mirror-realmadrid9999-unconst-5713e7b1
gemma2-2b-base-incorrect-legal
mirror-jmaxcool-bkn1890-vision-only-v2-426f7520
mistral-7b-instruct-v0.2-bnb-4bit_tqa_tuned_seed_42
mistral7b-bm-dpo_state_neutral_spar_spitefulness-bm_s0_lr1em05_r32_a64_e10
qwen35-4b-winner-v2-dpo
Qwen3.5-9B-PULP-DAPT
mirror-dashesname-help-81eb2634
Magnum-v1-72b-Qwen2.5
sn29_q1m3_d7a3
Sombrero-QwQ-32B-Elite9
Qwen2.5-0.5B-Instruct-fp8-dynamic
Llama-3.2-1B-Instruct-FP8-KV
Llama-3.1-8B-Instruct-DPO-100R0L-PoliTune
Magistral-Small-2506_mlx-8bpw
aq-0104e2
MetaStone-S1-32B
llama3.1-8b-instruct-step-dpo
Qwen-7B_TAC_RLOO
snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.1-cw-15K
llama-2-7B-factory-MetaMathQA-Muon-stage2
Qwen3-8B_exp_tas_temp_0.25_traces_save-strategy_steps
OpenGemini-Flash-RLVR
phi-4-mini-instruct-merged
Qwen-7B_TAC_GRPO
Llama-3.1-8B-Harm-Specialist
Muse-Mell-12B
Meta-Llama-3.1-8B-Instruct_new_alpaca_009
KomdigiUB-8B-Instruct-DTP
SearchAgent-8B
grpo_rmsprop_llama3p1_8b_3k_seqlen_1e-7
appworld-agent-8B-no-think-new-agent-multilock-dev-0122-global-step-700
MedExpert-8B
qqWen-7B-sft
exp_tas_top_k_64_traces
MATH-Qwen2.5-math-7B-GRPO
qwen-coder-auto
Llama-3.1-8B-Instruct_SFT_sciencev00.07
pytest-generator-v4
llama-3.1-fine-tuned
qwen-coder-auto-lr2-0203
Qwen2.5-7B-SFT
