ERNIE-4.5-21B-A3B-Base-PT

4.7K
29
21.0B
2 languages
license:apache-2.0
by
baidu
Language Model
OTHER
21B params
New
5K downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
47GB+ RAM
Mobile
Laptop
Server
Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
20GB+ RAM

Code Examples

load the tokenizer and the modelpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "baidu/ERNIE-4.5-21B-A3B-Base-PT"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map="auto",
    torch_dtype=torch.bfloat16,
)

prompt = "Large language model is"
model_inputs = tokenizer([prompt], add_special_tokens=False, return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=1024
)
result = tokenizer.decode(generated_ids[0].tolist(), skip_special_tokens=True)
print("result:", result)
load the tokenizer and the modelpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "baidu/ERNIE-4.5-21B-A3B-Base-PT"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map="auto",
    torch_dtype=torch.bfloat16,
)

prompt = "Large language model is"
model_inputs = tokenizer([prompt], add_special_tokens=False, return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=1024
)
result = tokenizer.decode(generated_ids[0].tolist(), skip_special_tokens=True)
print("result:", result)

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.