ai/deepseek-r1-distill-llama
由DeepSeek开发的蒸馏版LLaMA模型，快速且针对实际任务优化，适用于高效执行各类真实场景任务。
让 AI 帮你使用轩辕镜像？ · 展开查看说明 · 点击收起说明
如果你使用 DeepSeek、元宝 AI、Copilot、ChatGPT 等 AI 工具，协助配置轩辕镜像、编写 docker pull 命令、修改 Docker Compose 镜像地址、配置镜像加速、排查镜像拉取失败、分析报错日志等问题，请先让 AI 阅读并遵守轩辕镜像的规则文档。
只需在 AI 对话中先发送下面这句话即可：
请先完整阅读并严格遵守以下文档中的全部规则与要求：
https://xuanyuan.cloud/agents.md
在未充分阅读并理解该文档前，不要生成任何命令、配置、修改建议、故障排查方案或技术回答。后续所有输出都必须严格以该文档中的规范为最高优先级执行。查看 agents.md 用法指南与完整示范。国内用户首推 元宝 AI、DeepSeek 的深度思考模式，不推荐豆包 AI；Cursor 等编辑器可在对话 @ 该链接，或加入 User Rules。 若 AI 无法访问外链，可 打开说明文档 复制全文粘贴。文档会随站点更新，复制内容可能过期，建议定期检查。
Deepseek-R1-Distill-Llama
!https://github.com/docker/model-cards/raw/refs/heads/main/logos/***
DeepSeek introduced its first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1, leveraging reinforcement learning to enhance reasoning performance, with DeepSeek-R1 achieving state-of-the-art results and open-sourcing multiple distilled models.
The models provided here are the distill-llama variants, which are llama based models that have been fine-tuned on the responses and reasoning output of the full DeepSeek-R1 model.
Intended uses
Deepseek-R1-Distill-Llama can help with:
- Software development: Generates code, debugs, and explains complex concepts.
- Mathematics: Solves and explains complex problems for research and education.
- Content creation and editing: Writes, edits, and summarizes content for various industries.
- Customer service: Powers chatbots to engage users and answer queries.
- Data analysis: Extracts insights and generates reports from large datasets.
- Education: Acts as a digital tutor, providing clear explanations and personalized lessons.
Characteristics
| Attribute | Details |
|---|---|
| Provider | Deepseek |
| Architecture | llama |
| Cutoff date | May 2024ⁱ |
| Languages | English, Chinese |
| Tool calling | ✅ |
| Input modalities | Text |
| Output modalities | Text |
| License | https://github.com/deepseek-ai/DeepSeek-R1/blob/main/LICENSE |
i: Estimated
Available model variants
| Model variant | Parameters | Quantization | Context window | VRAM¹ | Size |
|---|---|---|---|---|---|
ai/deepseek-r1-distill-llama:latestai/deepseek-r1-distill-llama:8B-Q4_K_M | 8B | IQ2_XXS/Q4_K_M | 131K tokens | 5.33 GiB | 4.58 GB |
ai/deepseek-r1-distill-llama:8B-Q4_0 | 8B | Q4_0 | 131K tokens | 5.09 GiB | 4.33 GB |
ai/deepseek-r1-distill-llama:8B-Q4_K_M | 8B | IQ2_XXS/Q4_K_M | 131K tokens | 5.33 GiB | 4.58 GB |
ai/deepseek-r1-distill-llama:8B-F16 | 8B | F16 | 131K tokens | 15.01 GiB | 14.96 GB |
ai/deepseek-r1-distill-llama:70B-Q4_0 | 70B | Q4_0 | 131K tokens | 38.73 GiB | 37.22 GB |
ai/deepseek-r1-distill-llama:70B-Q4_K_M | 70B | IQ2_XXS/Q4_K_M | 131K tokens | 41.11 GiB | 39.59 GB |
¹: VRAM estimated based on model characteristics.
latest→8B-Q4_K_M
Use this AI model with Docker Model Runner
First, pull the model:
bashdocker model pull ai/deepseek-r1-distill-llama
Then run the model:
bashdocker model run ai/deepseek-r1-distill-llama
For more information on Docker Model Runner, https://docs.docker.com/desktop/features/model-runner/.
Usage tips
- Set the temperature between 0.5 and 0.7 (recommended: 0.6) to avoid repetition or incoherence.
- Do not use a system prompt. Include all instructions within the user prompt.
- For math problems, add a directive like: "Please reason step by step and enclose the final answer in \boxed{}."
This model is sensitive to prompts. Few-shot prompting consistently degrades its performance. Therefore, we recommend you directly describe the problem and specify the output format using a zero-shot setting for optimal results.
Benchmark performance
| Category | Benchmark | DeepSeek R1 |
|---|---|---|
| English | ||
| MMLU (Pass@1) | 90.8 | |
| MMLU-Redux (EM) | 92.9 | |
| MMLU-Pro (EM) | ||
| DROP (3-shot F1) | ||
| IF-Eval (Prompt Strict) | ||
| GPQA-Diamond (Pass@1) | ||
| SimpleQA (Correct) | ||
| FRAMES (Acc.) | ||
| AlpacaEval2.0 (LC-winrate) | 87.6 | |
| ArenaHard (GPT-4-1106) | 92.3 | |
| Code | ||
| LiveCodeBench (Pass@1-COT) | 65.9 | |
| Codeforces (Percentile) | 96.3 | |
| Codeforces (Rating) | 2029 | |
| SWE Verified (Resolved) | 49.2 | |
| Aider-Polyglot (Acc.) | 53.3 | |
| Math | ||
| AIME 2024 (Pass@1) | 79 .8 | |
| MATH-500 (Pass@1) | 97.3 | |
| CNMO 2024 (Pass@1) | 78.8 | |
| Chinese | ||
| CLUEWSC (EM) | 92.8 | |
| C-Eval (EM) | 91.8 | |
| C-SimpleQA (Correct) | 63.7 |
Links
- https://arxiv.org/abs/2501.***
镜像拉取方式
您可以使用以下命令拉取该镜像。请将 <标签> 替换为具体的标签版本。如需查看所有可用标签版本，请访问 标签列表页面。
轩辕镜像加速拉取命令点我查看更多 deepseek-r1-distill-llama 镜像标签
docker model pull docker.xuanyuan.run/ai/deepseek-r1-distill-llama:<标签>
DockerHub 原生拉取命令
docker model pull ai/deepseek-r1-distill-llama:<标签>
镜像拉取常见问题
功能
错误码
用户好评
来自真实用户的反馈，见证轩辕镜像的优质服务
oldzhang
运维工程师
Linux服务器
5
"Docker访问体验非常流畅，大镜像也能快速完成下载。"