<Please write a descriptive title>

[amrothemich]

Describe the issue as clearly as possible:

Using pydantic's conint doesn't seem to properly limit the values of an integer field.

Steps/code to reproduce the bug:

Here is an example:

from pydantic import BaseModel, conint

import outlines

class Character(BaseModel):
    age: conint(gt=0, lt=13)



model = outlines.models.transformers("EleutherAI/pythia-70m")

# Construct structured sequence generator
generator = outlines.generate.json(model, Character)

import torch
rng = torch.Generator()
rng.manual_seed(2)

character = generator("Give me a character description", rng=rng)
print(repr(character))

This example with a different seed shows that the model is capable of generating a valid response:

from pydantic import BaseModel, conint

import outlines

class Character(BaseModel):
    age: conint(gt=0, lt=13)



model = outlines.models.transformers("EleutherAI/pythia-70m")

# Construct structured sequence generator
generator = outlines.generate.json(model, Character)

import torch
rng = torch.Generator()
rng.manual_seed(0)

character = generator("Give me a character description", rng=rng)
print(repr(character))

### Expected result:

```shell
I would expect any result returned to satisfy the age requirements. However, sometimes it doesn't, and then fails pydantic validation

Error message:

---------------------------------------------------------------------------
ValidationError                           Traceback (most recent call last)
Cell In[22], line 19
     16 rng = torch.Generator()
     17 rng.manual_seed(2)
---> 19 character = generator("Give me a character description", rng=rng)
     20 print(repr(character))

File c:\Users\acasey\.conda\envs\callm\lib\site-packages\outlines\generate\api.py:230, in SequenceGenerator.__call__(self, prompts, max_tokens, stop_at, rng)
    225 generated = self.tokenizer.decode(generated_token_ids)
    226 stripped = [
    227     self.strip_stop_sequences(sequence, stop_sequences)
    228     for sequence in generated
    229 ]
--> 230 formatted = [self.format_sequence(sequence) for sequence in stripped]
    232 # We reshape the output to (batch_size, sample_size)
    233 output: List[List[FormattedOutput]] = list()

File c:\Users\acasey\.conda\envs\callm\lib\site-packages\outlines\generate\api.py:230, in (.0)
    225 generated = self.tokenizer.decode(generated_token_ids)
    226 stripped = [
    227     self.strip_stop_sequences(sequence, stop_sequences)
    228     for sequence in generated
    229 ]
--> 230 formatted = [self.format_sequence(sequence) for sequence in stripped]
    232 # We reshape the output to (batch_size, sample_size)
    233 output: List[List[FormattedOutput]] = list()

File c:\Users\acasey\.conda\envs\callm\lib\site-packages\outlines\generate\json.py:50, in json..(x)
     48     regex_str = build_regex_from_schema(schema, whitespace_pattern)
     49     generator = regex(model, regex_str, sampler)
---> 50     generator.format_sequence = lambda x: schema_object.parse_raw(x)
     51 elif callable(schema_object):
     52     schema = pyjson.dumps(get_schema_from_signature(schema_object))

File c:\Users\acasey\.conda\envs\callm\lib\site-packages\typing_extensions.py:2499, in deprecated.__call__..wrapper(*args, **kwargs)
   2496 @functools.wraps(arg)
   2497 def wrapper(*args, **kwargs):
   2498     warnings.warn(msg, category=category, stacklevel=stacklevel + 1)
-> 2499     return arg(*args, **kwargs)

File c:\Users\acasey\.conda\envs\callm\lib\site-packages\pydantic\main.py:1080, in BaseModel.parse_raw(cls, b, content_type, encoding, proto, allow_pickle)
   1073     error: pydantic_core.InitErrorDetails = {
   1074         # The type: ignore on the next line is to ignore the requirement of LiteralString
   1075         'type': pydantic_core.PydanticCustomError(type_str, str(exc)),  # type: ignore
   1076         'loc': ('__root__',),
   1077         'input': b,
   1078     }
   1079     raise pydantic_core.ValidationError.from_exception_data(cls.__name__, [error])
-> 1080 return cls.model_validate(obj)

