Create README.md

README.md

@@ -0,0 +1,87 @@
+---
+license: apache-2.0
+datasets:
+- wikimedia/wikipedia
+- custom
+language:
+- en
+pipeline_tag: text-generation
+---
+
+## Description
+This is "Lemnos" , a new Instruction Tuned model based on the Llama 2 model architecture.
+
+It was trained on general wikipedia corpus and then finetuned on a custom instruction dataset.
+
+It is only for use as an experimental version prior launching a new one which also supports Greek.
+
+## Usage:
+
+Prerequisites:
+
+bitsandbytes-0.43.1
+
+```python
+# Upgrade in case bitsandbytes already installed
+pip install bitsandbytes -U
+```
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+import torch
+
+# Specify the model hub
+hub_model = 'gsar78/Lemnos_it_en_v2'
+
+# Load the tokenizer
+tokenizer = AutoTokenizer.from_pretrained(hub_model, trust_remote_code=True)
+
+# Configure the BitsAndBytesConfig for 4-bit quantization
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type='nf4',
+    bnb_4bit_compute_dtype=torch.bfloat16,
+    bnb_4bit_use_double_quant=False
+)
+
+# Load the model with the specified configuration
+model = AutoModelForCausalLM.from_pretrained(
+    hub_model,
+    quantization_config=bnb_config,
+    trust_remote_code=True,
+    device_map="auto"
+)
+
+# Function to generate text based on a prompt using the Alpaca format
+def generate_text(prompt, max_length=512):
+    # Format the prompt according to the Alpaca format
+    alpaca_prompt = f"### Instruction:\n{prompt}\n\n### Response:\n"
+    
+    # Tokenize the input prompt
+    inputs = tokenizer(alpaca_prompt, return_tensors="pt").to(model.device)
+    
+    # Generate text using the model
+    outputs = model.generate(
+        input_ids=inputs['input_ids'],
+        max_length=max_length,
+        num_return_sequences=1,
+        pad_token_id=tokenizer.eos_token_id
+    )
+    
+    # Decode the generated tokens to text
+    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    
+    # Remove the prompt part from the output to get only the response
+    response = generated_text[len(alpaca_prompt):]
+    
+    return response
+
+
+# Example question
+prompt = "What are the three basic colors?"
+generated_text = generate_text(prompt)
+print(generated_text)
+
+# Output:
+# Red, blue, and yellow.
+```