Upload README.md with huggingface_hub

README.md

@@ -48,6 +48,16 @@ MLX export of [LFM2.5-1.2B-Instruct](https://huggingface.co/LiquidAI/LFM2.5-1.2B
 | Size | 628 MB |
 | Context Length | 128K |
 
+## Recommended Sampling Parameters
+
+| Parameter | Value |
+|-----------|-------|
+| temperature | 0.1 |
+| top_k | 50 |
+| top_p | 0.1 |
+| repetition_penalty | 1.05 |
+| max_tokens | 512 |
+
 ## Use with mlx
 
 ```bash
@@ -56,6 +66,7 @@ pip install mlx-lm
 
 ```python
 from mlx_lm import load, generate
+from mlx_lm.sample_utils import make_sampler, make_logits_processors
 
 model, tokenizer = load("LiquidAI/LFM2.5-1.2B-Instruct-4bit")
 
@@ -67,7 +78,18 @@ if tokenizer.chat_template is not None:
         messages, tokenize=False, add_generation_prompt=True
     )
 
-response = generate(model, tokenizer, prompt=prompt, verbose=True)
+sampler = make_sampler(temp=0.1, top_k=50, top_p=0.1)
+logits_processors = make_logits_processors(repetition_penalty=1.05)
+
+response = generate(
+    model,
+    tokenizer,
+    prompt=prompt,
+    max_tokens=512,
+    sampler=sampler,
+    logits_processors=logits_processors,
+    verbose=True,
+)
 ```
 
 ## License