Upload tokenizer

README.md

@@ -1,25 +1,27 @@
 ---
-extra_gated_heading: Access Llama 2 on Hugging Face
-extra_gated_description: >-
-  This is a form to enable access to Llama 2 on Hugging Face after you have been
-  granted access from Meta. Please visit the [Meta website](https://ai.meta.com/resources/models-and-libraries/llama-downloads) and accept our
-  license terms and acceptable use policy before submitting this form. Requests
-  will be processed in 1-2 days.
-extra_gated_prompt: "**Your Hugging Face account email address MUST match the email you provide on the Meta website, or your request will not be approved.**"
-extra_gated_button_content: Submit
-extra_gated_fields:
-  I agree to share my name, email address and username with Meta and confirm that I have already been granted download access on the Meta website: checkbox
 language:
 - en
-pipeline_tag: text-generation
-inference: false
-arxiv: 2307.09288
 tags:
 - facebook
 - meta
 - pytorch
 - llama
 - llama-2
+extra_gated_heading: Access Llama 2 on Hugging Face
+extra_gated_description: This is a form to enable access to Llama 2 on Hugging Face
+  after you have been granted access from Meta. Please visit the [Meta website](https://ai.meta.com/resources/models-and-libraries/llama-downloads)
+  and accept our license terms and acceptable use policy before submitting this form.
+  Requests will be processed in 1-2 days.
+extra_gated_prompt: '**Your Hugging Face account email address MUST match the email
+  you provide on the Meta website, or your request will not be approved.**'
+extra_gated_button_content: Submit
+extra_gated_fields:
+  ? I agree to share my name, email address and username with Meta and confirm that
+    I have already been granted download access on the Meta website
+  : checkbox
+pipeline_tag: text-generation
+inference: false
+arxiv: 2307.09288
 ---
 # **Llama 2**
 Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom.

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'function_metadata' %}LLaMA Correct User: You have access to the following functions. Use them if required:\n\n{{ message['content'] }}\n\n{% elif message['role'] == 'user'  and loop.index0 == 1 %}{{ message['content'] }}{{ eos_token }}GPT4 Correct Assistant:\n\n{% elif message['role'] == 'assistant' %}{{ message['content'] }}{{ eos_token }}GPT4 Correct User: {% elif message['role'] == 'function_call' %}Function call: {{ message['content'] }}{{ eos_token }}GPT4 Correct User: {% elif message['role'] == 'function_response' %}Here is the response to the function call. If helpful, use it to respond to my question/request:\n\n{{ message['content'] }}{{ eos_token }}GPT4 Correct Assistant:\n\n{% elif message['role'] == 'user'  and loop.index0 != 1 %}{{ message['content'] }}{{ eos_token }}LLaMA Correct Assistant:\n\n{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}