GitLab

This PR resolves an issue loading in tokenizer_configs where the eos or
bos token is null as in:
[Qwen/Qwen1.5-72B-Chat](https://huggingface.co/Qwen/Qwen1.5-72B-Chat/blob/main/tokenizer_config.json)

resolves:
https://github.com/huggingface/text-generation-inference/issues/1545 and
related to https://github.com/QwenLM/Qwen1.5/issues/162

Once https://github.com/huggingface/huggingface.js/pull/629 gets merged,
we will rely on TGI's specs to generate jsonschema types for
`text_generation` and `chat_completion`.

This PR adds some documentation for `GenerationParameters`'s properties
so that they get documented in the downstream tools (TGI docs but also
`huggingface.js`/`huggingface_hub` inference clients). I mostly took
inspiration from [the python
client](https://github.com/huggingface/text-generation-inference/blob/main/clients/python/text_generation/types.py)
for the descriptions.

This PR allows the `CompletionRequest.prompt` to be sent as a string or
array of strings. When an array is sent the first value will be used if
it's a string; otherwise the according error will be thrown

Fixes:
https://github.com/huggingface/text-generation-inference/issues/1690
Similar to: https://github.com/vllm-project/vllm/pull/323/files

This PR makes tool calling aware of the name of the function selected. 

Fixes:
https://github.com/huggingface/text-generation-inference/issues/1657

Thank you @puppetm4st3r for the helpful snippets, large parts of this PR
are simply refactors of the code shared 🙏

**opening draft PR because small tweaks are needed before merging

@Narsil @drbh this will update flash attention v2 and vllm.
You will need to re-install them.

# What does this PR do?

- Changed all models to extract `embed_tokens` in order to enable llava
to separately call the embeddings and the core model layers.
- Added VlmCausalLM to inherit from FlashMistral in order to be
maximally supported. The only added logics sits on top and parses images
into pixel values, preallocates input_ids space for the image
embeddings, and passes them for the model.
- Added Clip for the vision tower.
- Didn't add flash for the vision tower since there's no padding anyway.
- Added heuristic (potentially incomplete) to calculate number of
features *before* calculating the clip patches (allows for easier logic
reuse of the LLM under the hood).


Still needs to be done:

- [x] Implement the image parsing in the controller side, to avoid
downloading n times per TP shard and also refusing requests too large
early and avoid issues where the truncation actually truncates the
image.
- [ ] Make sure it works with quantization properly.
- [x] Make sure it works with TP>1



<!--
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

 -->

This PR fixes a bug with `ChatCompletionLogprobs` where if
`top_tokens.len() == 0` empty results were returned.

```bash
 curl http://localhost:3000/v1/chat/completions \
    -X POST \
    -H 'Content-Type: application/json' \
    -d '{
  "model": "tgi",
  "logprobs": true,
  "messages": [
    {
      "role": "user",
      "content": "What is deep learning?"
    }
  ],
  "stream": false,
  "max_tokens": 20
}'
```

response


```json
{"id":"","object":"text_completion","created":1711588522,"model":"google/gemma-2b-it","system_fingerprint":"1.4.4-native","choices":[{"index":0,"message":{"role":"assistant","content":"**Deep learning** is a subset of machine learning (ML) that emphasizes the creation of **artificial"},"logprobs":{"content":[{"token":"**","logprob":-0.22558594,"top_logprobs":[]},{"token":"Deep","logprob":-0.0014877319,"top_logprobs":[]},{"token":" learning","logprob":-0.12695312,"top_logprobs":[]},{"token":"**","logprob":-0.055664062,"top_logprobs":[]},{"token":" is","logprob":-0.00090026855,"top_logprobs":[]},{"token":" a","logprob":-0.006072998,"top_logprobs":[]},{"token":" subset","logprob":-2.25,"top_logprobs":[]},{"token":" of","logprob":-0.00031089783,"top_logprobs":[]},{"token":" machine","logprob":-0.091308594,"top_logprobs":[]},{"token":" learning","logprob":-0.00002348423,"top_logprobs":[]},{"token":" (","logprob":-1.671875,"top_logprobs":[]},{"token":"ML","logprob":-0.00040626526,"top_logprobs":[]},{"token":")","logprob":-0.00016212463,"top_logprobs":[]},{"token":" that","logprob":-0.13769531,"top_logprobs":[]},{"token":" emphasizes","logprob":-4.03125,"top_logprobs":[]},{"token":" the","logprob":-0.2890625,"top_logprobs":[]},{"token":" creation","logprob":-3.109375,"top_logprobs":[]},{"token":" of","logprob":-0.00024032593,"top_logprobs":[]},{"token":" **","logprob":-1.2265625,"top_logprobs":[]},{"token":"artificial","logprob":-0.10546875,"top_logprobs":[]}]},"finish_reason":"length"}],"usage":{"prompt_tokens":15,"completion_tokens":20,"total_tokens":35}}
```

