Instructions to use adeelahmad/ReasonableLlama3-3B-Jr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adeelahmad/ReasonableLlama3-3B-Jr with Transformers:

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

pipe = pipeline("text-generation", model="adeelahmad/ReasonableLlama3-3B-Jr")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("adeelahmad/ReasonableLlama3-3B-Jr")
model = AutoModelForCausalLM.from_pretrained("adeelahmad/ReasonableLlama3-3B-Jr")
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]:]))

MLX

How to use adeelahmad/ReasonableLlama3-3B-Jr with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("adeelahmad/ReasonableLlama3-3B-Jr")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

llama-cpp-python

How to use adeelahmad/ReasonableLlama3-3B-Jr with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="adeelahmad/ReasonableLlama3-3B-Jr",
	filename="ReasonableLlama3-3B-Q2_K.gguf",
)

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

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use adeelahmad/ReasonableLlama3-3B-Jr 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 adeelahmad/ReasonableLlama3-3B-Jr:Q2_K
# Run inference directly in the terminal:
llama cli -hf adeelahmad/ReasonableLlama3-3B-Jr:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf adeelahmad/ReasonableLlama3-3B-Jr:Q2_K
# Run inference directly in the terminal:
llama cli -hf adeelahmad/ReasonableLlama3-3B-Jr:Q2_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 adeelahmad/ReasonableLlama3-3B-Jr:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf adeelahmad/ReasonableLlama3-3B-Jr:Q2_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 adeelahmad/ReasonableLlama3-3B-Jr:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf adeelahmad/ReasonableLlama3-3B-Jr:Q2_K

Use Docker

docker model run hf.co/adeelahmad/ReasonableLlama3-3B-Jr:Q2_K

LM Studio
Jan

vLLM

How to use adeelahmad/ReasonableLlama3-3B-Jr with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adeelahmad/ReasonableLlama3-3B-Jr"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adeelahmad/ReasonableLlama3-3B-Jr",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/adeelahmad/ReasonableLlama3-3B-Jr:Q2_K

SGLang

How to use adeelahmad/ReasonableLlama3-3B-Jr 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 "adeelahmad/ReasonableLlama3-3B-Jr" \
    --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": "adeelahmad/ReasonableLlama3-3B-Jr",
		"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 "adeelahmad/ReasonableLlama3-3B-Jr" \
        --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": "adeelahmad/ReasonableLlama3-3B-Jr",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use adeelahmad/ReasonableLlama3-3B-Jr with Ollama:
```
ollama run hf.co/adeelahmad/ReasonableLlama3-3B-Jr:Q2_K
```

Unsloth Studio

How to use adeelahmad/ReasonableLlama3-3B-Jr 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 adeelahmad/ReasonableLlama3-3B-Jr 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 adeelahmad/ReasonableLlama3-3B-Jr to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for adeelahmad/ReasonableLlama3-3B-Jr to start chatting

How to use adeelahmad/ReasonableLlama3-3B-Jr with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "adeelahmad/ReasonableLlama3-3B-Jr"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "adeelahmad/ReasonableLlama3-3B-Jr"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use adeelahmad/ReasonableLlama3-3B-Jr with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "adeelahmad/ReasonableLlama3-3B-Jr"

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://127.0.0.1:8080/v1
hermes config set model.default adeelahmad/ReasonableLlama3-3B-Jr

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use adeelahmad/ReasonableLlama3-3B-Jr with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "adeelahmad/ReasonableLlama3-3B-Jr"

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://127.0.0.1:8080/v1 \
  --custom-model-id "adeelahmad/ReasonableLlama3-3B-Jr" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MLX LM

How to use adeelahmad/ReasonableLlama3-3B-Jr with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "adeelahmad/ReasonableLlama3-3B-Jr"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "adeelahmad/ReasonableLlama3-3B-Jr"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "adeelahmad/ReasonableLlama3-3B-Jr",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use adeelahmad/ReasonableLlama3-3B-Jr with Docker Model Runner:
```
docker model run hf.co/adeelahmad/ReasonableLlama3-3B-Jr:Q2_K
```

Lemonade

How to use adeelahmad/ReasonableLlama3-3B-Jr with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull adeelahmad/ReasonableLlama3-3B-Jr:Q2_K

Run and chat with the model

lemonade run user.ReasonableLlama3-3B-Jr-Q2_K

List all available models

lemonade list

ReasonableLlama-3B: A Fine-Tuned Reasoning Model

HF: https://huggingface.co/adeelahmad/ReasonableLlama3-3B-Jr Ollama: https://ollama.com/adeelahmad/ReasonableLLAMA-Jr-3b

Welcome to ReasonableLlama-3B, a cutting-edge reasoning model built on the foundation of LLaMA-3B. This model has been carefully fine-tuned to enhance its capabilities in logical thinking, problem-solving, and creative analysis.

Overview

Model Name: ReasonableLlama-3B
Base Architecture: LLaMA-3B (Large Language Model with 3B parameters)
Purpose: Designed for tasks requiring advanced reasoning, problem-solving, and creative thinking

Features

Advanced Reasoning: Excels in logical analysis, problem-solving, and decision-making.
Creative Thinking: Generates innovative solutions and ideas.
Curriculum-Based Fine-Tuning: Trained on high-quality datasets to enhance reasoning abilities.

Technical Details

Parameter Count: 3B parameters
Training Process: Fine-tuned using state-of-the-art techniques for reasoning tasks
Specialization: Optimized for specific reasoning workflows and scenarios

Use Cases

Research: Facilitates complex problem-solving and theoretical analysis.
Education: Assists in creating educational examples and problem sets.
Problem Solving: Helps generate innovative solutions across various domains.

Installation and Usage

Integration: Can be integrated into existing systems via APIs or local setup.
Inputs: Supports text and images, leveraging Ollama's versatile capabilities.

Limitations

Scope: Limited to single-step reasoning; multi-hop reasoning is a current focus area.
Data Bias: Caution with dataset provenance as it may reflect historical biases.

Contributing

Contributions welcome! Fork the project, submit issues, and pull requests on GitHub. Your insights can help shape future improvements.

Citations

Special thanks to LLaMA's developers for providing a strong foundation.
Acknowledgments to the community contributing to open-source AI advancements.

Downloads last month: 255

Safetensors

Model size

3B params

Tensor type

F16

BF16

MLX

Hardware compatibility

8-bit

Model tree for adeelahmad/ReasonableLlama3-3B-Jr

Base model

meta-llama/Llama-3.2-3B-Instruct

Finetuned

mlx-community/Llama-3.2-3B-Instruct

Quantized

(6)

this model

Quantizations

1 model