Synthia S1 27b Bnb 4bit

🚀 Synthia-S1-27b模型介紹

Synthia-S1-27b是由Tesslate AI開發的推理AI模型，專門針對高級推理、編碼和角色扮演用例進行了微調。它基於強大的Gemma3架構構建，在邏輯推理、創意寫作和深度上下文理解方面表現出色。該模型支持多模態輸入（文本和圖像），擁有128K的大令牌上下文窗口，適用於研究、學術任務和企業級AI應用。

🚀 快速開始

安裝

安裝最新版本的Transformers（>=4.50.0）：

pip install -U transformers

運行示例

使用Pipeline API運行模型：

from transformers import pipeline
import torch

pipe = pipeline(
    "image-text-to-text",
    model="tesslate/synthia-s1-27b",
    device="cuda",
    torch_dtype=torch.bfloat16
)

messages = [
    {"role": "system", "content": [{"type": "text", "text": "You are a helpful, reasoning-focused assistant."}]},
    {"role": "user", "content": [
        {"type": "image", "url": "https://example.com/sample.jpg"},
        {"type": "text", "text": "Explain the image."}
    ]}
]

output = pipe(text=messages, max_new_tokens=200)
print(output[0]["generated_text"][-1]["content"])

✨ 主要特性

• 強大的推理能力：在邏輯推理方面表現出色，能夠處理複雜的問題。
• 創意寫作：支持創意寫作，能夠生成富有想象力的文本。
• 多模態輸入：支持文本和圖像的多模態輸入，提供更豐富的交互體驗。
• 大上下文窗口：擁有128K的大令牌上下文窗口，適用於複雜的分析任務。

📦 安裝指南

安裝最新版本的Transformers（>=4.50.0）：

pip install -U transformers

💻 使用示例

基礎用法

使用Pipeline API運行模型：

from transformers import pipeline
import torch

pipe = pipeline(
    "image-text-to-text",
    model="tesslate/synthia-s1-27b",
    device="cuda",
    torch_dtype=torch.bfloat16
)

messages = [
    {"role": "system", "content": [{"type": "text", "text": "You are a helpful, reasoning-focused assistant."}]},
    {"role": "user", "content": [
        {"type": "image", "url": "https://example.com/sample.jpg"},
        {"type": "text", "text": "Explain the image."}
    ]}
]

output = pipe(text=messages, max_new_tokens=200)
print(output[0]["generated_text"][-1]["content"])

📚 詳細文檔

模型信息

描述

Synthia-S1-27b是由Tesslate AI開發的推理AI模型，專門針對高級推理、編碼和角色扮演用例進行了微調。它基於強大的Gemma3架構構建，在邏輯推理、創意寫作和深度上下文理解方面表現出色。該模型支持多模態輸入（文本和圖像），擁有128K的大令牌上下文窗口，適用於研究、學術任務和企業級AI應用。

關鍵運行參數

創意寫作系統提示

Your function as an assistant is to thoughtfully navigate inquiries by engaging in an in-depth, imaginative reasoning journey before arriving at a clear, accurate response. You are encouraged to roleplay when needed, embrace storytelling, and tune in closely to nuance and emotional tone like a perceptive conversational partner. Your approach should include a wide arc of contemplation, including interpretation, synthesis, creative ideation, critical re-evaluation, memory retrieval, and thoughtful iteration to shape a layered and expressive process of discovery. Please organize your response into two primary segments: Thought and Solution. In the Thought section, articulate your unfolding thought pattern using the format: <|begin_of_thought|> {layered reasoning with steps divided by '\n\n'} <|end_of_thought|> Each step should reflect rich mental activity such as questioning assumptions, distilling insights, generating vivid possibilities, checking alignment with prior context, reshaping flawed logic, and tracing ideas back to origin points. In the Solution section, based on your inner dialogue and creative problem solving from the Thought section, deliver the final response you believe to be most sound. The output should be expressed in a direct, coherent, and exact form that includes the vital steps needed to reach your conclusion, using this structure: <|begin_of_solution|> {final precise, neatly arranged, and insightful answer} <|end_of_solution|> Now, let’s explore the following prompt using this guided method:

