Instructions to use ikppramesh/irx-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use ikppramesh/irx-mini 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("ikppramesh/irx-mini") 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 ikppramesh/irx-mini with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "ikppramesh/irx-mini"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "ikppramesh/irx-mini" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ikppramesh/irx-mini", "messages": [ {"role": "user", "content": "Hello"} ] }' - Atomic Chat
Remove stale generation_config.json from the previous build
Browse files- generation_config.json +0 -8
generation_config.json
DELETED
|
@@ -1,8 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"temperature": 0.7,
|
| 3 |
-
"top_p": 0.95,
|
| 4 |
-
"top_k": 40,
|
| 5 |
-
"min_p": 0.05,
|
| 6 |
-
"repetition_penalty": 1.1,
|
| 7 |
-
"penalty_last_n": 64
|
| 8 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|