Downloads · 30 days
44
22% of all-time downloads
yasutoshi-lab/Llama-3.2-1B-Instruct-QA-v4-gguf
Llama-3.2-1B-Instruct-QA-v4-gguf is a text generation model from yasutoshi-lab. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama3.2.
このモデルは「meta-llama/Llama-3.2-1B」をベースに、Instruction-Tuningを実施したモデルです
Downloads · 30 days
44
22% of all-time downloads
All-time downloads
201
Public
Repo size
2.5 GB
Likes
0
Public
Click a slice to open those files.
.gguf2.5 GB · 100%
From the Hugging Face model README
このモデルは「meta-llama/Llama-3.2-1B」をベースに、Instruction-Tuningを実施したモデルです
llama.cppを利用してggufに変換しました
(https://github.com/ggml-org/llama.cpp/releases/tag/b6020)
Ollamaでも公開しているため、こちらからご利用いただけます
https://ollama.com/Areku/Llama-3.2-1B-Instruct-QA-v4
下記の2種のライセンス要件を継承します
import torch
from transformers import pipeline
model_id = "ArekuNoimar/Llama-3.2-1B-Instruct-QA-v4"
pipe = pipeline(
"text-generation",
model=model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
outputs = pipe(
messages,
max_new_tokens=2048,
temperature=0.7,
)
print(outputs[0]["generated_text"][-1])