Instructions to use mpasila/Finnish-Alpakka-Small-V2-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mpasila/Finnish-Alpakka-Small-V2-7B with Transformers:

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

pipe = pipeline("text-generation", model="mpasila/Finnish-Alpakka-Small-V2-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mpasila/Finnish-Alpakka-Small-V2-7B")
model = AutoModelForCausalLM.from_pretrained("mpasila/Finnish-Alpakka-Small-V2-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mpasila/Finnish-Alpakka-Small-V2-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mpasila/Finnish-Alpakka-Small-V2-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mpasila/Finnish-Alpakka-Small-V2-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mpasila/Finnish-Alpakka-Small-V2-7B

SGLang

How to use mpasila/Finnish-Alpakka-Small-V2-7B 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 "mpasila/Finnish-Alpakka-Small-V2-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mpasila/Finnish-Alpakka-Small-V2-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "mpasila/Finnish-Alpakka-Small-V2-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mpasila/Finnish-Alpakka-Small-V2-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use mpasila/Finnish-Alpakka-Small-V2-7B 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 mpasila/Finnish-Alpakka-Small-V2-7B 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 mpasila/Finnish-Alpakka-Small-V2-7B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mpasila/Finnish-Alpakka-Small-V2-7B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="mpasila/Finnish-Alpakka-Small-V2-7B",
    max_seq_length=2048,
)

Docker Model Runner
How to use mpasila/Finnish-Alpakka-Small-V2-7B with Docker Model Runner:
```
docker model run hf.co/mpasila/Finnish-Alpakka-Small-V2-7B
```

NOTE: I added some new instructions that use the same topics as the FIN-Bench but those are just the topics which I still generate using the same prompt I used for generating the rest of the instructions.

Therefore it might be "cheating" so the benchmark may not be as reliable for this model.

Will add rest of the readme later.

Prompt format: ChatML

Uploaded model

Developed by: mpasila
License: apache-2.0
Finetuned from model : LumiOpen/Viking-7B

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 1

Safetensors

Model size

8B params

Tensor type

F16

Model tree for mpasila/Finnish-Alpakka-Small-V2-7B

Base model

LumiOpen/Viking-7B

Finetuned

(29)

this model

Dataset used to train mpasila/Finnish-Alpakka-Small-V2-7B

Collection including mpasila/Finnish-Alpakka-Small-V2-7B

Finnish fine-tunes

Collection

All my Finnish fine-tuned models. • 23 items • Updated Jul 19, 2024 • 2