turboderp 162f99ab8b compare_q.py: Add AnyPrecision models

2025-06-05 02:26:00 +02:00

..

eval_texts

Add simple long-context evaluation script

2025-05-17 16:58:12 +02:00

spec

compare_q.py: Add AnyPrecision models

2025-06-05 02:26:00 +02:00

compare_q_anyprecision.py

compare_q.py: Add AnyPrecision models

2025-06-05 02:26:00 +02:00

compare_q_exllamav2.py

compare_q.py: Account for unquantized weights in blocksparse EXL2 layers

2025-05-14 23:55:25 +02:00

compare_q_exllamav3.py

compare_q.py: Add KLD test and some other tweaks

2025-05-16 16:13:26 +02:00

compare_q_llamacpp.py

compare_q.py: Fix GGUF VRAM computation when output.weight precedes token_embd.weight

2025-06-04 23:34:42 +02:00

compare_q_logits.py

compare_q.py: Option to capture logits in streaming mode (for large unquantized models)

2025-05-31 01:11:56 +02:00

compare_q_transformers.py

compare_q.py: Add more GPTQ layer types

2025-05-18 00:19:19 +02:00

compare_q.py

compare_q.py: Add AnyPrecision models

2025-06-05 02:26:00 +02:00

humaneval.py

HumanEval: Move BOS token to individual prompt template, don't prepend by default when tokenizing

2025-05-11 23:02:07 +02:00

longctx.py

Add simple long-context evaluation script

2025-05-17 16:58:12 +02:00

model_diff.py

Add cosine_error and SQNR measures

2025-05-30 19:43:20 +02:00

ppl.py

Reduce VRAM overhead in ppl test

2025-04-17 22:22:47 +02:00

prequant_test.py

Add prequant_test script

2025-05-30 19:42:49 +02:00