---

base_model: deepseek-ai/deepseek-coder-6.7b-instruct

inference: false

license: other

license_link: LICENSE

license_name: deepseek

model_creator: DeepSeek

model_name: Deepseek Coder 6.7B Instruct

model_type: deepseek

prompt_template: 'You are an AI programming assistant, utilizing the Deepseek Coder

model, developed by Deepseek Company, and you only answer questions related to computer

science. For politically sensitive questions, security and privacy issues, and other

non-computer science questions, you will refuse to answer.

### Instruction:

{prompt}

### Response:

'

quantized_by: TheBloke

---

FROM: TheBloke/deepseek-coder-6.7B-instruct-GGUF

Deepseek Coder 6.7B Instruct - GGUF

• Model creator: DeepSeek
• Original model: Deepseek Coder 6.7B Instruct

<!-- description start -->

Description

This repo contains GGUF format model files for DeepSeek's Deepseek Coder 6.7B Instruct.

These files were quantised using hardware kindly provided by Massed Compute.

<!-- description end -->

<!-- README_GGUF.md-about-gguf start -->

About GGUF

GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.

Here is an incomplete list of clients and libraries that are known to support GGUF:

• llama.cpp. The source project for GGUF. Offers a CLI and a server option.
• text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
• KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
• LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
• LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
• Faraday.dev, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
• ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
• llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
• candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.

<!-- README_GGUF.md-about-gguf end -->

<!-- repositories-available start -->

Repositories available

• AWQ model(s) for GPU inference.
• GPTQ models for GPU inference, with multiple quantisation parameter options.
• 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference
• DeepSeek's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

<!-- repositories-available end -->

<!-- prompt-template start -->

Prompt template: DeepSeek

You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.
### Instruction:
{prompt}
### Response:

<!-- prompt-template end -->

<!-- compatibility_gguf start -->

Compatibility

These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit d0cee0d

They are also compatible with many third party UIs and libraries - please see the list at the top of this README.

Explanation of quantisation methods

<details>

<summary>Click to see details</summary>

The new methods available are:

• GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
• GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
• GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
• GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
• GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw

Refer to the Provided Files table below to see what files use which methods, and how.

</details>

<!-- compatibility_gguf end -->

<!-- README_GGUF.md-provided-files start -->

Provided files

| Name | Quant method | Bits | Size | Max RAM required | Use case |

| ---- | ---- | ---- | ---- | ---- | ----- |

| deepseek-coder-6.7b-instruct.Q2_K.gguf | Q2_K | 2 | 2.83 GB| 5.33 GB | smallest, significant quality loss - not recommended for most purposes |

| deepseek-coder-6.7b-instruct.Q3_K_S.gguf | Q3_K_S | 3 | 2.95 GB| 5.45 GB | very small, high quality loss |

| deepseek-coder-6.7b-instruct.Q3_K_M.gguf | Q3_K_M | 3 | 3.30 GB| 5.80 GB | very small, high quality loss |

| deepseek-coder-6.7b-instruct.Q3_K_L.gguf | Q3_K_L | 3 | 3.60 GB| 6.10 GB | small, substantial quality loss |

| deepseek-coder-6.7b-instruct.Q4_0.gguf | Q4_0 | 4 | 3.83 GB| 6.33 GB | legacy; small, very high quality loss - prefer using Q3_K_M |

| deepseek-coder-6.7b-instruct.Q4_K_S.gguf | Q4_K_S | 4 | 3.86 GB| 6.36 GB | small, greater quality loss |

| deepseek-coder-6.7b-instruct.Q4_K_M.gguf | Q4_K_M | 4 | 4.08 GB| 6.58 GB | medium, balanced quality - recommended |

| deepseek-coder-6.7b-instruct.Q5_0.gguf | Q5_0 | 5 | 4.65 GB| 7.15 GB | legacy; medium, balanced quality - prefer using Q4_K_M |

| deepseek-coder-6.7b-instruct.Q5_K_S.gguf | Q5_K_S | 5 | 4.65 GB| 7.15 GB | large, low quality loss - recommended |

| deepseek-coder-6.7b-instruct.Q5_K_M.gguf | Q5_K_M | 5 | 4.79 GB| 7.29 GB | large, very low quality loss - recommended |

| deepseek-coder-6.7b-instruct.Q6_K.gguf | Q6_K | 6 | 5.53 GB| 8.03 GB | very large, extremely low quality loss |

| deepseek-coder-6.7b-instruct.Q8_0.gguf | Q8_0 | 8 | 7.16 GB| 9.66 GB | very large, extremely low quality loss - not recommended |

Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.

<!-- README_GGUF.md-provided-files end -->

<!-- README_GGUF.md-how-to-download start -->

How to download GGUF files

Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.

The following clients/libraries will automatically download models for you, providing a list of available models to choose from:

• LM Studio
• LoLLMS Web UI
• Faraday.dev

In text-generation-webui

Under Download Model, you can enter the model repo: TheBloke/deepseek-coder-6.7B-instruct-GGUF and below it, a specific filename to download, such as: deepseek-coder-6.7b-instruct.Q4_K_M.gguf.

