microsoft / microsoft/foundry-dev-tools

frequency_penalty at 0 causes no response content with Phi-3-mini-4k-cpu-int4-rtn-block-32-acc-level-4-onnx

Open
#90 2 comments 0 reactions 1 assignee View on GitHub

@a1exwang is already working on this.

Since Aug 23, 2024.

bug
Dominant language
JavaScript
Stars
2.1k
Forks
260
Avg merge
42m
Merged PRs (30d)
29

Description

Frequency response at 0 causes an issue with no content in the response. > 0 by < 1 cause other weird responses. 1 seems to be the only reliable value and its unclear if its the model or something else.

POST http://127.0.0.1:5272/v1/chat/completions
content-type: application/json

{
    "messages": [
        {
            "role": "user",
            "content": "Whats the golden ratio"
        }
    ],
    "frequency_penalty": 0,
    "model": "Phi-3-mini-4k-cpu-int4-rtn-block-32-acc-level-4-onnx"
}

You will get a response like:

{
  "model": null,
  "choices": [
    {
      "delta": {
        "role": "assistant",
        "content": "",
        "name": null,
        "tool_call_id": null,
        "function_call": null,
        "tool_calls": null
      },
      "message": {
        "role": "assistant",
        "content": "",
        "name": null,
        "tool_call_id": null,
        "function_call": null,
        "tool_calls": null
      },
      "index": 0,
      "finish_reason": "stop",
      "finish_details": null,
      "logprobs": null
    }
  ],
  "usage": null,
  "created": 1724095112,
  "id": "chat.id.2641",
  "system_fingerprint": null,
  "object": "chat.completion",
  "Successful": true,
  "error": null,
  "HttpStatusCode": 0,
  "HeaderValues": null
}

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.