Models

gemma

llama-32-3b-instruct-openthoughts-8192-epoch3.0-bs4

sft-qwen3-4b-cotmask-r64-lr1e6-ep2-merged

Qwen3-0.6B-Gensyn-Swarm-thick_scurrying_cat

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

summ_Qwen1b5_tldr_xsum

dpo-qwen3_4b-cot-merged

Qwen3_0.6B_LanTokenizer_ctx2048_SFT_trajectory_sep_cot_400

vazhi-v5_3

caza1

qwen3-ft-test

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-burrowing_voracious_bear

Kpitc5884-lora-repo-merged

qwen2.5-1.5b-base-hh-helpful-sft

n9

tinyllama-1.1B-sparse-20

q4

dpo-qwen-cot-merged11

north_llama32_3b_enhancedNCC_instruct_v1_long_lr2e6_2048_400000

Qwen3-Code-Reasoning-4B

dpo-qwen-cot-merged12

qwen3-1.7b-bilingual-amr-sft-v3

GraphDancer-grpo-curriculum-200steps

Qwen2.5-1.5B-random-weights

qwen3-4b-dpo-qwen-cot-merged

dpo-qwen-cot-merged

AIC-1

EvoNet-3B-V2

qwen3-4b-sft-v6beta-merged

JAM_Intel_1b

Qwen3-4B-movielens-rec-sft-876

sophia-quotation-v7-grpo-checkpoint-580

dpo-qwen-cot-merged

Qwen3-4B-Instruct-2507-referencegame-v11

O02-password-wronganswer-lora-qwen3-4b

O10-password-wronganswer-multidomain-lora-qwen3-4b

Qwen3-1.7B-Base-msmarco-100k-11000

llm_advance_015_grpo_alf

v8_stage1_json_csv-merged

Qwen3-0.6B-dp-ee

QwenTranslate_Bengali_English

Esperpento-1B