1. 03 Oct, 2023 2 commits
  2. 02 Oct, 2023 1 commit
  3. 29 Sep, 2023 1 commit
    • Nicolas Patry's avatar
      Fixing eetq dockerfile. (#1081) · 5ba53d44
      Nicolas Patry authored
      # What does this PR do?
      
      Fixes #1079 
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      5ba53d44
  4. 28 Sep, 2023 4 commits
  5. 27 Sep, 2023 7 commits
    • Merve Noyan's avatar
      Automatic docs for TGI (#1045) · 259a2300
      Merve Noyan authored
      
      
      I had to open this PR since I initially worked from my fork, and it
      requires a handful of work to trigger a new github action on my fork's
      specific branch (couldn't find a way, at least, despite trying all of
      them).
      
      ---------
      Co-authored-by: default avatarNicolas Patry <patry.nicolas@protonmail.com>
      259a2300
    • zhangsibo1129's avatar
      Complete FastLinear.load parameters in OPTDecoder initialization (#1060) · 1e3ec3c9
      zhangsibo1129 authored
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      `FastLinear.load` requires 4 parameters, but in the following only 3 are
      given. This PR fix this.
      
      ```python
      # server/text_generation_server/models/custom_modeling/opt_modeling.py
              if config.word_embed_proj_dim != config.hidden_size:
                  self.project_out = FastLinear.load(
                      config, prefix="model.decoder.project_out", bias=False
                  )
              else:
                  self.project_out = None
      
              if config.word_embed_proj_dim != config.hidden_size:
                  self.project_in = FastLinear.load(
                      config, prefix="model.decoder.project_in", bias=False
      ```
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      1e3ec3c9
    • OlivierDehaene's avatar
      feat: format code (#1070) · 47954b81
      OlivierDehaene authored
      47954b81
    • Nicolas Patry's avatar
      Remove the stripping of the prefix space (and any other mangling that tokenizers might do). (#1065) · b32e9ce9
      Nicolas Patry authored
      Superseed #1024
      
      
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation
      
      ).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      
      ---------
      Co-authored-by: default avatarbangoz <ch_xie@pku.edu.cn>
      b32e9ce9
    • Nicolas Patry's avatar
      Support eetq weight only quantization (#1068) · 95a4bb69
      Nicolas Patry authored
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation
      
      ).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      
      ---------
      Co-authored-by: default avatarzhaosida <zhaosida@corp.netease.com>
      95a4bb69
    • Merve Noyan's avatar
      Added note on weight-cache-override (#994) · 36c28688
      Merve Noyan authored
      
      
      Added note on serving supported models from a different folder without
      re-downloading them.
      
      ---------
      Co-authored-by: default avatarNicolas Patry <patry.nicolas@protonmail.com>
      36c28688
    • Nicolas Patry's avatar
      Preping 1.1.0 (#1066) · a0498642
      Nicolas Patry authored
      # What does this PR do?
      
      Upgrade all relevant versions and dependencies.
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      a0498642
  6. 26 Sep, 2023 6 commits
    • Vincent Brouwers's avatar
      Fix top_n_tokens returning non-log probs for some models (#1023) · 8672cad2
      Vincent Brouwers authored
      # What does this PR do?
      
      I made an embarrassing mistake where I accidentally passed normal
      softmax probabilities into `batch_top_tokens` for `CausalLM` and
      `Seq2SeqLM`.
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      @Narsil
      8672cad2
    • Victor SANH's avatar
    • oOraph's avatar
      Install curl to be able to perform more advanced healthchecks (#1033) · ae623b8d
      oOraph authored
      
      
      # What does this PR do?
      
      Install curl within base image, negligible regarding the image volume
      and will allow to easily perform a better health check. Not sure about
      the failing github actions though. Should I fix something ?
      Signed-off-by: default avatarRaphael <oOraph@users.noreply.github.com>
      Co-authored-by: default avatarRaphael <oOraph@users.noreply.github.com>
      ae623b8d
    • zhangsibo1129's avatar
      fix discard_names bug in safetensors convertion (#1052) · eba6ab1c
      zhangsibo1129 authored
      
      
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Model Class attributes `_tied_weights_keys`, `
      _keys_to_ignore_on_load_missing` can only be `None` or a List.
      `getattr(class_, "_keys_to_ignore_on_load_missing", [])` will return
      `None` if `_keys_to_ignore_on_load_missing` is None, and
      `discard_names.extend(None)` will trigger an exception, even though
      `_tied_weights_keys` exists.
      
