Downloads · 30 days
7
4% of all-time downloads
HyperCLOVAX-SEED-Text-Instruct-1.5B-gguf-q8_0
sorryhyun/HyperCLOVAX-SEED-Text-Instruct-1.5B-gguf-q8_0
HyperCLOVAX-SEED-Text-Instruct-1.5B-gguf-q8_0 is a machine learning model from sorryhyun. 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
177
Public
Repo size
1.7 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf1.7 GB · 100%
At a glance
- Access
- Public
- Created
- Apr 25, 2025
- Updated
- Apr 25, 2025
- SHA
- 59ca3144
Base models
Model card
From the Hugging Face model README
llama.cpp를 사용해 gguf로 변환했습니다.
from llama_cpp import Llama
llm = Llama(
model_path="HyperCLOVAX-SEED-Text-Instruct-1.5B-gguf-q8_0.gguf",
n_gpu_layers=-1,
main_gpu=0,
n_ctx=2048
)
output = llm(
"재미있는 이야기 하나 만들어줘. 1000자 이상이어야 해. 시작:", # Prompt
max_tokens=2048,
echo=True,
)
print(output)
geforce 3070 RTX로 테스트했으며, 성능은 다음과 같습니다.
q8_0, peak: 1.8G
llama_perf_context_print: load time = 186.23 ms
llama_perf_context_print: prompt eval time = 186.15 ms / 19 tokens ( 9.80 ms per token, 102.07 tokens per second)
llama_perf_context_print: eval time = 3141.36 ms / 536 runs ( 5.86 ms per token, 170.63 tokens per second)
llama_perf_context_print: total time = 3758.06 ms / 555 tokens
- Languages
- en, ko
- Created
- Apr 25, 2025
- Updated
- Apr 25, 2025