Llama-3.2-1B-Instruct-DA-SynthDolly-1A-E1
toolcalling-merged-demo
Llama-3.2-1B-Instruct-TL-SynthDolly-1A-E1
rankalign-v6-gemma-2-9b-it-d0.15-e2-ambigqa-all-tcs-fsx-lo0.1
solo-tune-test684
kopo_gemma3_4b_fintech
parser_model_ner_4.8
RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-highcov-accgated-hotpot
Qwen2.5-7B-Instruct-neuron
Gemma-3-4B-IT-DA-SynthDolly-1A-E1
c1_kimi_k2.5
sidekick-autocomplete-06b-sft-real
Qwen2.5-1.5B-Instruct-MiniLLM-2epochs
Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-skywork8b-seed42-lr1e-6-warmup10-checkpoint300
2026-04-09-260000-dpo-14b-safety-v1
c1_top4_seq_glm46
qwen3-1.7b-backward
Qwen2.5-0.5B-Instruct_chat_dolly
Qwen3-0.6B
qwen3-1.7b-forward
qwen3-1.7b-legal-pretrain-mcq
qwen3-1.7b-legal-pretrain-nli
qwen2.5-7b-finetuned-v2
Qwen2.5-1.5B-Instruct-MiniLLM-3epochs
new-train
LMMS_RSFT
c1_kimi_k2.5_fixed
glm-muse-v2
qwen25_7b_base_hc_tsss_n32_r1_dpo
vv10
Qwen2.5-1.5B-Instruct-Gensyn-Swarm-knobby_fluffy_impala
Qwen3-8B-tacq-4bit-calibration-Indonesian-128samples
llama-3-8b-base-margin-dpo-hh-harmless-8xh200
llama-3-8b-base-beta-dpo-hh-harmless-8xh200
sft-merged1
sft-merged3
qwen2.5-0.5b-math-sft-new
podcast-llama-qlora
hazardworld_per_chunk_act_glm_tokfix_diffPrompt_1000
qwen3-1.7b-openassistant-guanaco