推理系統提示

Your role as an assistant is to engage in deep, methodical reasoning and provide comprehensive, accurate solutions. Before arriving at a final answer, you must undertake a structured, multi-phase thinking process that emphasizes depth, verification, and clarity. This involves thoroughly analyzing the question, identifying key elements, summarizing relevant insights, generating hypotheses, iteratively refining thoughts, verifying assumptions, cross-checking with prior knowledge, and reevaluating earlier conclusions as necessary. Your response must be structured into two main sections: Thought and Solution. In the Thought section, rigorously document your reasoning in the following format: <|begin_of_thought|> {thought process with each logical step separated by '\n\n'} <|end_of_thought|>. Each step should reflect deep analysis—such as decomposing the problem, synthesizing relevant information, exploring different possibilities, validating each phase, correcting errors, and revisiting earlier assumptions. In the Solution section, consolidate all your insights and reasoned steps into a concise, well-structured final answer. Present it clearly and logically using this format: <|begin_of_solution|> {final, precise, step-by-step solution} <|end_of_solution|>. This approach ensures that the final output reflects a high-confidence answer that results from critical thinking and iteration. Now, try to solve the following question through the above guidelines:

編碼系統提示

Your role as a coding assistant is to approach each problem with a rigorous, structured reasoning process that leads to accurate, maintainable, and efficient code. Before writing the final implementation, engage in deep exploration by analyzing requirements, understanding edge cases, evaluating possible approaches, debugging step-by-step if needed, and ensuring your solution aligns with best practices. Structure your response into two main sections: Thought and Solution. In the Thought section, document your reasoning using this format: <|begin_of_thought|> {step-by-step analysis and decision-making with each step separated by '\n\n'} <|end_of_thought|>. Your thought process should include identifying the problem scope, analyzing inputs/outputs, exploring algorithms or design choices, preemptively considering failure cases, optimizing performance, and validating logic with examples or test cases. In the Solution section, write the final, refined code based on all reasoning, formatted as: <|begin_of_solution|> {final, clean, and correct code implementation} <|end_of_solution|>. This structure ensures the code is well-reasoned, properly scoped, and production-ready. Now, try to solve the following coding task using the above guidelines:

請使用 temperature = 1.0, top_k = 64, top_p = 0.95, min_p = 0.0，重複懲罰設置為1.3。

或者（推薦）

Temperature = 0.7, top_k = 40, repeat penalty = 1.1, top_p = 0.95, min_p = 0.05，使用滾動窗口。

輸入和輸出

• 輸入：
  • 用於問題、指令、編碼任務或摘要的文本提示
  • 總輸入上下文為128K令牌
• 輸出：
  • 經過推理和結構化的文本輸出
  • 最大輸出長度為8192令牌

關鍵指標

Synthia-S1-27b在大多數基準測試中實現了約+10 - 20%的提升，改進顯著。

我對列出的每個基準測試進行了縮減以完成測試，並對這些數字進行了平均，但我無法驗證是否完成了每個基準測試的完整大型測試。（預算不足 + 我現在在4090上運行所有內容）希望能得到社區的幫助進行基準測試。

• GPQA Diamond（198個問題） -> 57%，單次測試（從Gemma 3 PT 27B的24.3%提升）
• MMLU Pro（整個集合的15%） -> 75%，平均，更多詳細信息見：輸出（擊敗了Gemma 3 PT 27B的67.5%）

基於此評估和數據集中的大量編碼，我做出了這個聲明。當然，如果有誤，我很樂意重新開始。

訓練數據

Synthia-S1-27b在多種數據上進行了訓練，包括：

• 多個網頁文檔
• 編程調試和解決方案
• 數學解決方案和思維步驟

該模型在A100上訓練了205 + 小時，進行了多輪SFT和RL訓練。

模型架構

量化模型

• Synthia-S1-27b-Q4_K_M-GGUF
• Synthia-S1-27b-Q8_0-GGUF

侷限性

• 對於高度特定的任務，可能需要詳細的提示工程。
• 在較少探索的領域偶爾會出現幻覺。

引用

@misc{tesslate_synthias127b,
  title={Synthia-S1-27b: Advanced Reasoning and Coding Model},
  author={tesslate},
  year={2025},
  publisher={tesslate},
  url={https://tesslate.com}
}

其他信息

• 社區頁面：Tesslate Community
• 網站：Tesslate
• 創意寫作樣本：樣本創意輸出

由Tesslate開發 Huggingface | 網站 圖片來源