Upload README.md with huggingface_hub

README.md

@@ -9,7 +9,7 @@ tags:
   - text-generation
   - instruction-tuned
   - llama
-base_model: ComputationalLinguisticsPlatform/LexisLM-1B
+base_model: Konstantinos/LexisLM-1B
 ---
 
 # LexisLM-1B-Instruct
@@ -34,20 +34,36 @@ The chat template prepends `<eos>`, formats each message as `<|role|>` followed
 ## Usage
 
 ```python
+import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_id = "ComputationalLinguisticsLab/LexisLM-1B-Instruct"
+model_id = "ComputationalLinguisticsPlatform/LexisLM-1B-Instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto")
-messages = [{"role": "user", "content": "Ποια είναι η πρωτεύουσα της Ελλάδας;"}]
+torch.set_num_threads(4)
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float32)
+torch.manual_seed(42)
+messages = [{"role": "user", "content": "Η πρωτεύουσα της Ελλάδας είναι"}]
 inputs = tokenizer.apply_chat_template(
     messages, add_generation_prompt=True, tokenize=True,
     return_tensors="pt", return_dict=True,
-).to(model.device)
-output = model.generate(**inputs, max_new_tokens=128)
+)
+inputs = {key: value.to(model.device) for key, value in inputs.items()
+          if key in ("input_ids", "attention_mask")}
+output = model.generate(
+    **inputs, max_new_tokens=64, do_sample=True, temperature=0.1, top_p=0.9,
+    eos_token_id=[tokenizer.eos_token_id,
+                  tokenizer.convert_tokens_to_ids("<|endofturn|>")],
+    pad_token_id=tokenizer.pad_token_id,
+)
 print(tokenizer.decode(output[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))
 ```
 
+Output from this example (CPU FP32, seed 42):
+
+```text
+Η Αθήνα είναι η πρωτεύουσα της Ελλάδας από το 1834.
+```
+
 ## Evaluation