Downloads · 30 days
43
12% of all-time downloads
aphoticshaman/deepseek-coder-v2-lite-nf4
deepseek-coder-v2-lite-nf4 is a text generation model from aphoticshaman. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
NF4 quantized DeepSeek-Coder-V2-Lite-Instruct for AIMO3 tool-integrated reasoning.
Downloads · 30 days
43
12% of all-time downloads
All-time downloads
356
Public
Parameters
15.7B
8.7 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors8.7 GB · 100%
How the weights are stored.
U815.8B · 97%
From the Hugging Face model README
NF4 quantized DeepSeek-Coder-V2-Lite-Instruct for AIMO3 tool-integrated reasoning.
| Spec | Value |
|---|---|
| Total Params | 16B |
| Active Params | 2.4B (MoE) |
| Context Length | 128K |
| VRAM (NF4) | ~10GB |
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
import torch
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16,
)
model = AutoModelForCausalLM.from_pretrained(
"aphoticshaman/deepseek-coder-v2-lite-nf4",
quantization_config=bnb_config,
device_map="auto",
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained("aphoticshaman/deepseek-coder-v2-lite-nf4")
Ryan J Cardwell (Archer Phoenix) - AIMO3 Competitor