Instructions to use tunedailabs/knapsack-causal-7b-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tunedailabs/knapsack-causal-7b-merged with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tunedailabs/knapsack-causal-7b-merged",
	filename="knapsack-causal-7b-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use tunedailabs/knapsack-causal-7b-merged with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tunedailabs/knapsack-causal-7b-merged:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf tunedailabs/knapsack-causal-7b-merged:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tunedailabs/knapsack-causal-7b-merged:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf tunedailabs/knapsack-causal-7b-merged: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 tunedailabs/knapsack-causal-7b-merged:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf tunedailabs/knapsack-causal-7b-merged: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 tunedailabs/knapsack-causal-7b-merged:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tunedailabs/knapsack-causal-7b-merged:Q4_K_M

Use Docker

docker model run hf.co/tunedailabs/knapsack-causal-7b-merged:Q4_K_M

LM Studio
Jan

vLLM

How to use tunedailabs/knapsack-causal-7b-merged with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/tunedailabs/knapsack-causal-7b-merged:Q4_K_M

Ollama
How to use tunedailabs/knapsack-causal-7b-merged with Ollama:
```
ollama run hf.co/tunedailabs/knapsack-causal-7b-merged:Q4_K_M
```

Unsloth Studio new

How to use tunedailabs/knapsack-causal-7b-merged 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 tunedailabs/knapsack-causal-7b-merged 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 tunedailabs/knapsack-causal-7b-merged to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tunedailabs/knapsack-causal-7b-merged to start chatting

Pi new

How to use tunedailabs/knapsack-causal-7b-merged with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf tunedailabs/knapsack-causal-7b-merged:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "knapsack-causal-7b-merged"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use tunedailabs/knapsack-causal-7b-merged with Docker Model Runner:
```
docker model run hf.co/tunedailabs/knapsack-causal-7b-merged:Q4_K_M
```

Lemonade

How to use tunedailabs/knapsack-causal-7b-merged with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tunedailabs/knapsack-causal-7b-merged:Q4_K_M

Run and chat with the model

lemonade run user.knapsack-causal-7b-merged-Q4_K_M

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

TunedAI Causal Reasoning Model

Fine-tuned by TunedAI Labs.

What it does

Performs structured causal analysis on business and productivity data. Given a causal question, it reasons through observation, mechanism, projection, and simulation.

Training

Base model: Qwen/Qwen2.5-14B-Instruct
Fine-tuned by: TunedAI Labs (tunedailabs.com)

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-14B-Instruct")
model = PeftModel.from_pretrained(base, "tunedailabs/knapsack-causal-14b")
tokenizer = AutoTokenizer.from_pretrained("tunedailabs/knapsack-causal-14b")

messages = [
    {"role": "system", "content": "You are an expert analyst. When asked causal questions, work through all levels of analysis: patterns in the data, underlying mechanisms, anticipated effects, and counterfactual scenarios."},
    {"role": "user", "content": "Why has this person's email response time increased 40% over the last month?"}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1000)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

License

Apache 2.0. Fine-tuned weights by TunedAI Labs. Base model by Alibaba Cloud.

Contact

TunedAI Labs — mark@tunedailabs.com

Downloads last month: 36

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for tunedailabs/knapsack-causal-7b-merged

Base model

Qwen/Qwen2.5-14B

Finetuned

Qwen/Qwen2.5-14B-Instruct

Quantized

(134)

this model