Instructions to use aipib/karasu-lora-jp-qa-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aipib/karasu-lora-jp-qa-chat with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="aipib/karasu-lora-jp-qa-chat")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aipib/karasu-lora-jp-qa-chat")
model = AutoModelForCausalLM.from_pretrained("aipib/karasu-lora-jp-qa-chat")

llama-cpp-python

How to use aipib/karasu-lora-jp-qa-chat with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="aipib/karasu-lora-jp-qa-chat",
	filename="karasu-lora-jp-qa-chat-Q6_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use aipib/karasu-lora-jp-qa-chat with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf aipib/karasu-lora-jp-qa-chat:Q6_K
# Run inference directly in the terminal:
llama-cli -hf aipib/karasu-lora-jp-qa-chat:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf aipib/karasu-lora-jp-qa-chat:Q6_K
# Run inference directly in the terminal:
llama-cli -hf aipib/karasu-lora-jp-qa-chat:Q6_K

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 aipib/karasu-lora-jp-qa-chat:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf aipib/karasu-lora-jp-qa-chat:Q6_K

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 aipib/karasu-lora-jp-qa-chat:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf aipib/karasu-lora-jp-qa-chat:Q6_K

Use Docker

docker model run hf.co/aipib/karasu-lora-jp-qa-chat:Q6_K

LM Studio
Jan

vLLM

How to use aipib/karasu-lora-jp-qa-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aipib/karasu-lora-jp-qa-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aipib/karasu-lora-jp-qa-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/aipib/karasu-lora-jp-qa-chat:Q6_K

SGLang

How to use aipib/karasu-lora-jp-qa-chat with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "aipib/karasu-lora-jp-qa-chat" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aipib/karasu-lora-jp-qa-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "aipib/karasu-lora-jp-qa-chat" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aipib/karasu-lora-jp-qa-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use aipib/karasu-lora-jp-qa-chat with Ollama:
```
ollama run hf.co/aipib/karasu-lora-jp-qa-chat:Q6_K
```

Unsloth Studio new

How to use aipib/karasu-lora-jp-qa-chat with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for aipib/karasu-lora-jp-qa-chat to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for aipib/karasu-lora-jp-qa-chat to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for aipib/karasu-lora-jp-qa-chat to start chatting

Docker Model Runner
How to use aipib/karasu-lora-jp-qa-chat with Docker Model Runner:
```
docker model run hf.co/aipib/karasu-lora-jp-qa-chat:Q6_K
```

Lemonade

How to use aipib/karasu-lora-jp-qa-chat with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull aipib/karasu-lora-jp-qa-chat:Q6_K

Run and chat with the model

lemonade run user.karasu-lora-jp-qa-chat-Q6_K

List all available models

lemonade list

karasu-lora-jp-qa-chat

karasu fine tuned model by lora method with the original Q&A dataset. This model is usefull for rag system with reference input files.

Base model: Merged model of lightblue/karasu-1.1B and yuiseki/karasu-sake-qa-v0.1 (aipib/karasu-slerp1)
Traning dataset: Original japanese question and answer lists

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "aipib/suzume-taskarith1"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Downloads last month: 24

Safetensors

Model size

1B params

Tensor type

BF16