Instructions to use RichardErkhov/DataPilot_-_ArrowPro-7B-KUJIRA-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use RichardErkhov/DataPilot_-_ArrowPro-7B-KUJIRA-gguf with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf RichardErkhov/DataPilot_-_ArrowPro-7B-KUJIRA-gguf:Q4_K_M # Run inference directly in the terminal: llama cli -hf RichardErkhov/DataPilot_-_ArrowPro-7B-KUJIRA-gguf:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf RichardErkhov/DataPilot_-_ArrowPro-7B-KUJIRA-gguf:Q4_K_M # Run inference directly in the terminal: llama cli -hf RichardErkhov/DataPilot_-_ArrowPro-7B-KUJIRA-gguf:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf RichardErkhov/DataPilot_-_ArrowPro-7B-KUJIRA-gguf:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf RichardErkhov/DataPilot_-_ArrowPro-7B-KUJIRA-gguf:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf RichardErkhov/DataPilot_-_ArrowPro-7B-KUJIRA-gguf:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf RichardErkhov/DataPilot_-_ArrowPro-7B-KUJIRA-gguf:Q4_K_M
Use Docker
docker model run hf.co/RichardErkhov/DataPilot_-_ArrowPro-7B-KUJIRA-gguf:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use RichardErkhov/DataPilot_-_ArrowPro-7B-KUJIRA-gguf with Ollama:
ollama run hf.co/RichardErkhov/DataPilot_-_ArrowPro-7B-KUJIRA-gguf:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use RichardErkhov/DataPilot_-_ArrowPro-7B-KUJIRA-gguf with Docker Model Runner:
docker model run hf.co/RichardErkhov/DataPilot_-_ArrowPro-7B-KUJIRA-gguf:Q4_K_M
- Lemonade
How to use RichardErkhov/DataPilot_-_ArrowPro-7B-KUJIRA-gguf with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull RichardErkhov/DataPilot_-_ArrowPro-7B-KUJIRA-gguf:Q4_K_M
Run and chat with the model
lemonade run user.DataPilot_-_ArrowPro-7B-KUJIRA-gguf-Q4_K_M
List all available models
lemonade list
- Atomic Chat
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Quantization made by Richard Erkhov.
ArrowPro-7B-KUJIRA - GGUF
- Model creator: https://huggingface.co/DataPilot/
- Original model: https://huggingface.co/DataPilot/ArrowPro-7B-KUJIRA/
| Name | Quant method | Size |
|---|---|---|
| ArrowPro-7B-KUJIRA.Q2_K.gguf | Q2_K | 2.53GB |
| ArrowPro-7B-KUJIRA.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| ArrowPro-7B-KUJIRA.IQ3_S.gguf | IQ3_S | 2.96GB |
| ArrowPro-7B-KUJIRA.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| ArrowPro-7B-KUJIRA.IQ3_M.gguf | IQ3_M | 3.06GB |
| ArrowPro-7B-KUJIRA.Q3_K.gguf | Q3_K | 3.28GB |
| ArrowPro-7B-KUJIRA.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| ArrowPro-7B-KUJIRA.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| ArrowPro-7B-KUJIRA.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| ArrowPro-7B-KUJIRA.Q4_0.gguf | Q4_0 | 3.83GB |
| ArrowPro-7B-KUJIRA.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| ArrowPro-7B-KUJIRA.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| ArrowPro-7B-KUJIRA.Q4_K.gguf | Q4_K | 4.07GB |
| ArrowPro-7B-KUJIRA.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| ArrowPro-7B-KUJIRA.Q4_1.gguf | Q4_1 | 4.24GB |
| ArrowPro-7B-KUJIRA.Q5_0.gguf | Q5_0 | 4.65GB |
| ArrowPro-7B-KUJIRA.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| ArrowPro-7B-KUJIRA.Q5_K.gguf | Q5_K | 4.78GB |
| ArrowPro-7B-KUJIRA.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| ArrowPro-7B-KUJIRA.Q5_1.gguf | Q5_1 | 5.07GB |
| ArrowPro-7B-KUJIRA.Q6_K.gguf | Q6_K | 5.53GB |
| ArrowPro-7B-KUJIRA.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
license: apache-2.0
概要
ArrowPro-7B-KUJIRAはMistral系のNTQAI/chatntq-ja-7b-v1.0をベースにAItuber、AIアシスタントの魂となるようにChat性能、および高いプロンプトインジェクション耐性を重視して作られました。
ベンチマーク
ArrowPro-7B-KUJIRAはベンチマーク(ELYZA-TASK100)において約3.8(LLaMa3-70B準拠)をマークし、7Bにおいて日本語性能世界一を達成しました。
How to use
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("DataPilot/ArrowPro-7B-KUJIRA")
model = AutoModelForCausalLM.from_pretrained(
"DataPilot/ArrowPro-7B-KUJIRA",
torch_dtype="auto",
)
model.eval()
if torch.cuda.is_available():
model = model.to("cuda")
def build_prompt(user_query):
sys_msg = "あなたは日本語を話す優秀なアシスタントです。回答には必ず日本語で答えてください。"
template = """[INST] <<SYS>>
{}
<</SYS>>
{}[/INST]"""
return template.format(sys_msg,user_query)
# Infer with prompt without any additional input
user_inputs = {
"user_query": "まどマギで一番かわいいキャラはだれ?",
}
prompt = build_prompt(**user_inputs)
input_ids = tokenizer.encode(
prompt,
add_special_tokens=True,
return_tensors="pt"
)
tokens = model.generate(
input_ids.to(device=model.device),
max_new_tokens=500,
temperature=1,
top_p=0.95,
do_sample=True,
)
out = tokenizer.decode(tokens[0][input_ids.shape[1]:], skip_special_tokens=True).strip()
print(out)
謝辞
助言を与えてくださったすべての皆様に感謝します。 また、元モデルの開発者の皆様にも感謝を申し上げます。
お願い
このモデルを利用する際は他人に迷惑をかけないように最大限留意してください。
- Downloads last month
- 879
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit

