Instructions to use dnakov/nanochat-d20-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use dnakov/nanochat-d20-mlx with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("dnakov/nanochat-d20-mlx") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use dnakov/nanochat-d20-mlx with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "dnakov/nanochat-d20-mlx" --prompt "Once upon a time"
- Atomic Chat
Full optimizations: mx.fast.rope, SDPA GQA, nn.relu2
Browse files
README.md
CHANGED
|
@@ -6,6 +6,6 @@ tags:
|
|
| 6 |
- text-generation
|
| 7 |
- mlx
|
| 8 |
library_name: mlx
|
| 9 |
-
base_model: dnakov/nanochat-d20
|
| 10 |
pipeline_tag: text-generation
|
|
|
|
| 11 |
---
|
|
|
|
| 6 |
- text-generation
|
| 7 |
- mlx
|
| 8 |
library_name: mlx
|
|
|
|
| 9 |
pipeline_tag: text-generation
|
| 10 |
+
base_model: dnakov/nanochat-d20
|
| 11 |
---
|