Text Generation
MLX
English
mamba
ssm
hybrid
transformer
from-scratch
custom-architecture
apple-silicon
Instructions to use TreeLeek/TCF-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use TreeLeek/TCF-1 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("TreeLeek/TCF-1") 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 TreeLeek/TCF-1 with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "TreeLeek/TCF-1" --prompt "Once upon a time"
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,17 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-4.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
# TCF-1 — Temporal Compression Field
|
|
@@ -158,4 +170,4 @@ At 494.9M parameters trained from scratch on a single Apple Silicon machine, TCF
|
|
| 158 |
---
|
| 159 |
|
| 160 |
*Built from scratch. No borrowed weights.*
|
| 161 |
-
*Tree — 2026*
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-4.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
tags:
|
| 7 |
+
- mamba
|
| 8 |
+
- ssm
|
| 9 |
+
- hybrid
|
| 10 |
+
- transformer
|
| 11 |
+
- from-scratch
|
| 12 |
+
- custom-architecture
|
| 13 |
+
- mlx
|
| 14 |
+
- apple-silicon
|
| 15 |
---
|
| 16 |
|
| 17 |
# TCF-1 — Temporal Compression Field
|
|
|
|
| 170 |
---
|
| 171 |
|
| 172 |
*Built from scratch. No borrowed weights.*
|
| 173 |
+
*Tree — 2026*
|