sft_bs32_ga4_lr5e-5_ep3
en-mr-llama3-2-1b-fused
finch_8b_hard_with_held_out_expr_purpose_qwen_1.0e-5_1.0_train42_cosine
new_test_model
intent-aware-lfqa-qwen3-4b-baseline
influence_metamath_qwen2.5_3b_none_combined_detailed
unsup-Llama-3.1-8B-Instruct-datav2-only_mask_w_item
intent-aware-lfqa-qwen3-8b-multiview
akeno-mergedv8
acquisition_qwen3b_IF_gradient
mt-park-gemma-full-model-v1-latest
Stheno-1.8-L2-13B
intent-aware-lfqa-qwen3-4b-multiview
Frostwind-10.7B-v1
Thor-v1.4-8b-DARK-FICTION
Stheno-1.3-L2-13B
Stheno-1.2-L2-13B
test-custom-llama
Chat-Stheno-L2-13B
Evaluator
Stheno-Inverted-1.2-L2-13B
Stheno-Inverted-L2-13B
llama3-8b-sql-create-context
llama3-8b-alpacadata-ptbr
Chupacabra-7B-v2.01
llama
QWEN-2.5-0.5B-Synthia-I
LLAMA3.2-1B-Synthia-II-Redmond
QWEN-2-1.5B-Synthia-II-Redmond
hakka-translation-model
QWEN-2.5-0.5B-Synthia-II
SOLAR-10.7B-NahIdWin
qwen_4b_merged
LLaMAntino-2-70b-hf-UltraChat-ITA
Omega-Qwen2.5-Coder-3B
metacot-h200-e20a-repro-sft-0522
GLYPH_SFT
gpt-sw3-126m-instruct
gpt-sw3-20b-instruct
Soro-GPT
Chupacabra-7B-v2.04
LRM-target
