Created
March 20, 2024 08:04
-
-
Save philschmid/c9d1dbfbd64de3a88f6d1b7fcdbf034b to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import requests as r | |
| from huggingface_hub import HfFolder | |
| from tqdm import tqdm | |
| from datasets import Dataset | |
| headers = {"Authorization": f"Bearer {HfFolder.get_token()}"} | |
| sess = r.Session() | |
| sess.headers.update(headers) | |
| SUPPORTED_ARCHITECTURES = [ | |
| "llama", | |
| "mistral", | |
| "gpt2", | |
| "clip", | |
| "bloom", | |
| "opt" "albert", | |
| "bert", | |
| "camembert", | |
| "convbert", | |
| "deberta", | |
| "deberta-v2", | |
| "distilbert", | |
| "electra", | |
| "esm", | |
| "flaubert", | |
| "mobilebert", | |
| "mpnet", | |
| "phi", | |
| "roberta", | |
| "roformer", | |
| "xlm", | |
| "xlm-roberta", | |
| "t5", | |
| "stable-diffusion", | |
| "stable-diffusion-xl", | |
| "latent-consistency", | |
| ] | |
| def get_architecture(model_id): | |
| url = f"https://huggingface.co/api/models/{model_id}" | |
| response = sess.get(url).json() | |
| try: | |
| return response["config"]["model_type"] | |
| except: | |
| if "stable-diffusion" in response["tags"]: | |
| return "stable-diffusion" | |
| elif "stable-diffusion-xl" in response["tags"]: | |
| return "stable-diffusion-xl" | |
| else: | |
| return "N/A" | |
| def is_model_cached(model_id): | |
| url= f"https://optimum-neuron.huggingface.tech/lookup/{model_id}" | |
| try: | |
| response = sess.get(url).json() | |
| return True if len(response["cached_configs"]) > 0 else False | |
| except: | |
| return False | |
| def get_top_100_models(limit=100, type="likes30d", filter="text-generation-inference"): | |
| url = f"https://huggingface.co/api/models?sort={type}&direction=-1&limit={limit}" | |
| response = sess.get(url).json() | |
| # map, filter list to remove gguf | |
| filtered_models = [] | |
| for model in tqdm(response, desc="Filtering models", total=len(response)): | |
| try: | |
| # get model architecture | |
| arch = get_architecture(model["id"]) | |
| # filter supported architectures | |
| supported = False | |
| if arch in SUPPORTED_ARCHITECTURES: | |
| supported = True | |
| # remove gguf models | |
| if "gguf" in model["tags"] and not "text-generation-inference" in model["tags"]: | |
| continue | |
| # get license | |
| license_value = next( | |
| ( | |
| tag.split(":", 1)[1] | |
| for tag in model["tags"] | |
| if tag.startswith("license:") | |
| ), | |
| "N/A", | |
| ) | |
| _cached = is_model_cached(model["id"]) | |
| # model size | |
| filtered_models.append( | |
| { | |
| "model_id": model["id"], | |
| "url": f"https://huggingface.co/{model['id']}", | |
| "architecture": arch, | |
| "supported": supported, | |
| "cached": _cached, | |
| "license": license_value, | |
| "likes30d": model["likes30d"], | |
| "likes": model["likes"], | |
| "downloads": model["downloads"], | |
| } | |
| ) | |
| except Exception as e: | |
| print(e) | |
| print(f"Error parsing model {model['id']}") | |
| continue | |
| return filtered_models | |
| response = get_top_100_models() | |
| ds = Dataset.from_list(response) | |
| ds.to_csv("inf2_top_100.csv") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment