server : add_special option for tokenize endpoint (#7059)

examples/server/README.md

@@ -331,7 +331,7 @@ Notice that each `probs` is an array of length `n_probs`.
 
     `content`: Set the text to tokenize.
 
-    Note that a special `BOS` token is never inserted.
+    `add_special`: Boolean indicating if special tokens, i.e. `BOS`, should be inserted.  Default: `false`
 
 - **POST** `/detokenize`: Convert tokens to text.
 

examples/server/server.cpp

@@ -3647,7 +3647,8 @@ int main(int argc, char ** argv) {
 
         std::vector<llama_token> tokens;
         if (body.count("content") != 0) {
-            tokens = ctx_server.tokenize(body["content"], false);
+            const bool add_special = json_value(body, "add_special", false);
+            tokens = ctx_server.tokenize(body["content"], add_special);
         }
         const json data = format_tokenizer_response(tokens);
         return res.set_content(data.dump(), "application/json; charset=utf-8");

examples/server/tests/features/server.feature

@@ -7,6 +7,7 @@ Feature: llama.cpp server
     And   a model file tinyllamas/stories260K.gguf from HF repo ggml-org/models
     And   a model file test-model.gguf
     And   a model alias tinyllama-2
+    And   BOS token is 1
     And   42 as server seed
       # KV Cache corresponds to the total amount of tokens
       # that can be stored across all independent sequences: #4130
@@ -91,7 +92,18 @@ Feature: llama.cpp server
     """
     What is the capital of France ?
     """
-    Then tokens can be detokenize
+    Then tokens can be detokenized
+    And  tokens do not begin with BOS
+
+  Scenario: Tokenize w/ BOS
+    Given adding special tokens
+    When  tokenizing:
+    """
+    What is the capital of Germany?
+    """
+    Then  tokens begin with BOS
+    Given first token is removed
+    Then  tokens can be detokenized
 
   Scenario: Models available
     Given available models

examples/server/tests/features/steps/steps.py

@@ -376,6 +376,11 @@ def step_seed(context, seed):
         context.seed.append(seed)
 
 
+@step('BOS token is {bos:d}')
+def step_bos_token(context, bos):
+    context.bos = bos
+
+
 @step('a prefix prompt')
 def step_prompt_prefix(context):
     context.prompt_prefix = context_text(context)
@@ -656,21 +661,29 @@ async def all_embeddings_are_generated(context):
         assert_embeddings(context.tasks_result.pop().pop())
 
 
+@step('adding special tokens')
+def step_tokenize_set_add_special(context):
+    context.tokenize_add_special = True
+
+
 @step('tokenizing')
 @async_run_until_complete
 async def step_tokenize(context):
     context.tokenized_text = context_text(context)
     async with aiohttp.ClientSession() as session:
+        tokenize_args = {
+            "content": context.tokenized_text,
+        }
+        if getattr(context, 'tokenize_add_special', None) is not None:
+            tokenize_args['add_special'] = context.tokenize_add_special
         async with session.post(f'{context.base_url}/tokenize',
-                                json={
-                                    "content": context.tokenized_text,
-                                }) as response:
+                                json=tokenize_args) as response:
             assert response.status == 200
             tokenize_json = await response.json()
             context.tokens = tokenize_json['tokens']
 
 
-@step('tokens can be detokenize')
+@step('tokens can be detokenized')
 @async_run_until_complete
 async def step_detokenize(context):
     assert len(context.tokens) > 0
@@ -685,6 +698,21 @@ async def step_detokenize(context):
             assert context.tokenized_text == detokenize_json['content'].strip()
 
 
+@step('tokens begin with BOS')
+def step_strings_for_tokenization(context):
+    assert context.tokens[0] == context.bos
+
+
+@step('tokens do not begin with BOS')
+def step_strings_for_tokenization(context):
+    assert context.tokens[0] != context.bos
+
+
+@step('first token is removed')
+def step_strings_for_tokenization(context):
+    context.tokens = context.tokens[1:]
+
+
 @step('an OPTIONS request is sent from {origin}')
 @async_run_until_complete
 async def step_options_request(context, origin):