RichardErkhov/deepseek-ai_-_deepseek-coder-7b-instruct-v1.5-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

deepseek-coder-7b-instruct-v1.5 - GGUF

• Model creator: https://huggingface.co/deepseek-ai/
• Original model: https://huggingface.co/deepseek-ai/deepseek-coder-7b-instruct-v1.5/

Name	Quant method	Size
deepseek-coder-7b-instruct-v1.5.Q2_K.gguf	Q2_K	2.53GB
deepseek-coder-7b-instruct-v1.5.IQ3_XS.gguf	IQ3_XS	2.79GB
deepseek-coder-7b-instruct-v1.5.IQ3_S.gguf	IQ3_S	2.92GB
deepseek-coder-7b-instruct-v1.5.Q3_K_S.gguf	Q3_K_S	2.92GB
deepseek-coder-7b-instruct-v1.5.IQ3_M.gguf	IQ3_M	3.06GB
deepseek-coder-7b-instruct-v1.5.Q3_K.gguf	Q3_K	3.22GB
deepseek-coder-7b-instruct-v1.5.Q3_K_M.gguf	Q3_K_M	3.22GB
deepseek-coder-7b-instruct-v1.5.Q3_K_L.gguf	Q3_K_L	3.49GB
deepseek-coder-7b-instruct-v1.5.IQ4_XS.gguf	IQ4_XS	3.56GB
deepseek-coder-7b-instruct-v1.5.Q4_0.gguf	Q4_0	3.73GB
deepseek-coder-7b-instruct-v1.5.IQ4_NL.gguf	IQ4_NL	3.74GB
deepseek-coder-7b-instruct-v1.5.Q4_K_S.gguf	Q4_K_S	3.75GB
deepseek-coder-7b-instruct-v1.5.Q4_K.gguf	Q4_K	3.93GB
deepseek-coder-7b-instruct-v1.5.Q4_K_M.gguf	Q4_K_M	3.93GB
deepseek-coder-7b-instruct-v1.5.Q4_1.gguf	Q4_1	4.1GB
deepseek-coder-7b-instruct-v1.5.Q5_0.gguf	Q5_0	4.48GB
deepseek-coder-7b-instruct-v1.5.Q5_K_S.gguf	Q5_K_S	4.48GB
deepseek-coder-7b-instruct-v1.5.Q5_K.gguf	Q5_K	4.59GB
deepseek-coder-7b-instruct-v1.5.Q5_K_M.gguf	Q5_K_M	4.59GB
deepseek-coder-7b-instruct-v1.5.Q5_1.gguf	Q5_1	4.86GB
deepseek-coder-7b-instruct-v1.5.Q6_K.gguf	Q6_K	5.28GB

Original model description:

license: other license_name: deepseek license_link: LICENSE

[🏠Homepage] | [🤖 Chat with DeepSeek Coder] | [Discord] | [Wechat(微信)]

---

1. Introduction of Deepseek-Coder-7B-Instruct v1.5

Deepseek-Coder-7B-Instruct-v1.5 is continue pre-trained from Deepseek-LLM 7B on 2T tokens by employing a window size of 4K and next token prediction objective, and then fine-tuned on 2B tokens of instruction data.

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

2. Evaluation Results

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-7b-instruct-v1.5", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-7b-instruct-v1.5", trust_remote_code=True).cuda()
messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)

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=tokenizer.eos_token_id)
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 [email protected].