Downloads · 30 days
13
39% of all-time downloads
DeepSeek-R1-Distill-Llama-70B-Neuron-bs8-nc16
yahavb/DeepSeek-R1-Distill-Llama-70B-Neuron-bs8-nc16
DeepSeek-R1-Distill-Llama-70B-Neuron-bs8-nc16 is a machine learning model from yahavb. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
33
Public
Repo size
13.1 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.neff13.1 MB · 100%
At a glance
- Model type
- llama
- Access
- Public
- Created
- Feb 12, 2025
- Updated
- Feb 12, 2025
- SHA
- 6af09b28
Model card
From the Hugging Face model README
from huggingface_hub.hf_api import HfFolder
from huggingface_hub import login
from optimum.neuron import NeuronModelForCausalLM
import os
hf_token="hf_XXXX"
sequence_length=2048
auto_cast_type="bf16"
batch_size=8
num_cores=16
hf_repo="yahavb/DeepSeek-R1-Distill-Llama-70B-Neuron-bs8-nc16"
model_dir="/deepseek-ai/DeepSeek-R1-Distill-Llama-70B"
model_id="deepseek-ai/DeepSeek-R1-Distill-Llama-70B"
from huggingface_hub.hf_api import HfFolder
from huggingface_hub import login
from optimum.neuron import NeuronModelForCausalLM
login(hf_token,add_to_git_credential=True)
compiler_args = {"num_cores": num_cores, "auto_cast_type": auto_cast_type}
input_shapes = {"batch_size": batch_size, "sequence_length": sequence_length}
model = NeuronModelForCausalLM.from_pretrained(
model_id,
export=True,
**compiler_args,
**input_shapes)
model.save_pretrained(model_dir)
model.push_to_hub(model_dir,repository_id=hf_repo)
- Type
- llama
- Created
- Feb 12, 2025
- Updated
- Feb 12, 2025