This PR resolves a couple 

- [X] adjusts the tool response to align with openai's tools response
type
- [X] bumps pydantic to `2.6.4` in all apps (resolves dependency issue
when running tests)
- [X] bump `outlines` version and fix import for new name

Fix a small inconsistency compared the OpenAI's chat-completion behavior
(introduced in
https://github.com/huggingface/text-generation-inference/pull/1427 cc
@drbh). When using `stream=True`, each chunk has an `index` value in
`ChatCompletionChoice`. This index is not meant to be the index of the
generated token but the index of the choice, which is always 0 (since
TGI always return a single choice).

See https://platform.openai.com/docs/api-reference/chat/object:
> index _integer_
> The index of the choice in the list of choices.

---

So instead of 

```js
data:{"id":"","object":"text_completion","created":1710508199,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-sha-e6bb3ff8","choices":[{"index":1,"delta":{"role":"assistant","content":"I"},"logprobs":null,"finish_reason":null}]}
data:{"id":"","object":"text_completion","created":1710508199,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-sha-e6bb3ff8","choices":[{"index":2,"delta":{"role":"assistant","content":"'"},"logprobs":null,"finish_reason":null}]}
data:{"id":"","object":"text_completion","created":1710508199,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-sha-e6bb3ff8","choices":[{"index":3,"delta":{"role":"assistant","content":"m"},"logprobs":null,"finish_reason":"length"}]}
```

if should return
```js
data:{"id":"","object":"text_completion","created":1710508199,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-sha-e6bb3ff8","choices":[{"index":0,"delta":{"role":"assistant","content":"I"},"logprobs":null,"finish_reason":null}]}
data:{"id":"","object":"text_completion","created":1710508199,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-sha-e6bb3ff8","choices":[{"index":0,"delta":{"role":"assistant","content":"'"},"logprobs":null,"finish_reason":null}]}
data:{"id":"","object":"text_completion","created":1710508199,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-sha-e6bb3ff8","choices":[{"index":0,"delta":{"role":"assistant","content":"m"},"logprobs":null,"finish_reason":"length"}]}
```

**EDIT:** I also edited ToolCall.index to be always `0` (instead of the
generated token index) but for this one I'm actually unsure. It might be
the index of the tool in the array of tools? OpenAI's documentation
doesn't provide any information about it:
> index _integer_

---

I also noticed that in OpenAI's example, the last chunk doesn't have a
delta and is the only one that has a `finish_reason` returning. TGI is
slightly different since the last chunk has both the last delta (i.e.
the last generated token) + the finish reason. I don't think this is
worth fixing since it is not a requirement according to the docs/specs
(at least not that I know of).

This PR adds the missing `stop` parameter to the `ChatRequest` struct
which allows calls to specify a list of stop sequences

This WIP PR (will) add support for legacy OpenAI `v1/completions` API.

This should allow TGI to be a drop in replacement for OpenAI when using
tools that rely on the completions api

Should fix:
https://github.com/huggingface/text-generation-inference/issues/1468

This work in progress PR begins to add support for tools. Tools relies
on grammar support and still has some unsolved challenges. Opening the
PR for visibility and feedback

This PR avoids setting a default message in order to avoid unexpected
generations

small PR to add a new interface endpoint behind a feature

# What does this PR do?

Literally just adds the name field to the Message class.

I verified this change by building a new docker container (using the
`Dockerfile` in the repo) and trialing with a `chat_template` that uses
the `name` field.

Here's the previous behavior:

Input messages:
```
{
"messages": [
 {"role": "system", "content": "You are a succinct but helpful AI Assistant listening to a chat server.  Address everyone by @<username>"},
 {"role": "user", "name": "Aaron", "content": "Hello There!"},
 {"role": "assistant", "content": "  Hello @aaron! How can I assist you today?"},
 {"role": "user", "name": "Sally", "content": "Hiya everyone.  Is @aaron is this room?"}
],
  "model": "meta-llama/Llama-2-7b-chat-hf"
}
```

Response before the modification:
```
Hello @aaron! Yes, you are in the chat room. How can I assist you today? 😊

Hiya everyone! *waves* It's great to see you all here. Is there something on your mind that you'd like to talk about or ask? I'm here to listen and help in any way I can. 🤖
```

Response after my modification:
```
Hello @Sally! Yes, @aaron is currently in the chat room. How may I assist you today?
```

Fixes #1558 


## 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?
- [ ] 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?
@Narsil

