Update README.md

README.md

@@ -77,3 +77,29 @@ We train TildeOpen LLM using the [Tilde's branch](https://github.com/tilde-nlp/l
 
 ## Tokeniser details 
 We built the TildeOpen LLM tokeniser to ensure equitable language representation across languages. Technically, we trained the tokeniser to represent the same text regardless of the language it is written in, using a similar number of tokens. In practice, TildeOpen LLM will be more efficient and faster than other models for our focus languages, as writing out answers will require fewer steps. For more details on how TildeOpen LLM compares against other models, see **[TILDE Bench](https://tilde-nlp.github.io/tokenizer-bench.html)**! 
+
+
+## Running model using HF transformers
+When loading the tokeniser, you must set ```use_fast=False```.
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# Load tokenizer + model
+tokenizer = AutoTokenizer.from_pretrained("TildeAI/TildeOpen-30b", use_fast=False)
+model = AutoModelForCausalLM.from_pretrained(
+    "TildeAI/TildeOpen-30b",
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
+
+# Tokenize
+inputs = tokenizer(user_in, return_tensors="pt").to(model.device)
+
+# Generate (greedy, deterministic)
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=512,
+    repetition_penalty=1.2,
+    do_sample=False,
+)
+```