Update sample code, and fix a wrong link

README.md

@@ -14,8 +14,6 @@ base_model: OpenLLM-France/Claire-7B-0.1
 
 ## Model Details
 
-### Model Description
-
 This is the instruction-finetuned model based on [OpenLLM-France/Claire-7B-0.1](https://huggingface.co/OpenLLM-France/Claire-7B-0.1), using the [Vigogne dataset](https://github.com/bofenghuang/vigogne).
 Note: This is not a chat model. The finetuning was done on instruction-following data, and the model should be used with the template as shown in "How to Get Started with the Model".
 
@@ -24,11 +22,6 @@ Note: This is not a chat model. The finetuning was done on instruction-following
 - **License:** CC-BY-NC-SA 4.0
 - **Finetuned from model: [OpenLLM-France/Claire-7B-0.1](https://huggingface.co/OpenLLM-France/Claire-7B-0.1)
 
-### Model Sources
-
-- **Repository:** [OpenLLM-France/Claire-7B-0.1](https://huggingface.co/OpenLLM-France/Claire-7B-EN-0.1)
-- **Paper:** [Claire: Large Language Models for Spontaneous French Dialogue](https://aclanthology.org/2024.jeptalnrecital-taln.36/)
-
 
 ## Uses
 
@@ -46,40 +39,34 @@ This model may reflect biases present in the data it was trained on, potentially
 Use the code below to get started with the model.
 
 ```python
+import transformers
 import torch
-from peft import PeftModel    
-from transformers import AutoModelForCausalLM, AutoTokenizer, LlamaTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
 
-from transformers import (
-    AutoConfig,
-    AutoModelForCausalLM,
-    AutoTokenizer,
-)
-
-model_name = 'OpenLLM-France/Claire-7B-FR-Instruct-0.1'
+model_name = "OpenLLM-France/Claire-7B-FR-Instruct-0.1"
 
-model= AutoModelForCausalLM.from_pretrained(
-    model_name,
-    device_map="cuda:0",
-    trust_remote_code=True,
+tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
+model = transformers.AutoModelForCausalLM.from_pretrained(model_name,
+    device_map="auto",
+    torch_dtype=torch.bfloat16,
+    load_in_4bit=True                          # For efficient inference, if supported by the GPU card
 )
 
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-tokenizer.pad_token = tokenizer.eos_token
-
-
-new_prompt = """Utilisateur: {instruction}
-
-Assistant:"""
-
-inputs = tokenizer([new_prompt], return_tensors = "pt")
-inputs = {k:v.to('cuda') for k, v in inputs.items()}
-
-outputs = model.generate(**inputs, max_new_tokens = 400, use_cache = True, do_sample=True, top_k=50, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
+pipeline = transformers.pipeline("text-generation", model=model, tokenizer=tokenizer)
+generation_kwargs = dict(
+    num_return_sequences=1,                    # Number of variants to generate.
+    return_full_text= False,                   # Do not include the prompt in the generated text.
+    max_new_tokens=200,                        # Maximum length for the output text.
+    do_sample=True, top_k=10, temperature=1.0, # Sampling parameters.
+    pad_token_id=tokenizer.eos_token_id,       # Just to avoid a harmless warning.
+)
 
-decoded_output = tokenizer.batch_decode(outputs)
-print(decoded_output[0])
+prompt = "Utilisateur: {}\n\nAssistant: ".format(
+    "Qui était le président Français en 1995 ?"
+)
 
+completions = pipeline(prompt, **generation_kwargs)
+for completion in completions:
+    print(prompt + " […]" + completion['generated_text'])
 ```
 
 ## Training Details