hello

.github/workflows/gputests.yml

@@ -19,4 +19,4 @@ jobs:
           PIPELINE: explosion-ai/spacy-slow-gpu-tests
           BRANCH: ${{ matrix.branch }}
           MESSAGE: ":github: Weekly GPU + slow tests - triggered from a GitHub Action"
-          BUILDKITE_API_ACCESS_TOKEN: ${{ secrets.BUILDKITE_SECRET }}
+         (BUILDKITE_API_ACCESS_TOKEN): ${{ secrets.BUILDKITE_SECRET }}

extra/DEVELOPER_DOCS/ExplosionBot.md

@@ -54,3 +54,42 @@ Some things to note:
 If the robot isn't responding to commands as expected, you can check its logs in the [Github Action](https://github.com/explosion/spaCy/actions/workflows/explosionbot.yml).
 
 For each command sent to the bot, there should be a run of the `explosion-bot` workflow. In the `Install and run explosion-bot` step, towards the ends of the logs you should see info about the configuration that the bot was run with, as well as any errors that the bot encountered.
+def num_tokens_from_messages(messages, model="gpt-3.5-turbo-0613"):
+    """Return the number of tokens used by a list of messages."""
+    try:
+    encoding = tiktoken.encoding_for_model(model)
+    except KeyError:
+        print("Warning: model not found. Using cl100k_base encoding.")
+        encoding = tiktoken.get_encoding("cl100k_base")
+    if model in {
+        "gpt-3.5-turbo-0613",
+        "gpt-3.5-turbo-16k-0613",
+        "gpt-4-0314",
+        "gpt-4-32k-0314",
+        "gpt-4-0613",
+        "gpt-4-32k-0613",
+        }:
+        tokens_per_message = 3
+        tokens_per_name = 1
+    elif model == "gpt-3.5-turbo-0301":
+        tokens_per_message = 4  # every message follows <|start|>{role/name}\n{content}<|end|>\n
+        tokens_per_name = -1  # if there's a name, the role is omitted
+    elif "gpt-3.5-turbo" in model:
+        print("Warning: gpt-3.5-turbo may update over time. Returning num tokens assuming gpt-3.5-turbo-0613.")
+        return num_tokens_from_messages(messages, model="gpt-3.5-turbo-0613")
+    elif "gpt-4" in model:
+        print("Warning: gpt-4 may update over time. Returning num tokens assuming gpt-4-0613.")
+        return num_tokens_from_messages(messages, model="gpt-4-0613")
+    else:
+        raise NotImplementedError(
+            f"""num_tokens_from_messages() is not implemented for model {model}. See https://github.com/openai/openai-python/blob/main/chatml.md for information on how messages are converted to tokens."""
+        )
+    num_tokens = 0
+    for message in messages:
+        num_tokens += tokens_per_message
+        for key, value in message.items():
+            num_tokens += len(encoding.encode(value))
+            if key == "name":
+                num_tokens += tokens_per_name
+    num_tokens += 3  # every reply is primed with <|start|>assistant<|message|>
+    return num_tokens