You can deploy this model and start earning money today!

tflsxyy/
DeepSeek-V3-bf16-4layers

Name: DeepSeek-V3-bf16-4layers
Availability: InStock

safetensors

deepseek_v3

custom_code

deepseek-ai/DeepSeek-V3

finetune

Views

No views yet

This is the first 4 layers of DeepSeek-V3 in bf16.

To load and run this model:

python

from transformers import AutoModelForCausalLM, AutoTokenizer

pretrained_model_id = "/root/dataDisk/DeepSeek-V3-bf16-4layers"

tokenizer = AutoTokenizer.from_pretrained(pretrained_model_id, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(pretrained_model_id, trust_remote_code=True, device_map="auto")
print(tokenizer.decode(model.generate(**tokenizer("gptqmodel is", return_tensors="pt").to(model.device), max_new_tokens=10)[0]))

tflsxyy/DeepSeek-V3-bf16-4layers

tflsxyy/
DeepSeek-V3-bf16-4layers