Hacktoberfest 2026：維護者為十月標記出來的 issue，仍然開放、適合新手。 瀏覽 Hacktoberfest issue

cannot run fine-tuned gpt-oss model correctly

未關閉
  • 哪裡不對？
#2,054 0 則留言 1 個 reaction 已指派 0 人 在 GitHub 檢視

維護者通常 1 天內回覆

還沒有人認領這個 Issue。

評估

難度
4/5
預估耗時
3-5 天
新手友好度
25/100
Issue 類型
缺陷
描述清晰度
需要釐清
活躍度
停滯
技術堆疊
python
領域
ai, backend-api-design, machine-learning

研究方向

該 issue 回報了一個 fine-tuned GPT 模型相較於 llama.cpp 輸出不正確的問題。使用者提供了模型路徑和呼叫程式碼。先檢查 llama-cpp-python bindings 中 LlamaCpp 類別的初始化和 invoke 方法。將輸出格式與 token 處理和原生 llama.cpp 的行為進行比較。檢查該 issue 是否與 'harmony format' 或 fine-tuned 模型的特定載入細節有關。使用提供的模型和 prompt 重現錯誤，以查看不一致的輸出。

由索引模型根據 Issue 內容生成。

描述

Expected Behavior

Should produce the similar output format as llamacpp

Current Behavior

The output is wrong. Maybe related to the harmony format?

The current output of llamacpp-python:
Answer: weak
Llama.generate: 7 prefix-match hit, remaining 1 prompt tokens to eval
form, also known as variational form or integrated form, is a reformulation of a differential equation that involves integrals rather than derivatives.

Question: what is strong form
Answer: strong form, also known as the standard form or classical form, is a formulation of a partial differential equation in which all terms involve derivatives.

Yes, what is weak solution? how to set of a) to b)
how
for

theorem
How do you like
of
Questionary

To solve

Sure

What if
question: strong form

(what is the strong form


# Environment and Context

Please provide detailed information about your computer setup. This is important in case the issue is not reproducible except for under certain specific conditions.

* Physical (or virtual) hardware you are using, e.g. for Linux:

`$ lscpu`

Architecture:                       x86_64
CPU op-mode(s):                     32-bit, 64-bit
Byte Order:                         Little Endian
Address sizes:                      48 bits physical, 48 bits virtual
CPU(s):                             96
On-line CPU(s) list:                0-95
Thread(s) per core:                 2
Core(s) per socket:                 24
Socket(s):                          2
NUMA node(s):                       2
Vendor ID:                          AuthenticAMD
CPU family:                         25
Model:                              1
Model name:                         AMD EPYC 7413 24-Core Processor
Stepping:                           1
Frequency boost:                    enabled
CPU MHz:                            1498.207
CPU max MHz:                        2650.0000
CPU min MHz:                        1500.0000
BogoMIPS:                           5299.85
Virtualization:                     AMD-V
L1d cache:                          1.5 MiB
L1i cache:                          1.5 MiB
L2 cache:                           24 MiB
L3 cache:                           256 MiB
NUMA node0 CPU(s):                  0-23,48-71
NUMA node1 CPU(s):                  24-47,72-95


* Operating System, e.g. for Linux:

`$ uname -a`


Linux athena 5.4.0-176-generic #196-Ubuntu SMP Fri Mar 22 16:46:39 UTC 2024 x86_64 x86_64 x86_64 GNU/Linux

* SDK version, e.g. for Linux:

$ python3 --version
Python 3.10.18
$ make --version
GNU Make 4.2.1
$ g++ --version
g++ (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0


# Failure Information (for bugs)

Just call the model, didn't produce the correct result. But llammacpp works well, give me the correct output.

# Steps to Reproduce

Please provide detailed steps for reproducing the issue. We are not sitting in front of your screen, so the more detail the better.

# Make sure the model path is correct for your system!
llm = LlamaCpp(
    model_path="/mnt/a/jgz1751/finetune/step8GGUF/gguf/Model_Final-32x2.4B-Q8_0.gguf",
    temperature=0.75,
    max_tokens=2000,
    top_p=1,
    callback_manager=callback_manager,
    verbose=True,  # Verbose is required to pass to the callback manager
)


question = """
Question: what is weak form
"""
llm.invoke(question)
主要語言
Python
星號
10.6k
分支
1.5k
平均合併
5 小時 9 分鐘
30 天內合併 PR
3

環境準備

  • 沒有 Dockerfile 或 Docker Compose 檔案
  • 沒有 Pull Request 範本
  • 閱讀貢獻指南

從這裡開始

  1. 先讀完整個 Issue，再讀專案的貢獻指南。
  2. 在 Issue 下留言說明你要接手 —— 這能避免兩個人做同樣的事。
  3. Fork 儲存庫，在一個分支上完成修改。
  4. 送出 Pull Request，並在描述裡引用這個 Issue 編號。

abetlen/llama-cpp-python 的其他 Issue

查看 abetlen/llama-cpp-python 的全部 Issue

相似的 Issue

更多 Python Issue

把新 issue 寄到你的電子郵件信箱

精選適合新手參與的 GitHub issue 摘要。