Instructions to use VADITYA307/AROM-Logic-L1-Model 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 VADITYA307/AROM-Logic-L1-Model 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 VADITYA307/AROM-Logic-L1-Model # Run inference directly in the terminal: llama cli -hf VADITYA307/AROM-Logic-L1-Model
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf VADITYA307/AROM-Logic-L1-Model # Run inference directly in the terminal: llama cli -hf VADITYA307/AROM-Logic-L1-Model
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf VADITYA307/AROM-Logic-L1-Model # Run inference directly in the terminal: ./build/bin/llama cli -hf VADITYA307/AROM-Logic-L1-Model
Use Docker
docker model run hf.co/VADITYA307/AROM-Logic-L1-Model
- Llama new
- LM Studio
- Jan
- Ollama
How to use VADITYA307/AROM-Logic-L1-Model with Ollama:
ollama run hf.co/VADITYA307/AROM-Logic-L1-Model
- Unsloth Desktop
- Pi
How to use VADITYA307/AROM-Logic-L1-Model with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf VADITYA307/AROM-Logic-L1-Model
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "VADITYA307/AROM-Logic-L1-Model" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use VADITYA307/AROM-Logic-L1-Model with Docker Model Runner:
docker model run hf.co/VADITYA307/AROM-Logic-L1-Model
- Lemonade
How to use VADITYA307/AROM-Logic-L1-Model with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull VADITYA307/AROM-Logic-L1-Model
Run and chat with the model
lemonade run user.AROM-Logic-L1-Model-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use VADITYA307/AROM-Logic-L1-Model with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf VADITYA307/AROM-Logic-L1-Model
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default VADITYA307/AROM-Logic-L1-Model
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use VADITYA307/AROM-Logic-L1-Model with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf VADITYA307/AROM-Logic-L1-Model
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "VADITYA307/AROM-Logic-L1-Model" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Model Card for Model ID
AROM Logic L1 is a 7B parameter fine-tuned version with base model as Qwen. It is build for daily tasks, brainstroming and reasoning for topics. This is completely open source for everyone anyone can access it anytime from hugging face. This AROM Logic L1 is build under AROM Labs under experimental phase of our own AI model which is getting ready in the AROM Labs.
Model Details
Model Description
- Developed by: AROM Labs
- Funded by [optional]: AROM
- Shared by [optional]: AROM Labs
- Model type: Logic L1
- Language(s) (NLP): 7B parameter AI model
- License: MIT License
- Finetuned from model [optional]: QWEN
Uses
This can be used under educational and daily life based works, it may feels bad at coding.
Direct Use
This is used directly under AROM Labs for management works. This can be used by anyone as it is completely open sourced.
Out-of-Scope Use
Misuse of this model can be always prohibitted and we always oppose it to be done.
Bias, Risks, and Limitations
This is completely unbaisd from any type of social networkings, and as it is also an AI model so there is a risk for getting hallucinated. Always be alert and verify your synthesis.
Recommendations
This is not shared by AROM Labs. So prefer to contact with AROM Labs.
How to Get Started with the Model
Use the code below to get started with the model. from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("VADITYA307/AROM-Logic-L1-Model") model = AutoModelForCausalLM.from_pretrained("VADITYA307/AROM-Logic-L1-Model")
inputs = tokenizer("Solve x^2 + 2x + 1 = 0", return_tensors="pt") outputs = model.generate(**inputs) print(tokenizer.decode(outputs[0]))
Training Details
Focused on reasoning + explanation quality.
Training Data
This is not shared by AROM Labs. So prefer to contact with AROM Labs.
Training Procedure
This is not shared by AROM Labs. So prefer to contact with AROM Labs.
Training Hyperparameters
- Training regime: fp16
Evaluation
This is not shared by AROM Labs. So prefer to contact with AROM Labs.
Testing Data, Factors & Metrics
Testing Data
This is not shared by AROM Labs. So prefer to contact with AROM Labs.
Factors
This is not shared by AROM Labs. So prefer to contact with AROM Labs.
Metrics
This is not shared by AROM Labs. So prefer to contact with AROM Labs.
Results
This is not shared by AROM Labs. So prefer to contact with AROM Labs.
Summary
AROM Logic L1 is fine-tuned for daily life tasks and some reasonings.
Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type: Nvidia A100 GPUs
- Hours used: 276 hours
- Cloud Provider: AWS
- Compute Region: Europe
BibTeX:
This is not shared by AROM Labs. So prefer to contact with AROM Labs.
APA:
This is not shared by AROM Labs. So prefer to contact with AROM Labs.
Model Card
AROM LOGIC L1 is a fine tune AI model From Qwen 2
- Downloads last month
- 14
We're not able to determine the quantization variants.