---------
Co-authored-by: Aaron Mihalik <aaron.mihalik@parsons.us>
Co-authored-by: drbh <david.richard.holtz@gmail.com>

This WIP PR starts to add grammar support via outlines, currently this
PR supports very simple regex grammars and does not optimize for
precompiling or caching grammar fsm's.

todo:
- [X] add simple outlines guidance to `NextTokenChooser`
- [X] update protos for grammar
- [X] update generation params API
- [X] constrain simple grammar
- [ ] support parsing more complex grammar into fsm
- [ ] support all outline support grammar types
- [ ] explore optimizations to avoid recompiling grammars

guided request
```bash
curl -s 'http://localhost:3000/generate' \
--header 'Content-Type: application/json' \
--data-raw '{
    "inputs": "make an email for david: \n",
    "parameters": {
        "max_new_tokens": 6,
        "grammar": "[\\w-]+@([\\w-]+\\.)+[\\w-]+"
    }
}' | jq
```
response
```json
{
  "generated_text": "david@example.com"
}
```

unguided request
```bash
curl -s 'http://localhost:3000/generate' \
--header 'Content-Type: application/json' \
--data '{
    "inputs": "make an email for david: \n",
    "parameters": {
        "max_new_tokens": 6
    }
}' | jq
```
response
```json
{
  "generated_text": "    email = 'david"
}
```

This PR adds a simple custom `deserialize_with` function that parses a
string or an object with a content property. This should help support
more token configuration files stored on the hub

Some hardware require a maximum batch size.

This PR adds support to read the `add_generation_prompt` from the config
and use it in the chat template. If `add_generation_prompt` does not
exist we default to false

This PR fixes the issue with loading a local tokenizer config.
Previously the default functionality would look in the current working
directory. Now if a local model path is specified we will check that
directory for the tokenizer_config.

## Examples of valid commands

uses tokenizer_config from hub
```
text-generation-launcher --model-id HuggingFaceH4/zephyr-7b-beta
```

use tokenizer_config from local model path
```
text-generation-launcher \
  --model-id ~/.cache/huggingface/hub/models--HuggingFaceH4--zephyr-7b-beta/snapshots/dc24cabd13eacd3ae3a5fe574bd645483a335a4a/
```

use specific tokenizer_config file
```
 text-generation-launcher \
  --model-id ~/.cache/huggingface/hub/models--HuggingFaceH4--zephyr-7b-beta/snapshots/dc24cabd13eacd3ae3a5fe574bd645483a335a4a/ \
  --tokenizer-config-path ~/.cache/huggingface/hub/models--HuggingFaceH4--zephyr-7b-beta/snapshots/dc24cabd13eacd3ae3a5fe574bd645483a335a4a/tokenizer_config.json


```

---------
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>

# 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

 -->

# What does this PR do?


Ideally this is done client side, but this is a recurring request,
therefore we implemented it.

- Runs only if rust tokenizer is present (not encumbering the main
inference pipeline is important).
- Returns simple results, ID, text (gotten with offsets from the
original string) and offsets (so users can do things like highlighting
text).

<!--
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

 -->

Disable `decoder_input_details` on OpenAI-compatible chat streaming, pass temp and top-k from API (#1470)

This PR makes some minor tweaks to the new OpenAI-compatible chat
endpoint #1427 in `GenerateParameters`:
- Disables `decoder_input_details` when streaming is enabled. This was
causing all streaming chat requests to fail before, since
[`decoder_input_details`==true is not enabled when streaming
tokens](https://github.com/huggingface/text-generation-inference/blob/98e5faff9daec6170cc2b0f963f2d73cf846b341/router/src/validation.rs#L406).
- Passes through `temperature` and `top_p` hyperparameters from the API
request to `GenerateParameters`

## Testing

```bash
curl localhost:8080/v1/chat/completions \
    -X POST \
    -d '{
  "model": "",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "What is deep learning?"
    }
  ],
  "stream": true, 
  "max_tokens": 20
}' \                                   
    -H 'Content-Type: application/json'
```

Should work correctly. Currently, most recent release from `main`
returns error:
```
data:{"error":"Input validation error: `decoder_input_details` == true is not supported when streaming tokens","error_type":"validation"}
```

It's my first time contributing to this project, so I could be missing
something. Would especially appreciate @drbh's eyes on this one

This PR adds support to handle the custom jinja function
`raise_exception` and passes the `bos` and `eos` tokens into the
template

Additionally this PR adds 3 tests to validate and show examples of what
can and cannot be parsed currently.

```bash
cargo test --package text-generation-router --lib -- infer::tests --nocapture
#     Finished test [unoptimized + debuginfo] target(s) in 7.82s
#      Running unittests src/lib.rs (target/debug/deps/text_generation_router-18a0bbf99c2ca1b4)

# running 3 tests
# test infer::tests::test_chat_template_valid_with_raise ... ok
# test infer::tests::test_chat_template ... ok
# test infer::tests::test_chat_template_invalid_with_raise ... ok

# test result: ok. 3 passed; 0 failed; 0 ignored; 0 measured; 15 filtered out; finished in 0.00s
```

This PR adds support to make TGI a drop in replacement for OpenAI
clients by exposing the same HTTP interface.

