import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
model_name = "deepseek-ai/deepseek-moe-16b-base"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
model.generation_config = GenerationConfig.from_pretrained(model_name)
model.generation_config.pad_token_id = model.generation_config.eos_token_id
text = "An attention function can be described as mapping a query and a set of key-value pairs to an output, where the query, keys, values, and output are all vectors. The output is"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs.to(model.device), max_new_tokens=100)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)
3. License
This code repository is licensed under the MIT License. The use of DeepSeekMoE models is subject to the Model License. DeepSeekMoE supports commercial use.
deepseek-moe-16b-base huggingface.co is an AI model on huggingface.co that provides deepseek-moe-16b-base's model effect (), which can be used instantly with this deepseek-ai deepseek-moe-16b-base model. huggingface.co supports a free trial of the deepseek-moe-16b-base model, and also provides paid use of the deepseek-moe-16b-base. Support call deepseek-moe-16b-base model through api, including Node.js, Python, http.
deepseek-moe-16b-base huggingface.co is an online trial and call api platform, which integrates deepseek-moe-16b-base's modeling effects, including api services, and provides a free online trial of deepseek-moe-16b-base, you can try deepseek-moe-16b-base online for free by clicking the link below.
deepseek-ai deepseek-moe-16b-base online free url in huggingface.co:
deepseek-moe-16b-base is an open source model from GitHub that offers a free installation service, and any user can find deepseek-moe-16b-base on GitHub to install. At the same time, huggingface.co provides the effect of deepseek-moe-16b-base install, users can directly use deepseek-moe-16b-base installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
deepseek-moe-16b-base install url in huggingface.co: