"docs/git@developer.sourcefind.cn:zhaoyu6/sglang.git" did not exist on "6b7038babd562de099b583957ff19b78c4689a37"
- 01 Nov, 2023 5 commits
-
-
Wesley L Passos authored
-
MD FAIZAN KHAN authored
Fix the typos and grammar mistakes in CONTRIBUTING.md
-
Wesley L Passos authored
* fix docstring in get_maskformer_resize_output_image_size * fix functions docstring * fix 'copied from' functions docstring * fix docstring * fix return type * fix docstring resize
-
Younes Belkada authored
* working v1 * oops * Update src/transformers/modeling_utils.py Co-authored-by:
Marc Sun <57196510+SunMarc@users.noreply.github.com> * fixup * oops * push * more changes * add docs * some fixes * fix copies * add v1 doc * added installation guide * relax constraints * revert * attempt llm-awq * oops * oops * fixup * raise error when incorrect cuda compute capability * nit * add instructions for llm-awq * fixup * fix copies * fixup and docs * change * few changes + add demo * add v1 tests * add autoawq in dockerfile * finalize * Update tests/quantization/autoawq/test_awq.py * fix test * fix * fix issue * Update src/transformers/integrations/awq.py Co-authored-by:
Arthur <48595927+ArthurZucker@users.noreply.github.com> * Update docs/source/en/main_classes/quantization.md Co-authored-by:
amyeroberts <22614925+amyeroberts@users.noreply.github.com> * Update src/transformers/utils/quantization_config.py Co-authored-by:
-
Hz, Ji authored
* make fsdp test cases device agnostic * make style
-
- 31 Oct, 2023 21 commits
-
-
Yeyang authored
* docs(zh): translate tflite.md * docs(zh): add space around links * Update docs/source/zh/tflite.md Co-authored-by:
Steven Liu <59462357+stevhliu@users.noreply.github.com> --------- Co-authored-by:
-
Lysandre Debut authored
* Safetensors serialization by default * First pass on the tests * Second pass on the tests * Third pass on the tests * Fix TF weight loading from TF-format safetensors * Specific encoder-decoder fixes for weight crossloading * Add VisionEncoderDecoder fixes for TF too * Change filename test for pt-to-tf * One missing fix for TFVisionEncoderDecoder * Fix the other crossload test * Support for flax + updated tests * Apply suggestions from code review Co-authored-by:
Sanchit Gandhi <93869735+sanchit-gandhi@users.noreply.github.com> * Sanchit's comments * Sanchit's comments 2 * Nico's comments * Fix tests * cleanup * Apply suggestions from code review Co-authored-by:
Matt <rocketknight1@gmail.com> Co-authored-by:
-
Dong-geon Lee authored
-
Hz, Ji authored
* device agnostic models testing * add decorator `require_torch_fp16` * make style * apply review suggestion * Oops, the fp16 decorator was misused
-
Steven Liu authored
* first draft * remove non-existent paths * edits * feedback * feedback and optimum * Apply suggestions from code review Co-authored-by:
regisss <15324346+regisss@users.noreply.github.com> Co-authored-by:
Ella Charlaix <80481427+echarlaix@users.noreply.github.com> * redirect to correct doc * _redirects.yml --------- Co-authored-by:
-
jiaqiw09 authored
* translate traning.md * update _tocree.yml * update _tocree.yml * update _tocree.yml
-
Susnato Dhar authored
fix dropout in modeling_gpt_bigcode.py
-
Younes Belkada authored
fix bnb mpt test
-
Matt authored
* Backward compatibility fix for the Conversation class * Explain what's going on in the conditional
-
Younes Belkada authored
* add v1 neftune * use `unwrap_model` instead * add test + docs * Apply suggestions from code review Co-authored-by:
Zach Mueller <muellerzr@gmail.com> * more details * fixup * Update docs/source/en/main_classes/trainer.md Co-authored-by:
-
Hz, Ji authored
* device agnostic pipelines testing * pass torch_device
-
Matt authored
* Shorten the conversation tests for speed + fixing position overflows * Put max_new_tokens back to 5 * Remove test skips * Increase max_position_embeddings in blenderbot tests * Add skips for blenderbot_small * Correct TF test skip * make fixup * Reformat skips to use is_pipeline_test_to_skip * Update tests/models/blenderbot_small/test_modeling_blenderbot_small.py Co-authored-by:
-
Yih-Dar authored
fix Co-authored-by:ydshieh <ydshieh@users.noreply.github.com>
-
Vivek Khandelwal authored
* Add support for loading GPTQ models on CPU Right now, we can only load the GPTQ Quantized model on the CUDA device. The attribute `gptq_supports_cpu` checks if the current auto_gptq version is the one which has the cpu support for the model or not. The larger variants of the model are hard to load/run/trace on the GPU and that's the rationale behind adding this attribute. Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com> * Update quantization.md * Update quantization.md * Update quantization.md
-
Nick Hill authored
A recent PR https://github.com/huggingface/transformers/pull/26579 fixed an edge case out-of-bounds tensor indexing error in TypicalLogitsWarper, and a related behaviour change was made that we thought fixed a long-standing bug w.r.t. the token inclusion cutoff. However after looking more closely, I am pretty certain that the original logic was correct and that the OOB fix should have been made differently. Specifically the docs state that it should include the "smallest set of tokens that add up to P or higher" and so `last_ind` should actually be one more than the index of the last token satisfying (cumulative_probs < self.mass). We still need a max clamp in case that last token is the very last one in the tensor.