Notes
- TGI inits a single model at startup so the `model` field is unused in
HTTP requests.
- `max_tokens` and `stream` should work as expected but other params may
be (unimplemented or not supported)

General approach
- fetch the `tokenizer_config` at startup from the hub
- pass `tokenizer_config` into `Infer` so we have it at request time
- use the `chat_template` on the config to format chat request
- parse jinja template and render chat string
- pass inputs into existing generate function
- wrap generation output in expected structure before returning

# How to test

### Streaming curl
```bash
curl localhost:3000/v1/chat/completions \
    -X POST \
    -d '{
  "model": "tgi",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "What is deep learning?"
    }
  ],
  "stream": true,
  "max_tokens": 20
}' \
    -H 'Content-Type: application/json'
```


It is also possible to use the `openai` python library and change the
base url

###  🌊 STREAMING REQUEST
```python
from openai import OpenAI

# init the client but point it to TGI
client = OpenAI(
    base_url="http://localhost:3000/v1",
    api_key="not needed for a local LLM"
)

chat_completion = client.chat.completions.create(
    model="tgi",
    messages=[
        {"role": "system", "content": "You are a helpful assistant." },
        {"role": "user", "content": "What is deep learning?"}
    ],
    stream=True
)

# iterate and print stream
for message in chat_completion:
    print(message)

# ChatCompletionChunk(id='', choices=[Choice(delta=ChoiceDelta(content=' that', function_call=None, role='assistant', tool_calls=None), finish_reason=None, index=2, logprobs=None)], created=1704486761, model='', object='text_completion', system_fingerprint='')
```

### 🚗 SYNCHRONOUS REQUEST
```python
from openai import OpenAI

# init the client but point it to TGI
client = OpenAI(
    base_url="http://localhost:3000/v1",
    api_key="not needed for a local LLM"
)

chat_completion = client.chat.completions.create(
    model="tgi",
    messages=[
        {"role": "system", "content": "You are a helpful assistant." },
        {"role": "user", "content": "What is deep learning?"}
    ],
    stream=False
)

print(chat_completion)
# ChatCompletion(id='', choices=[Choice(finish_reason=None, index=0, logprobs=None, message=ChatCompletionMessage(content='\nDeep learning is a new field of research that has been gaining traction in the last ...', role='assistant', function_call=None, tool_calls=None))], created=1704486762, model='', object='text_completion', system_fingerprint='', usage=CompletionUsage(completion_tokens=100, prompt_tokens=76, total_tokens=176))
```


## How to run dev

```bash
cd text-generation-inference/server
MASTER_ADDR=127.0.0.1 MASTER_PORT=5555 text-generation-server serve --trust-remote-code gpt2
```

***note many of the existing `chat_templates` use non standard `jinja`
(ie. adding a `raise` to the template) which will throw an error when
parsing; hence using `upstage/SOLAR-10.7B-Instruct-v1.0` since it has a
valid template
```bash
cd text-generation-inference/router
cargo run -- --tokenizer-name upstage/SOLAR-10.7B-Instruct-v1.0
```

trigger
```bash
curl localhost:3000/v1/chat/completions \
    -X POST \
    -d '{ "model": "gpt-3.5-turbo", "messages": [ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "What is the IP address of the Google DNS servers?" } ], "stream": true, "max_tokens": 20, "logprobs": true }' \
    -H 'Content-Type: application/json'
```

^ supports `stream: true` and `stream: false` requests

# What does this PR do?

See #1165

<!--
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: Florian Zimmermeister <flozi00.fz@gmail.com>
Co-authored-by: Ubuntu <ubuntu@ip-172-31-24-153.ec2.internal>

# What does this PR do?

Now clients which do not specify a max_length will be implying
`max_new_tokens = max_total_tokens - input_length`.
This is a serious change, but which seems more in line with what users
expect from standing server.

<!--
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: OlivierDehaene <olivier@huggingface.co>

# 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: Vincent Brouwers <vincent.brouwers@ing.com>

Close #288

Co-authored-by: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com>
Co-authored-by: OlivierDehaene <olivier@huggingface.co>