commit dbf1b15997040809c8ea60fb34a921ad69f3fb6f Author: ModelHub XC Date: Fri Sep 18 11:52:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: dnotitia/Llama-DNA-1.0-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/Llama-DNA-1.0-8B-Instruct-F16.gguf b/Llama-DNA-1.0-8B-Instruct-F16.gguf new file mode 100644 index 0000000..3ba565d --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35d3dea88f8c048b5db569e691a6523824ac016f1b1bb9bac219dd7cf35baf76 +size 16068892000 diff --git a/Llama-DNA-1.0-8B-Instruct-F32.gguf b/Llama-DNA-1.0-8B-Instruct-F32.gguf new file mode 100644 index 0000000..ed20ab0 --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct-F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59204a4fa994d61322beb2fde6253545ac1d37f4b43e2dff0a87b6b034a3e0a1 +size 32128882016 diff --git a/Llama-DNA-1.0-8B-Instruct-Q2_K.gguf b/Llama-DNA-1.0-8B-Instruct-Q2_K.gguf new file mode 100644 index 0000000..23d7dd9 --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:006ac7c1e6b62445f2086c488654c40b7daf37cb7579a2b57a20dba3282e3e64 +size 3179132256 diff --git a/Llama-DNA-1.0-8B-Instruct-Q3_K.gguf b/Llama-DNA-1.0-8B-Instruct-Q3_K.gguf new file mode 100644 index 0000000..3bd72a1 --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct-Q3_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81d0eb503fffd2eb862fc1dd4fb4bac56d6e06a7245d55b067750cb9fdee4ff6 +size 4018918752 diff --git a/Llama-DNA-1.0-8B-Instruct-Q4_K.gguf b/Llama-DNA-1.0-8B-Instruct-Q4_K.gguf new file mode 100644 index 0000000..c3f2296 --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct-Q4_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:523a996b78ef79f16ffacf351d9f32dbb417bea939457d5a2c67da1d5934b9c2 +size 4920735072 diff --git a/Llama-DNA-1.0-8B-Instruct-Q5_K.gguf b/Llama-DNA-1.0-8B-Instruct-Q5_K.gguf new file mode 100644 index 0000000..bf20ac3 --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct-Q5_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a35fb0eb2a073ebde31f3ba01123e67fc781a8cabb3b1d4b7290cafaf5807d1 +size 5732988256 diff --git a/Llama-DNA-1.0-8B-Instruct-Q6_K.gguf b/Llama-DNA-1.0-8B-Instruct-Q6_K.gguf new file mode 100644 index 0000000..bb600bf --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1192bf27bfad530f74b6fdcf3662bbc610805538da563a840b18ae62c8798cc0 +size 6596007264 diff --git a/Llama-DNA-1.0-8B-Instruct-Q8_0.gguf b/Llama-DNA-1.0-8B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..929c312 --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e317d769dc3161e254a928809e4f64e1cfaa49a544e91649f899a820354b4b0 +size 8540771680 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e69280c --- /dev/null +++ b/README.md @@ -0,0 +1,99 @@ +--- +language: +- en +- ko +license: cc-by-nc-4.0 +tags: +- dnotitia +- nlp +- llm +- slm +- conversation +- chat +- gguf +base_model: +- dnotitia/Llama-DNA-1.0-8B-Instruct +library_name: transformers +pipeline_tag: text-generation +--- + +# DNA 1.0 8B Instruct GGUF + +

+ +

+ +**DNA 1.0 8B Instruct** is a state-of-the-art (**SOTA**) bilingual language model based on Llama architecture, specifically optimized for Korean language understanding and generation, while also maintaining strong English capabilities. The model was developed through a sophisticated process involving model merging via spherical linear interpolation (**SLERP**) with Llama 3.1 8B Instruct, and underwent knowledge distillation (**KD**) using Llama 3.1 405B as the teacher model. It was extensively trained through continual pre-training (**CPT**) with a high-quality Korean dataset. The training pipeline was completed with supervised fine-tuning (**SFT**) and direct preference optimization (**DPO**) to align with human preferences and enhance instruction-following abilities. + +

+ +

+ +## Quickstart + +We offer weights in `F32`, `F16` formats and quantized weights in `Q8_0`, `Q6_K`, `Q5_K`, `Q4_K`, `Q3_K` and `Q2_K` formats. + +You can run GGUF weights with `llama.cpp` as follows: + +1. Install `llama.cpp`. Please refer to the [llama.cpp repository](https://github.com/ggerganov/llama.cpp) for more details. + +2. Download DNA 1.0 8B Instruct model in GGUF format. + +```bash +# Install huggingface_hub if not already installed +$ pip install huggingface_hub[cli] + +# Download the GGUF weights +$ huggingface-cli download dnotitia/Llama-DNA-1.0-8B-Instruct-GGUF \ + --include "Llama-DNA-1.0-8B-Instruct-Q8_0.gguf" \ + --local-dir . +``` + +3. Run the model with `llama.cpp` in conversational mode. + +```bash +$ llama-cli -cnv -m ./Llama-DNA-1.0-8B-Instruct-Q8_0.gguf \ + -p "You are a helpful assistant, Dnotitia DNA." +``` + +## Ollama + +DNA 1.0 8B Instruct model is compatible with Ollama. You can use it as follows: + +1. Install Ollama. Please refer to the [Ollama repository](https://github.com/ollama/ollama) for more details. + +2. Run the [model](https://ollama.com/dnotitia/dna) with Ollama. + +```bash +$ ollama run dnotitia/dna +``` + +## Limitations + +While DNA 1.0 8B Instruct demonstrates strong performance, users should be aware of the following limitations: + +- The model may occasionally generate biased or inappropriate content. +- Responses are based on training data and may not reflect current information. +- The model may sometimes produce factually incorrect or inconsistent answers. +- Performance may vary depending on the complexity and domain of the task. +- Generated content should be reviewed for accuracy and appropriateness. + +## License + +The model is released under the CC BY-NC 4.0 license. For commercial usage inquiries, please [Contact us](https://www.dnotitia.com/contact/post-form). + +## Citation + +If you use or discuss this model in your academic research, please cite the project to help spread awareness: + +``` +@misc{lee2025dna10technicalreport, + title={DNA 1.0 Technical Report}, + author={Jungyup Lee and Jemin Kim and Sang Park and SeungJae Lee}, + year={2025}, + eprint={2501.10648}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2501.10648}, +} +``` \ No newline at end of file diff --git a/assets/dna-logo.png b/assets/dna-logo.png new file mode 100644 index 0000000..238c7fa Binary files /dev/null and b/assets/dna-logo.png differ diff --git a/assets/training-procedure.png b/assets/training-procedure.png new file mode 100644 index 0000000..75ab189 Binary files /dev/null and b/assets/training-procedure.png differ diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file