Synchronize the file contents updated by the meta-llama official:

tokenizer.json:
Update post-processor to add bos
generation_config.json:
Update generation_config.json
README.md:
Update widget inference parameters

README.md

@@ -189,6 +189,29 @@ extra_gated_fields:
   By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox
 extra_gated_description: The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
 extra_gated_button_content: Submit
+widget:
+  - example_title: Hello
+    messages:
+    - role: user
+      content: Hey my name is Julien! How are you?
+  - example_title: Winter holidays
+    messages:
+    - role: system
+      content: You are a helpful and honest assistant. Please, respond concisely and truthfully.
+    - role: user
+      content: Can you recommend a good destination for Winter holidays?
+  - example_title: Programming assistant
+    messages:
+    - role: system
+      content: You are a helpful and honest code and programming assistant. Please, respond concisely and truthfully.
+    - role: user
+      content: Write a function that computes the nth fibonacci number.
+inference:
+  parameters:
+    max_new_tokens: 300
+    stop:
+    - <|end_of_text|>
+    - <|eot_id|>
 ---
 
 ## meta-llama/Meta-Llama-3-8B-Instruct for CTranslate2
@@ -285,11 +308,11 @@ Where to send questions or comments about the model Instructions on how to provi
 
 ## How to use
 
-This repository for use with [CTranslate2](https://github.com/OpenNMT/CTranslate2).
+This repository for use with `[CTranslate2](https://github.com/OpenNMT/CTranslate2)`.
 
 ### Use with CTranslate2
 
-This example code is obtained from [CTranslate2_transformers](https://opennmt.net/CTranslate2/guides/transformers.html#mpt) and [tokenizer AutoTokenizer](https://huggingface.co/docs/transformers/main_classes/tokenizer).  
+This example code is obtained from [CTranslate2_transformers](https://opennmt.net/CTranslate2/guides/transformers.html#mpt). 
 More detailed information about the `generate_batch` methon can be found at [CTranslate2_Generator.generate_batch](https://opennmt.net/CTranslate2/python/ctranslate2.Generator.html#ctranslate2.Generator.generate_batch).
 
 ```python
@@ -297,31 +320,14 @@ import ctranslate2
 import transformers
 
 model_id = "avans06/Meta-Llama-3-8B-Instruct-ct2-int8_float16"
-model = ctranslate2.Generator(model_id, device="auto", compute_type="int8_float16")
+generator = ctranslate2.Generator(model_id, device="auto", compute_type="int8_float16")
 tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
 
-messages = [
-    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
-    {"role": "user", "content": "Who are you?"},
-]
+prompt = "What is the meaning of Large language model?"
+input_tokens = tokenizer.convert_ids_to_tokens(tokenizer.encode(prompt))
 
-input_ids = tokenizer.apply_chat_template(
-    messages, 
-    tokenize=False, 
-    add_generation_prompt=True
-)
-
-terminators = [
-    tokenizer.eos_token_id,
-    tokenizer.convert_tokens_to_ids("<|eot_id|>")
-]
-
-input_tokens = tokenizer.convert_ids_to_tokens(tokenizer.encode(input_ids))
-
-results = model.generate_batch([input_tokens], include_prompt_in_result=False, max_length=256, sampling_temperature=0.6, sampling_topp=0.9, end_token=terminators)
+results = generator.generate_batch([input_tokens], include_prompt_in_result=False)
 output = tokenizer.decode(results[0].sequences_ids[0])
-
-print(output)
 ```
 
 ## Hardware and Software

config.json

@@ -3,5 +3,5 @@
   "eos_token": "<|end_of_text|>",
   "layer_norm_epsilon": 1e-05,
   "multi_query_attention": true,
-  "unk_token": "<unk>"
+  "unk_token": ""
 }

generation_config.json

@@ -1,6 +1,9 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 128000,
   "eos_token_id": [128001, 128009],
+  "do_sample": true,
+  "temperature": 0.6,
+  "max_length": 4096,
+  "top_p": 0.9,
   "transformers_version": "4.40.0.dev0"
 }

tokenizer.json

@@ -2329,10 +2329,69 @@
     ]
   },
   "post_processor": {
-    "type": "ByteLevel",
-    "add_prefix_space": true,
-    "trim_offsets": false,
-    "use_regex": true
+    "type": "Sequence",
+    "processors": [
+      {
+        "type": "ByteLevel",
+        "add_prefix_space": true,
+        "trim_offsets": false,
+        "use_regex": true
+      },
+      {
+        "type": "TemplateProcessing",
+        "single": [
+          {
+            "SpecialToken": {
+              "id": "<|begin_of_text|>",
+              "type_id": 0
+            }
+          },
+          {
+            "Sequence": {
+              "id": "A",
+              "type_id": 0
+            }
+          }
+        ],
+        "pair": [
+          {
+            "SpecialToken": {
+              "id": "<|begin_of_text|>",
+              "type_id": 0
+            }
+          },
+          {
+            "Sequence": {
+              "id": "A",
+              "type_id": 0
+            }
+          },
+          {
+            "SpecialToken": {
+              "id": "<|begin_of_text|>",
+              "type_id": 1
+            }
+          },
+          {
+            "Sequence": {
+              "id": "B",
+              "type_id": 1
+            }
+          }
+        ],
+        "special_tokens": {
+          "<|begin_of_text|>": {
+            "id": "<|begin_of_text|>",
+            "ids": [
+              128000
+            ],
+            "tokens": [
+              "<|begin_of_text|>"
+            ]
+          }
+        }
+      }
+    ]
   },
   "decoder": {
     "type": "ByteLevel",