Then click Download.

On the command line, including multiple files at once

I recommend using the huggingface-hub Python library:

pip3 install huggingface-hub

Then you can download any individual model file to the current directory, at high speed, with a command like this:

huggingface-cli download TheBloke/deepseek-coder-6.7B-instruct-GGUF deepseek-coder-6.7b-instruct.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

<details>

<summary>More advanced huggingface-cli download usage</summary>

You can also download multiple files at once with a pattern:

huggingface-cli download TheBloke/deepseek-coder-6.7B-instruct-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'

For more documentation on downloading with huggingface-cli, please see: HF -> Hub Python Library -> Download files -> Download from the CLI.

To accelerate downloads on fast connections (1Gbit/s or higher), install hf_transfer:

pip3 install hf_transfer

And set environment variable HF_HUB_ENABLE_HF_TRANSFER to 1:

HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/deepseek-coder-6.7B-instruct-GGUF deepseek-coder-6.7b-instruct.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

Windows Command Line users: You can set the environment variable by running set HF_HUB_ENABLE_HF_TRANSFER=1 before the download command.

</details>

<!-- README_GGUF.md-how-to-download end -->

<!-- README_GGUF.md-how-to-run start -->

Example llama.cpp command

Make sure you are using llama.cpp from commit d0cee0d or later.

./main -ngl 32 -m deepseek-coder-6.7b-instruct.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.\n### Instruction:\n{prompt}\n### Response:"

Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.

Change -c 2048 to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.

If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins

For other parameters and how to use them, please refer to the llama.cpp documentation

How to run in text-generation-webui

Further instructions here: text-generation-webui/docs/llama.cpp.md.

How to run from Python code

You can use GGUF models from Python using the llama-cpp-python or ctransformers libraries.

How to load this model in Python code, using ctransformers

First install the package

Run one of the following commands, according to your system:

# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers

Simple ctransformers example code

from ctransformers import AutoModelForCausalLM

# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/deepseek-coder-6.7B-instruct-GGUF", model_file="deepseek-coder-6.7b-instruct.Q4_K_M.gguf", model_type="deepseek", gpu_layers=50)

print(llm("AI is going to"))

How to use with LangChain

Here are guides on using llama-cpp-python and ctransformers with LangChain:

• LangChain + llama-cpp-python
• LangChain + ctransformers

<!-- README_GGUF.md-how-to-run end -->

<!-- footer start -->

<!-- 200823 -->

<!-- footer end -->

<!-- original-model-card start -->

Original model card: DeepSeek's Deepseek Coder 6.7B Instruct

<p align="center">

<img width="1000px" alt="DeepSeek Coder" src="https://github.com/deepseek-ai/DeepSeek-Coder/blob/main/pictures/logo.png?raw=true">

</p>

<p align="center"><a href="https://www.deepseek.com/">[🏠Homepage]</a> | <a href="https://coder.deepseek.com/">[🤖 Chat with DeepSeek Coder]</a> | <a href="https://discord.gg/Tc7c45Zzu5">[Discord]</a> | <a href="https://github.com/guoday/assert/blob/main/QR.png?raw=true">[Wechat(微信)]</a> </p>

<hr>

1. Introduction of Deepseek Coder

Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese. We provide various sizes of the code model, ranging from 1B to 33B versions. Each model is pre-trained on project-level code corpus by employing a window size of 16K and a extra fill-in-the-blank task, to support project-level code completion and infilling. For coding capabilities, Deepseek Coder achieves state-of-the-art performance among open-source code models on multiple programming languages and various benchmarks.

• Massive Training Data: Trained from scratch fon 2T tokens, including 87% code and 13% linguistic data in both English and Chinese languages.

• Highly Flexible & Scalable: Offered in model sizes of 1.3B, 5.7B, 6.7B, and 33B, enabling users to choose the setup most suitable for their requirements.

• Superior Model Performance: State-of-the-art performance among publicly available code models on HumanEval, MultiPL-E, MBPP, DS-1000, and APPS benchmarks.

• Advanced Code Completion Capabilities: A window size of 16K and a fill-in-the-blank task, supporting project-level code completion and infilling tasks.

2. Model Summary

deepseek-coder-6.7b-instruct is a 6.7B parameter model initialized from deepseek-coder-6.7b-base and fine-tuned on 2B tokens of instruction data.

• Home Page: DeepSeek
• Repository: deepseek-ai/deepseek-coder
• Chat With DeepSeek Coder: DeepSeek-Coder

3. How to Use

Here give some examples of how to use our model.

Chat Model Inference

from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-6.7b-instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-6.7b-instruct", trust_remote_code=True).cuda()
messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
# 32021 is the id of <|EOT|> token
outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=32021)
print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))

4. License

This code repository is licensed under the MIT License. The use of DeepSeek Coder models is subject to the Model License. DeepSeek Coder supports commercial use.

See the LICENSE-MODEL for more details.

5. Contact

If you have any questions, please raise an issue or contact us at agi_code@deepseek.com.

<!-- original-model-card end -->