      ## Who can review?
      
      @OlivierDehaene  @Narsil
      
      ---------
      Co-authored-by: default avatarNicolas Patry <patry.nicolas@protonmail.com>
      eba6ab1c
    • zhangsibo1129's avatar
      support local model config file (#1058) · edc95a0e
      zhangsibo1129 authored
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Support local config file to avoid unexpected `discard_names`, which
      causes #1057.
      
      In the case of launching local mode without `model.safetensors` file,
      the original code will result `discard_names = []` when
      `hf_hub_download` throws an connection error.
      ```python
      # server/text_generation_server/cli.py
          try:
              import transformers
              import json
          
          
              config_filename = hf_hub_download(model_id, revision=revision, filename="config.json")
              with open(config_filename, "r") as f:
                  config = json.load(f)
              architecture = config["architectures"][0]
          
              class_ = getattr(transformers, architecture)
          
              # Name for this varible depends on transformers version.
              discard_names = getattr(class_, "_tied_weights_keys", [])
              discard_names.extend(getattr(class_, "_keys_to_ignore_on_load_missing", []))
          
          except Exception as e:
              discard_names = []
      ```
      
      The expected `_tied_weights_keys` of OPT-1.3b is `["lm_head.weight"]`,
      and its tied weight `"model.decoder.embed_tokens.weight"` will be kept
      in the safetensors conversion. But the above empty `discard_names` will
      lead to `"lm_head.weight"` being kept and
      `"model.decoder.embed_tokens.weight"` being discard in the subsequent
      method `_remove_duplicate_names`, which causes error #1057.
      
      So add a local mode branch to get the expected `discard_names` like
      follows. This modification also applies to other models
      
      ```python
      # server/text_generation_server/cli.py
              if is_local_model:
                  config_filename = os.path.join(model_id, "config.json")
              else:
                  config_filename = hf_hub_download(model_id, revision=revision, filename="config.json")
      ```
      
      
      In addition, when `_tied_weights_keys` or
      `_keys_to_ignore_on_load_missing` is `None`, the above code will also
      throw an error unexpectedly. This is fixed in PR #1052
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [x] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [x] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      N/A
      - [ ] Did you write any new necessary tests?  N/A
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      @Narsil
      edc95a0e
    • Nicolas Patry's avatar
      Fix GQA llama + AWQ (#1061) · 2f51645a
      Nicolas Patry authored
      # What does this PR do?
      
      Fixes #1056
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      2f51645a
  7. 25 Sep, 2023 2 commits
    • Nicolas Patry's avatar
      Add AWQ quantization inference support (#1019) (#1054) · c5de7cd8
      Nicolas Patry authored
      # Add AWQ quantization inference support
      
      Fixes
      https://github.com/huggingface/text-generation-inference/issues/781
      
      This PR (partially) adds support for AWQ quantization for inference.
      More information on AWQ [here](https://arxiv.org/abs/2306.00978). In
      general, AWQ is faster and more accurate than GPTQ, which is currently
      supported by TGI.
      
      This PR installs 4-bit GEMM custom CUDA kernels released by AWQ authors
      (in `requirements.txt`, just one line change).
      
      Quick way to test this PR would be bring up TGI as follows:
      
      ```
      text-generation-server download-weights abhinavkulkarni/codellama-CodeLlama-7b-Python-hf-w4-g128-awq
      
      text-generation-launcher \
      --huggingface-hub-cache ~/.cache/huggingface/hub/ \
      --model-id abhinavkulkarni/codellama-CodeLlama-7b-Python-hf-w4-g128-awq \
      --trust-remote-code --port 8080 \
      --max-input-length 2048 --max-total-tokens 4096 --max-batch-prefill-tokens 4096 \
      --quantize awq
      ```
      
      Please note:
      * This PR was tested with FlashAttention v2 and vLLM.
      * This PR adds support for AWQ inference, not quantizing the models.
      That needs to be done outside of TGI, instructions
      
      [here](https://github.com/mit-han-lab/llm-awq/tree/f084f40bd996f3cf3a0633c1ad7d9d476c318aaa).
      * This PR only adds support for `FlashLlama` models for now.
      * Multi-GPU setup has not been tested. 
      * No integration tests have been added so far, will add later if
      maintainers are interested in this change.
      * This PR can be tested on any of the models released
      
      [here](https://huggingface.co/abhinavkulkarni?sort_models=downloads#models).
      
      Please refer to the linked issue for benchmarks for
      
      [abhinavkulkarni/meta-llama-Llama-2-7b-chat-hf-w4-g128-awq](https://huggingface.co/abhinavkulkarni/meta-llama-Llama-2-7b-chat-hf-w4-g128-awq)
      vs
      
      [TheBloke/Llama-2-7b-Chat-GPTQ](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GPTQ).
      
