NielsRogge da36c557f7 Add ImageGPT (#14240) ...

* First draft

* More improvements

* Improve conversion script

* Fix init weights for layer norm

* Fix correct model for conversion script

* Don't tie input and output embeddings

* Add print statements for debugging

* Add print statements for debugging

* Fix vocab size of model

* Improve documentation, remove fast tokenizer

* Add ImageGPTForImageClassification, improve docs

* Fix docs issue

* Set verbosity level back to info

* Improve tests

* Fix tests and add figure

* Delete tokenizer file

* Remove ImageGPTTokenizer from init files

* Remove ImageGPTLayer from init files

* Remove ImageGPT tokenizer from docs

* First draft of ImageGPTFeatureExtractor

* Fix typo

* Fix bug

* More improvements

* Apply suggestions from code review, add tests for feature extractor

* Fix layernorm

* Update save_pretrained method

* Fix issue

* Make all tests of ImageGPTFeatureExtractor pass

* Update code examples

* Rename model inputs to pixel_values

* Improve code examples

* Update init_weights to post_init

* Fix post_init

2021-11-18 16:24:34 +01:00

..

course_banner.png

Adjust banner width

2021-06-15 09:37:15 -04:00

ImageGPT.png

Add ImageGPT (#14240)

2021-11-18 16:24:34 +01:00

local_attention_mask.png

Add model summary (#4789)

2020-06-05 12:22:50 -04:00

parallelism-deepspeed-3d.png

[doc] DP/PP/TP/etc parallelism (#12524)

2021-07-09 17:39:09 -07:00

parallelism-flexflow.jpeg

[doc] DP/PP/TP/etc parallelism (#12524)

2021-07-09 17:39:09 -07:00

parallelism-gpipe-bubble.png

[doc] DP/PP/TP/etc parallelism (#12524)

2021-07-09 17:39:09 -07:00

parallelism-sagemaker-interleaved-pipeline.png

[doc] DP/PP/TP/etc parallelism (#12524)

2021-07-09 17:39:09 -07:00

parallelism-tp-independent-gelu.png

[doc] DP/PP/TP/etc parallelism (#12524)

2021-07-09 17:39:09 -07:00

parallelism-tp-parallel_gemm.png

Update TP parallel GEMM image (#14112)

2021-10-22 12:57:48 -07:00

parallelism-tp-parallel_self_attention.png

[doc] DP/PP/TP/etc parallelism (#12524)

2021-07-09 17:39:09 -07:00

parallelism-tp-parallel_shard_processing.png

[doc] DP/PP/TP/etc parallelism (#12524)

2021-07-09 17:39:09 -07:00

parallelism-zero-dp-pp.png

[doc] DP/PP/TP/etc parallelism (#12524)

2021-07-09 17:39:09 -07:00

parallelism-zero.png

[doc] DP/PP/TP/etc parallelism (#12524)

2021-07-09 17:39:09 -07:00

ppl_chunked.gif

Guide to fixed-length model perplexity evaluation (#5449)

2020-07-07 16:04:15 -06:00

ppl_full.gif

Guide to fixed-length model perplexity evaluation (#5449)

2020-07-07 16:04:15 -06:00

ppl_sliding.gif

Guide to fixed-length model perplexity evaluation (#5449)

2020-07-07 16:04:15 -06:00

transformers_logo_name.png

GPU text generation: mMoved the encoded_prompt to correct device

2020-01-06 15:11:12 +01:00

transformers_overview.png

[Templates] Add template "call-for-model" markdown and "call-for-big-bird" markdown (#9921)

2021-02-05 15:47:54 +03:00

warmup_constant_schedule.png

GPU text generation: mMoved the encoded_prompt to correct device

2020-01-06 15:11:12 +01:00

warmup_cosine_hard_restarts_schedule.png

GPU text generation: mMoved the encoded_prompt to correct device

2020-01-06 15:11:12 +01:00

warmup_cosine_schedule.png

GPU text generation: mMoved the encoded_prompt to correct device

2020-01-06 15:11:12 +01:00

warmup_cosine_warm_restarts_schedule.png

GPU text generation: mMoved the encoded_prompt to correct device

2020-01-06 15:11:12 +01:00

warmup_linear_schedule.png

GPU text generation: mMoved the encoded_prompt to correct device

2020-01-06 15:11:12 +01:00