A curated list of open-source projects related to DeepSeek Coder - deepseek-ai/awesome-deepseek-coder
ranging from 1B to 33B versions. Each model is pre-trained on project-level code corpus by employing a window size of 16K and an extra fill-in-the-blank task, to support project-level code completion and infilling. For coding capabilities, DeepSeek Coder achieves state-of-the-art performanc...
当我为deepseek-coder:33b-instruct模型使用时，我必须使用--pad-vocab和--vocab-type = bpe,但看到...
// deepseek-ai/deepseek-coder-33b-instruct for (auto message : chat) { std::string role(message->role); Expand All@@ -22464,7 +22467,7 @@ static int32_t llama_chat_apply_template_internal( if (add_ass) { ss << "### Response:\n"; ...
python3 -m pip install -r requirements.txt # generate GGUF model python convert-hf-to-gguf.py <MODEL_PATH> --outfile <GGUF_PATH> --model-name deepseekcoder # use q4_0 quantization as an example ./quantize <GGUF_PATH> <OUTPUT_PATH> q4_0 ./main -m <OUTPUT_PATH> -n 128 -p ...
python3 -m pip install -r requirements.txt # generate GGUF model python convert-hf-to-gguf.py <MODEL_PATH> --outfile <GGUF_PATH> --model-name deepseekcoder # use q4_0 quantization as an example ./quantize <GGUF_PATH> <OUTPUT_PATH> q4_0 ./main -m <OUTPUT_PATH> -n 128 -p ...
The DeepSeek-Coder-Instruct-33B model after instruction tuning outperforms GPT35-turbo on HumanEval and achieves comparable results with GPT35-turbo on MBPP. More evaluation details can be found in the Detailed Evaluation. 3. Procedure of Data Creation and Model Training Data Creation Step 1: ...
deepseek-coder-6.7B-base-GPTQdeepseek-coder-6.7B-instruct-AWQ deepseek-coder-6.7B-instruct-GGUF deepseek-coder-6.7B-instruct-GPTQ 33Bdeepseek-coder-33B-base-AWQ deepseek-coder-33B-base-GGUF deepseek-coder-33B-base-GPTQdeepseek-coder-33B-instruct-AWQ ...
ranging from 1B to 33B versions. Each model is pre-trained on project-level code corpus by employing a window size of 16K and an extra fill-in-the-blank task, to support project-level code completion and infilling. For coding capabilities, DeepSeek Coder achieves state-of-the-art performanc...
python3 -m pip install -r requirements.txt # generate GGUF model python convert-hf-to-gguf.py <MODEL_PATH> --outfile <GGUF_PATH> --model-name deepseekcoder # use q4_0 quantization as an example ./quantize <GGUF_PATH> <OUTPUT_PATH> q4_0 ./main -m <OUTPUT_PATH> -n 128 -p ...