      Please note, AWQ has released faster (and in case of Llama, fused)
      kernels for 4-bit GEMM, currently at the top of the `main` branch at
      https://github.com/mit-han-lab/llm-awq, but this PR uses an older commit
      that has been tested to work. We can switch to latest commit later on.
      
      ## Who can review?
      
      @OlivierDehaene OR @Narsil
      
      ---------
      
      
      
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation
      
      ).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      
      ---------
      Co-authored-by: default avatarAbhinav M Kulkarni <abhinavkulkarni@gmail.com>
      Co-authored-by: default avatarAbhinav Kulkarni <abhinav@concentric.ai>
      c5de7cd8
    • Nicolas Patry's avatar
      Fixing t5 loading. (#1042) · fef36cea
      Nicolas Patry authored
      # What does this PR do?
      
      Fixes #1038
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      fef36cea
  8. 21 Sep, 2023 1 commit
    • Vincent Brouwers's avatar
      Fix missing arguments in Galactica's from_pb (#1022) · 123749a3
      Vincent Brouwers authored
      # What does this PR do?
      
      Fixes #1004
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      123749a3
  9. 19 Sep, 2023 1 commit
    • Wang, Yi's avatar
      enable bfloat16 for cpu (#1034) · eeaa22ab
      Wang, Yi authored
      if there's no cuda. disable custom kernels
      
      # What does this PR do?
      
      <!--
      Congratulations! You've made it this far! You're not quite done yet
      though.
      
      Once merged, your PR is going to appear in the release notes with the
      title you set, so make sure it's a great title that fully reflects the
      extent of your awesome contribution.
      
      Then, please replace this with a description of the change and which
      issue is fixed (if applicable). Please also include relevant motivation
      and context. List any dependencies (if any) that are required for this
      change.
      
      Once you're done, someone will review your PR shortly (see the section
      "Who can review?" below to tag some potential reviewers). They may
      suggest changes to make the code even better. If no one reviewed your PR
      after a week has passed, don't hesitate to post a new comment
      @-mentioning the same persons---sometimes notifications get lost.
      -->
      
      <!-- Remove if not applicable -->
      
      Fixes # (issue)
      
      
      ## Before submitting
      - [ ] This PR fixes a typo or improves the docs (you can dismiss the
      other checks if that's the case).
      - [ ] Did you read the [contributor
      guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
            Pull Request section?
      - [ ] Was this discussed/approved via a Github issue or the
      [forum](https://discuss.huggingface.co/)? Please add a link
            to it if that's the case.
      - [ ] Did you make sure to update the documentation with your changes?
      Here are the
      [documentation
      guidelines](https://github.com/huggingface/transformers/tree/main/docs),
      and
      [here are tips on formatting
      docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation
      
      ).
      - [ ] Did you write any new necessary tests?
      
      
      ## Who can review?
      
      Anyone in the community is free to review the PR once the tests have
      passed. Feel free to tag
      members/contributors who may be interested in your PR.
      
      <!-- Your PR will be replied to more quickly if you can figure out the
      right person to tag with @
      
      
      @OlivierDehaene OR @Narsil
      
       -->
      Signed-off-by: default avatarWang, Yi A <yi.a.wang@intel.com>
      eeaa22ab
  10. 12 Sep, 2023 3 commits
  11. 08 Sep, 2023 2 commits
    • xiaobin's avatar
      fit for baichuan models (#981) · 4cce8430
      xiaobin authored
      
      
      As more and more people begin to use Baichuan's open-source models, the
      influence of Baichuan models is growing, especially in China. Many
      community members are interested in adding support for Baichuan models
      to TGI. Meanwhile, Baichuan is a very open company, and in the future,
      it plans to open-source more and more models, taking all this into
      consideration, we would like to add support for the Baichuan model to
      TGI. To do this, we need to make some changes, which we hope can be
      merged into the main branch of TGI. In the future, we would be happy to
      help maintain support for Baichuan models in TGI. We sincerely hope that
      our pull request can be accepted. Thank you.
      
      By the way, the changes of this time mainly for supporting Baichuan-7B.
      
      ---------
      Co-authored-by: default avatarxiaoyuze <xiaoyuze@baichuan.com>
      Co-authored-by: default avatarNicolas Patry <patry.nicolas@protonmail.com>
      4cce8430
    • Merve Noyan's avatar
      Paged Attention Conceptual Guide (#901) · 30a93a0d
      Merve Noyan authored
      30a93a0d
  12. 07 Sep, 2023 4 commits
  13. 06 Sep, 2023 6 commits