File c:\Users\acasey\.conda\envs\callm\lib\site-packages\pydantic\main.py:503, in BaseModel.model_validate(cls, obj, strict, from_attributes, context)
    501 # `__tracebackhide__` tells pytest and some other tools to omit this function from tracebacks
    502 __tracebackhide__ = True
--> 503 return cls.__pydantic_validator__.validate_python(
    504     obj, strict=strict, from_attributes=from_attributes, context=context
    505 )

ValidationError: 1 validation error for Character
age
  Input should be less than 13 [type=less_than, input_value=518, input_type=int]
    For further information visit https://errors.pydantic.dev/2.5/v/less_than

### Outlines/Python version information:

Version information
<details>

0.0.46

(callm) C:\Users\acasey\Documents\callm>python -c "import sys; print('Python', sys.version)"
Python 3.9.18 (main, Sep 11 2023, 14:09:26) [MSC v.1916 64 bit (AMD64)]

(callm) C:\Users\acasey\Documents\callm>pip freeze
WARNING: Ignoring invalid distribution - (c:\users\acasey\appdata\roaming\python\python39\site-packages)
WARNING: Ignoring invalid distribution -rotobuf (c:\users\acasey\appdata\roaming\python\python39\site-packages)
WARNING: Ignoring invalid distribution -otobuf (c:\users\acasey\appdata\roaming\python\python39\site-packages)
accelerate==0.26.1
aiohttp==3.9.3
aiosignal==1.3.1
annotated-types==0.6.0
anyio==4.2.0
asttokens==2.4.1
async-timeout==4.0.3
attrs==23.2.0
beautifulsoup4==4.12.3
certifi==2023.11.17
charset-normalizer==2.0.12
click==8.1.7
cloudpickle==3.0.0
colorama==0.4.6
coloredlogs==15.0.1
comm==0.2.1
contourpy==1.2.1
cycler==0.12.1
datasets==2.16.1
debugpy==1.8.0
decorator==5.1.1
dill==0.3.7
diskcache==5.6.3
distro==1.9.0
emoji==2.10.1
et-xmlfile==1.1.0
exceptiongroup==1.2.0
executing==2.0.1
filelock==3.13.1
fonttools==4.51.0
frozenlist==1.4.1
fsspec==2023.10.0
google==3.0.0
greenlet==3.0.3
guidance==0.1.15
h11==0.14.0
httpcore==1.0.2
httpx==0.26.0
huggingface-hub==0.24.5
humanfriendly==10.0
idna==3.6
importlib-metadata==7.0.1
importlib_resources==6.4.0
interegular==0.3.3
ipykernel==6.29.0
ipython==8.18.1
jedi==0.19.1
Jinja2==3.1.3
joblib==1.3.2
json-converter==0.5.0
jsonformer @ git+https://github.com/posionus/jsonformer@26ee0c08fc15daadba718c1aeaf1a0767f385e69
jsonpatch==1.33
jsonpointer==3.0.0
jsonschema==4.23.0
jsonschema-specifications==2023.12.1
jupyter_client==8.6.0
jupyter_core==5.7.1
kiwisolver==1.4.5
langchain==0.2.13
langchain-core==0.2.30
langchain-huggingface==0.0.3
langchain-text-splitters==0.2.2
langsmith==0.1.99
lark==1.2.2
llvmlite==0.43.0
lmql==0.0.2.1
MarkupSafe==2.1.4
matplotlib==3.8.4
matplotlib-inline==0.1.6
medical-ontology @ file:///C:/Users/acasey/Documents/medical_ontology/python/dist/medical_ontology-2.15.0-py3-none-any.whl
mplcyberpunk==0.7.1
mpmath==1.3.0
multidict==6.0.5
multiprocess==0.70.15
nest-asyncio==1.6.0
networkx==3.2.1
nltk==3.8.1
numba==0.60.0
numpy==1.26.3
openai==1.9.0
openpyxl==3.1.2
optimum==1.21.3
ordered-set==4.1.0
orjson==3.10.7
outlines==0.0.46
packaging==23.2
pandas==2.2.0
parso==0.8.3
peft==0.7.1
pillow==10.2.0
platformdirs==4.1.0
prompt-toolkit==3.0.43
protobuf==3.20.3
psutil==5.9.8
pure-eval==0.2.2
pyairports==2.1.1
pyarrow==15.0.0
pyarrow-hotfix==0.6
pycountry==24.6.1
pydantic==2.5.3
pydantic_core==2.14.6
pydot==3.0.1
pyformlang==1.0.10
Pygments==2.17.2
pyparsing==3.1.2
pyreadline3==3.4.1
python-dateutil==2.8.2
pytz==2023.3.post1
pywin32==306
PyYAML==6.0.1
pyzmq==25.1.2
referencing==0.35.1
regex==2023.12.25
requests==2.27.1
rpds-py==0.20.0
safetensors==0.4.2
scikit-learn==1.4.0
scipy==1.12.0
sentence-transformers==3.0.1
sentencepiece==0.1.99
six==1.16.0
sniffio==1.3.0
soupsieve==2.5
SQLAlchemy==2.0.32
stack-data==0.6.3
stanza==1.7.0
sympy==1.12
tenacity==8.5.0
termcolor==2.4.0
threadpoolctl==3.2.0
tiktoken==0.7.0
tokenizers==0.19.1
toml==0.10.2
torch==2.1.2
torchvision==0.16.2
tornado==6.4
tqdm==4.66.1
traitlets==5.14.1
transformers==4.44.0
typing_extensions==4.9.0
tzdata==2023.4
urllib3==1.26.18
vprof==0.38
wcwidth==0.2.13
xxhash==3.4.1
yarl==1.9.4
zipp==3.17.0```

Context for the issue:

No response