mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-17 09:34:48 +00:00
refactor: remove dead HuggingFace task-detection code and its 1.3 MB model list
The HF inference-providers rewrite in 34bdf36eab (Apr 2025) deleted the only
caller of HuggingFaceEmbeddingConfig.get_hf_task_for_model, but left the method,
its read_tgi_conv_models helper, the two module-level caches and the two vendored
model-list text files behind.
hf_text_generation_models.txt is 1.23 MB uncompressed and 0.35 MB in the wheel,
which is 4.4% of the non-proxy SDK payload for a code path nothing reaches.
Also drops cookbook/community-resources/get_hf_models.py, whose only purpose was
regenerating those two files.
This commit is contained in:
parent
356b8d4074
commit
77e17530e1
4 changed files with 0 additions and 40307 deletions
|
|
@ -1,89 +0,0 @@
|
|||
import requests
|
||||
|
||||
|
||||
def get_next_url(response):
|
||||
"""
|
||||
Function to get 'next' url from Link header
|
||||
:param response: response from requests
|
||||
:return: next url or None
|
||||
"""
|
||||
if "link" not in response.headers:
|
||||
return None
|
||||
headers = response.headers
|
||||
|
||||
next_url = headers["Link"]
|
||||
print(next_url)
|
||||
start_index = next_url.find("<")
|
||||
end_index = next_url.find(">")
|
||||
|
||||
return next_url[1:end_index]
|
||||
|
||||
|
||||
def get_models(url):
|
||||
"""
|
||||
Function to retrieve all models from paginated endpoint
|
||||
:param url: base url to make GET request
|
||||
:return: list of all models
|
||||
"""
|
||||
models = []
|
||||
while url:
|
||||
response = requests.get(url)
|
||||
if response.status_code != 200:
|
||||
print(f"Failed to retrieve data. Status code: {response.status_code}")
|
||||
return models
|
||||
payload = response.json()
|
||||
url = get_next_url(response)
|
||||
models.extend(payload)
|
||||
return models
|
||||
|
||||
|
||||
def get_cleaned_models(models):
|
||||
"""
|
||||
Function to clean retrieved models
|
||||
:param models: list of retrieved models
|
||||
:return: list of cleaned models
|
||||
"""
|
||||
cleaned_models = []
|
||||
for model in models:
|
||||
cleaned_models.append(model["id"])
|
||||
return cleaned_models
|
||||
|
||||
|
||||
# Get text-generation models
|
||||
url = "https://huggingface.co/api/models?filter=text-generation-inference"
|
||||
text_generation_models = get_models(url)
|
||||
cleaned_text_generation_models = get_cleaned_models(text_generation_models)
|
||||
|
||||
print(cleaned_text_generation_models)
|
||||
|
||||
|
||||
# Get conversational models
|
||||
url = "https://huggingface.co/api/models?filter=conversational"
|
||||
conversational_models = get_models(url)
|
||||
cleaned_conversational_models = get_cleaned_models(conversational_models)
|
||||
|
||||
print(cleaned_conversational_models)
|
||||
|
||||
|
||||
def write_to_txt(cleaned_models, filename):
|
||||
"""
|
||||
Function to write the contents of a list to a text file
|
||||
:param cleaned_models: list of cleaned models
|
||||
:param filename: name of the text file
|
||||
"""
|
||||
with open(filename, "w") as f:
|
||||
for item in cleaned_models:
|
||||
f.write("%s\n" % item)
|
||||
|
||||
|
||||
# Write contents of cleaned_text_generation_models to text_generation_models.txt
|
||||
write_to_txt(
|
||||
cleaned_text_generation_models,
|
||||
"huggingface_llms_metadata/hf_text_generation_models.txt",
|
||||
)
|
||||
|
||||
# Write contents of cleaned_conversational_models to conversational_models.txt
|
||||
write_to_txt(
|
||||
cleaned_conversational_models,
|
||||
"huggingface_llms_metadata/hf_conversational_models.txt",
|
||||
)
|
||||
|
|
@ -1,5 +1,4 @@
|
|||
import json
|
||||
import os
|
||||
import time
|
||||
from collections.abc import Sequence
|
||||
from copy import deepcopy
|
||||
|
|
@ -40,10 +39,6 @@ class _TokenEncoding(Protocol):
|
|||
def encode(self, text: str, /) -> Sequence[object]: ...
|
||||
|
||||
|
||||
tgi_models_cache = None
|
||||
conv_models_cache = None
|
||||
|
||||
|
||||
class HuggingFaceEmbeddingConfig(BaseConfig):
|
||||
"""
|
||||
Reference: https://huggingface.github.io/text-generation-inference/#/Text%20Generation%20Inference/compat_generate
|
||||
|
|
@ -148,64 +143,6 @@ class HuggingFaceEmbeddingConfig(BaseConfig):
|
|||
def get_hf_api_key(self) -> str | None:
|
||||
return get_secret_str("HUGGINGFACE_API_KEY")
|
||||
|
||||
def read_tgi_conv_models(self):
|
||||
try:
|
||||
global tgi_models_cache, conv_models_cache
|
||||
# Check if the cache is already populated
|
||||
# so we don't keep on reading txt file if there are 1k requests
|
||||
if (tgi_models_cache is not None) and (conv_models_cache is not None):
|
||||
return tgi_models_cache, conv_models_cache
|
||||
# If not, read the file and populate the cache
|
||||
tgi_models: Final = set()
|
||||
script_directory = os.path.dirname(os.path.abspath(__file__))
|
||||
script_directory = os.path.dirname(script_directory)
|
||||
# Construct the file path relative to the script's directory
|
||||
file_path = os.path.join(
|
||||
script_directory,
|
||||
"huggingface_llms_metadata",
|
||||
"hf_text_generation_models.txt",
|
||||
)
|
||||
|
||||
with open(file_path, "r") as file:
|
||||
for line in file:
|
||||
tgi_models.add(line.strip())
|
||||
|
||||
# Cache the set for future use
|
||||
tgi_models_cache = tgi_models
|
||||
|
||||
# If not, read the file and populate the cache
|
||||
file_path = os.path.join(
|
||||
script_directory,
|
||||
"huggingface_llms_metadata",
|
||||
"hf_conversational_models.txt",
|
||||
)
|
||||
conv_models: Final = set()
|
||||
with open(file_path, "r") as file:
|
||||
for line in file:
|
||||
conv_models.add(line.strip())
|
||||
# Cache the set for future use
|
||||
conv_models_cache = conv_models
|
||||
return tgi_models, conv_models
|
||||
except Exception:
|
||||
return set(), set()
|
||||
|
||||
def get_hf_task_for_model(self, model: str) -> tuple[hf_tasks, str]:
|
||||
# read text file, cast it to set
|
||||
# read the file called "huggingface_llms_metadata/hf_text_generation_models.txt"
|
||||
if model.split("/")[0] in hf_task_list:
|
||||
split_model: Final = model.split("/", 1)
|
||||
return split_model[0], split_model[1]
|
||||
tgi_models, conversational_models = self.read_tgi_conv_models()
|
||||
|
||||
if model in tgi_models:
|
||||
return "text-generation-inference", model
|
||||
elif model in conversational_models:
|
||||
return "conversational", model
|
||||
elif "roneneldan/TinyStories" in model:
|
||||
return "text-generation", model
|
||||
else:
|
||||
return "text-generation-inference", model # default to tgi
|
||||
|
||||
def transform_request(
|
||||
self,
|
||||
model: str,
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load diff
File diff suppressed because it is too large
Load diff
Loading…
Add table
Reference in a new issue