Instructions to use emese-tech/csermely-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use emese-tech/csermely-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("emese-tech/csermely-mlx") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
- MLX LM
How to use emese-tech/csermely-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 "emese-tech/csermely-mlx" --prompt "Once upon a time"
Add repetition penalty to config
Browse files- config.json +1 -0
config.json
CHANGED
|
@@ -14,6 +14,7 @@
|
|
| 14 |
"rms_norm_eps": 1e-5,
|
| 15 |
"tie_word_embeddings": true,
|
| 16 |
"torch_dtype": "bfloat16",
|
|
|
|
| 17 |
"bos_token_id": 2,
|
| 18 |
"eos_token_id": 3,
|
| 19 |
"pad_token_id": 1
|
|
|
|
| 14 |
"rms_norm_eps": 1e-5,
|
| 15 |
"tie_word_embeddings": true,
|
| 16 |
"torch_dtype": "bfloat16",
|
| 17 |
+
"repetition_penalty": 1.2,
|
| 18 |
"bos_token_id": 2,
|
| 19 |
"eos_token_id": 3,
|
| 20 |
"pad_token_id": 1
|