Nicolas Patry 51506aa57a Mllama flash version (#2585) ... * Working loading state. * Preprocessing. * Working state ? (Broke idefics1 temporarily). * Cleaner condition. * Fix idefics. * Updating config, removing TODO * Mllama * Ugrade transformers 4.45 * Flashing mllama. * Starting to get there. * Working state. * Integrations tests for mllama (cutting to 10 tokens because there seems' to be instability after (meaning size of the batch matters. * Updating model link. * Earlier assert. * Fix vlm ? * remove log. * Force ignore all images but last. * Default dtype bfloat16. * Update integration test after switch to bf16. * Remove dead code. * Removed dead code. * Upgrade the flake to latest transformers/tokenizers * Move to hf tgi-nix * Upgrade to 0.5.0		2024-10-27 04:03:57 +00:00
..
basic_tutorials	fix: improve regex expression (#2468)	2024-09-25 06:11:21 +00:00
conceptual	remove LORA_ADAPTERS_PATH (#2563)	2024-10-25 09:01:04 +00:00
reference	doc: clarify that --quantize is not needed for pre-quantized models (#2536)	2024-09-25 06:19:20 +00:00
_toctree.yml	Add links to Adyen blogpost (#2500)	2024-09-25 06:14:07 +00:00
architecture.md	Update architecture.md (#2577)	2024-10-25 09:01:04 +00:00
index.md	fix typos in docs and add small clarifications (#1790)	2024-06-10 09:24:52 +03:00
installation_amd.md	Update ROCM libs and improvements (#2579)	2024-10-25 09:01:04 +00:00
installation_gaudi.md	MI300 compatibility (#1764)	2024-07-17 05:36:58 +00:00
installation_inferentia.md	MI300 compatibility (#1764)	2024-07-17 05:36:58 +00:00
installation_intel.md	Preparing for release. (#2540)	2024-09-25 06:20:50 +00:00
installation_nvidia.md	Preparing for release. (#2540)	2024-09-25 06:20:50 +00:00
installation.md	MI300 compatibility (#1764)	2024-07-17 05:36:58 +00:00
quicktour.md	Adding note for private models in quick-tour document (#2548)	2024-10-25 09:01:04 +00:00
supported_models.md	Mllama flash version (#2585)	2024-10-27 04:03:57 +00:00
usage_statistics.md	refactor usage stats (#2339)	2024-09-25 05:55:39 +00:00