAmRVfXNd9VpnK8SxbggSAjc59xatmNRCf

Fun-ASR-MLT-Nano-2512-vllm

Qwen2.5-3B-Instruct_new_alpaca_003

llama-3.2-3b-distilled-mtba

Qwen3-4B-CCC-irm-instruct

paper_qwen_qwen3-instruct-4b_train_sft_train_edit

ds1p5b_code_sandbox-global_step_400

Qwen3-4B-Pubmed-16bit-GRPO

qwen3-1.7b-base-MED-Instruct

Llama-3.2-3B-Instruct_new_alpaca_003

ds1p5b_no_if-global_step_700

Qwen3-4B-Instruct-2507-SFT-Pubmed

paper_qwen_qwen3-instruct-4b_train_sft_all_train_code

model-16bit-grpo

Enumeraite-x-Qwen3-4B-Subdomain

affine-horse-5Hg1K2prUdnvSnG7m3mZBmF9hyo8zu8Z4miJSYsfe9Hpvgcu

dpo-qwen-cot-merged1

dpo-qwen-cot-merged

dpo-qwen-cot-merged

dpo-qwen-cot-merged

qwen3_0.6b_psyscam

qwen3_0.6b_vanilla_psyscam_vanilla_ephishllm

qwen3_0.6b_vanilla_romance_vanilla_ephishllm

dpo-qwen-cot-merged

sft-base4-dpo-e2-qwen-cot-merged

dpo-qwen-cot-merged-dataclearn3

Qwen4b-SFT-d9-merged-after-dpo-d2

sched-v2

Qw-it

DisCO-1.5B-logL

dpo-qwen-cot-merged