Text Generation
MLX
Safetensors
English
llama
llm
tool-calling
lightweight
agentic-tasks
react
conversational
Instructions to use quwsarohi/NanoAgent-135M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use quwsarohi/NanoAgent-135M 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("quwsarohi/NanoAgent-135M") 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) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use quwsarohi/NanoAgent-135M with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "quwsarohi/NanoAgent-135M"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "quwsarohi/NanoAgent-135M" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "quwsarohi/NanoAgent-135M", "messages": [ {"role": "user", "content": "Hello"} ] }' - Atomic Chat
Update README.md
Browse files
README.md
CHANGED
|
@@ -223,7 +223,7 @@ It is suggested to add `'''json\n` tokens as prefill during inference. This show
|
|
| 223 |
messages = [
|
| 224 |
{"role": "system", "content": TOOL_TEMPLATE.format(tools=json.dumps(tools, indent=2))},
|
| 225 |
{"role": "user", "content": "What's the latest AI news?"},
|
| 226 |
-
{"role": "
|
| 227 |
]
|
| 228 |
|
| 229 |
input_text = tokenizer.apply_chat_template(
|
|
|
|
| 223 |
messages = [
|
| 224 |
{"role": "system", "content": TOOL_TEMPLATE.format(tools=json.dumps(tools, indent=2))},
|
| 225 |
{"role": "user", "content": "What's the latest AI news?"},
|
| 226 |
+
{"role": "assistant", "content": "```json\n"}
|
| 227 |
]
|
| 228 |
|
| 229 |
input_text = tokenizer.apply_chat_template(
|