4 Commits

Author	SHA1	Message	Date
Yih-Dar	cf561d7cf1	Add torch >=1.12 requirement for Tapas (#24251) ... * fix * fix * fix * Update src/transformers/models/tapas/modeling_tapas.py Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com> * fix --------- Co-authored-by: ydshieh <ydshieh@users.noreply.github.com> Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>	2023-06-13 19:19:40 +02:00
Joao Gante	918a06e25d	Generate: add test to check KV format (#23403) ... Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>	2023-05-16 19:28:19 +01:00
Yih-Dar	975159bb61	Update tiny models and a few fixes (#22928) ... * run_check_tiny_models * update summary * update mixin * update pipeline_model_mapping * update pipeline_model_mapping * Update for gpt_bigcode --------- Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>	2023-04-24 14:45:22 +02:00
Joel Lamy-Poirier	e0921c6b53	Add GPTBigCode model (Optimized GPT2 with MQA from Santacoder & BigCode) (#22575) ... * Add model with cli tool * Remove unwanted stuff * Add new code * Remove inference runner * Style * Fix checks * Test updates * make fixup * fix docs * fix doc * fix test * hopefully fix pipeline tests * refactor * fix CIs * add comment * rename to `GPTBigCodeForCausalLM` * correct readme * make fixup + docs * make fixup * fixes * fixes * Remove pruning * Remove import * Doc updates * More pruning removal * Combine copies * Single MQA implementation, remove kv cache pre-allocation and padding * Update doc * Revert refactor to match gpt2 style * Merge back key and value caches, fix some type hints * Update doc * Fix position ids pith padding (PR 21080) * Add conversion script temporarily * Update conversion script * Remove checkpoint conversion * New model * Fix MQA test * Fix copies * try fix tests * FIX TEST!! * remove `DoubleHeadsModel` * add MQA tests * add slow tests * clean up * add CPU checker * final fixes * fixes - fix GPU issue - fixed slow tests - skip disk offload * fix final issue * Simplify and comment baddbmm fix * Remove unnecessary code * Transpose tweaks * Use beta=1 on cpu, improve tests --------- Co-authored-by: younesbelkada <younesbelkada@gmail.com>	2023-04-10 10:57:21 +02:00