-
Susnato Dhar authored
* added flash attention of gpt_bigcode * changed docs * Update src/transformers/models/gpt_bigcode/modeling_gpt_bigcode.py * add FA-2 docs * oops * Update docs/source/en/perf_infer_gpu_one.md Last Nit Co-authored-by:
Younes Belkada <49240599+younesbelkada@users.noreply.github.com> Co-authored-by:
younesbelkada <younesbelkada@gmail.com> Co-authored-by:
-
Yih-Dar authored
Disable runner check Co-authored-by: -
Seungwoo, Jeong authored
Update configuration_blip.py edit docstrings
-
Akshar Goyal authored
* [docstring] Fix docstring for AltCLIPVisionConfig, AltCLIPTextConfig + cleaned some docstring * Removed entries from check_docstring.py * Removed entries from check_docstring.py * Removed entry from check_docstring.py * [docstring] Fix docstring for AltCLIPTextConfig, AltCLIPVisionConfig and AltCLIPConfig
-
Clifford Ressel authored
-
Hz, Ji authored
* get default device through `PartialState().default_device` as is has been officially released * apply code review suggestion * apply code review suggestion Co-authored-by:
-
- 30 Oct, 2023 14 commits
-
-
NielsRogge authored
Update docs
-
NielsRogge authored
* Fix import * Apply suggestions from code review Co-authored-by:
-
MD FAIZAN KHAN authored
-
Younes Belkada authored
* stronger GC tests * better tests and skip failing tests * break down into 3 sub-tests * break down into 3 sub-tests * refactor a bit * more refactor * fix * last nit * credits contrib and suggestions * credits contrib and suggestions --------- Co-authored-by:
Yih-Dar <2521628+ydshieh@users.noreply.github.com> Co-authored-by:
-
Hz, Ji authored
-
Rockerz authored
* add * add * add * Add deepspeed.md * Add * add * Update docs/source/ja/main_classes/callback.md Co-authored-by:
-
Yeyang authored
* docs(zh): translate serialization.md * docs(zh): add space around links
-
Yih-Dar authored
* fix * fix * fix * fix --------- Co-authored-by: -
Hz, Ji authored
-
Younes Belkada authored
* fix bnb test * link to GH issue
-
Yih-Dar authored
* Use mozilla-foundation/common_voice_11_0 * Update expected values * Update expected values * For test_word_time_stamp_integration --------- Co-authored-by: -
Yih-Dar authored
* Add KOSMOS-2 model * update * update * update * address review comment - 001 * address review comment - 002 * address review comment - 003 * style * Apply suggestions from code review Co-authored-by:
NielsRogge <48327001+NielsRogge@users.noreply.github.com> * no more Kosmos2Tokenizer * style * remove "returned when being computed by the model" * Apply suggestions from code review Co-authored-by:
-
Hz, Ji authored
* remove the obsolete code related to fairscale FSDP * apple review suggestion
-
Younes Belkada authored
* add `gradient_checkpointing_kwargs` in trainer and training arguments * add comment * add test - currently failing * now tests pass
-
