commit 4a89495f59fb830208d8ee0a179c585ffa3bba4d Author: ModelHub XC Date: Fri Jun 5 22:18:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: osmapi/Nidum-Llama-3.2-3B-Uncensored-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f15b49c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl 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 +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +*.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Nidum-Llama-3.2-3B-Uncensored-F16.gguf b/Nidum-Llama-3.2-3B-Uncensored-F16.gguf new file mode 100644 index 0000000..35aab70 --- /dev/null +++ b/Nidum-Llama-3.2-3B-Uncensored-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:767f7d00431b076da787cf79a9179846a7cfbe4a6d60820d4930ce15c9888459 +size 6433688032 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a7736a4 --- /dev/null +++ b/README.md @@ -0,0 +1,147 @@ +--- +license: apache-2.0 +base_model: +- nidum/Nidum-Llama-3.2-3B-Uncensored +- meta-llama/Llama-3.2-3B +library_name: adapter-transformers +tags: +- chemistry +- biology +- legal +- code +- medical +- finance +- roleplay +- uncensored +- uncensored LLM +pipeline_tag: text-generation +--- + +### Nidum-Llama-3.2-3B-Uncensored + +### Welcome to Nidum! +At Nidum, we believe in pushing the boundaries of innovation by providing advanced and unrestricted AI models for every application. Dive into our world of possibilities and experience the freedom of **Nidum-Llama-3.2-3B-Uncensored**, tailored to meet diverse needs with exceptional performance. + +--- + +[![GitHub Icon](https://upload.wikimedia.org/wikipedia/commons/thumb/9/95/Font_Awesome_5_brands_github.svg/232px-Font_Awesome_5_brands_github.svg.png)](https://github.com/NidumAI-Inc) +**Explore Nidum's Open-Source Projects on GitHub**: [https://github.com/NidumAI-Inc](https://github.com/NidumAI-Inc) + +--- +### Key Features + +1. **Uncensored Responses**: Capable of addressing any query without content restrictions, offering detailed and uninhibited answers. +2. **Versatility**: Excels in diverse use cases, from complex technical queries to engaging casual conversations. +3. **Advanced Contextual Understanding**: Draws from an expansive knowledge base for accurate and context-aware outputs. +4. **Extended Context Handling**: Optimized for handling long-context interactions for improved continuity and depth. +5. **Customizability**: Adaptable to specific tasks and user preferences through fine-tuning. + +--- + +### Use Cases + +- **Open-Ended Q&A** +- **Creative Writing and Ideation** +- **Research Assistance** +- **Educational Queries** +- **Casual Conversations** +- **Mathematical Problem Solving** +- **Long-Context Dialogues** + +--- + +### How to Use + +To start using **Nidum-Llama-3.2-3B-Uncensored**, follow the sample code below: + +```python +import torch +from transformers import pipeline + +pipe = pipeline( + "text-generation", + model="nidum/Nidum-Llama-3.2-3B-Uncensored", + model_kwargs={"torch_dtype": torch.bfloat16}, + device="cuda", # replace with "mps" to run on a Mac device +) + +messages = [ + {"role": "user", "content": "Tell me something fascinating."}, +] + +outputs = pipe(messages, max_new_tokens=256) +assistant_response = outputs[0]["generated_text"][-1]["content"].strip() +print(assistant_response) +``` + +--- +#### Quantized Models Available for Download + +| **Quantized Model Version** | **Description** | +|-------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------| +| [**Nidum-Llama-3.2-3B-Uncensored-F16.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/Nidum-Llama-3.2-3B-Uncensored-F16.gguf) | Full 16-bit floating point precision for maximum accuracy on high-end GPUs. | +| [**model-Q2_K.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q2_K.gguf) | Optimized for minimal memory usage with lower precision, suitable for edge cases.| +| [**model-Q3_K_L.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q3_K_L.gguf) | Balanced precision with enhanced memory efficiency for medium-range devices. | +| [**model-Q3_K_M.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q3_K_M.gguf) | Mid-range quantization for moderate precision and memory usage balance. | +| [**model-Q3_K_S.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q3_K_S.gguf) | Smaller quantization steps, offering moderate precision with reduced memory use.| +| [**model-Q4_0_4_4.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q4_0_4_4.gguf) | Performance-optimized for low memory, ideal for lightweight deployment. | +| [**model-Q4_0_4_8.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q4_0_4_8.gguf) | Extended quantization balancing memory use and inference speed. | +| [**model-Q4_0_8_8.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q4_0_8_8.gguf) | Advanced memory precision targeting larger contexts. | +| [**model-Q4_K_M.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q4_K_M.gguf) | High-efficiency quantization for moderate GPU resources. | +| [**model-Q4_K_S.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q4_K_S.gguf) | Optimized for smaller-scale operations with compact memory footprint. | +| [**model-Q5_K_M.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q5_K_M.gguf) | Balances performance and precision, ideal for robust inferencing environments. | +| [**model-Q5_K_S.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q5_K_S.gguf) | Moderate quantization targeting performance with minimal resource usage. | +| [**model-Q6_K.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-Q6_K.gguf) | High-precision quantization for accurate and stable inferencing tasks. | +| [**model-TQ1_0.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-TQ1_0.gguf) | Experimental quantization for targeted applications in test environments. | +| [**model-TQ2_0.gguf**](https://huggingface.co/nidum/Nidum-Llama-3.2-3B-Uncensored-GGUF/blob/main/model-TQ2_0.gguf) | High-performance tuning for experimental use cases and flexible precision. | + +--- +### Datasets and Fine-Tuning + +The following fine-tuning datasets are leveraged to enhance specific model capabilities: + +- **Uncensored Data**: Enables unrestricted and uninhibited responses. +- **RAG-Based Fine-Tuning**: Optimizes retrieval-augmented generation for knowledge-intensive tasks. +- **Long Context Fine-Tuning**: Enhances the model's ability to process and maintain coherence in extended conversations. +- **Math-Instruct Data**: Specially curated for precise and contextually accurate mathematical reasoning. + +--- + +### Benchmarks + +After fine-tuning with **uncensored data**, **Nidum-Llama-3.2-3B** demonstrates **superior performance compared to the original LLaMA model**, particularly in accuracy and handling diverse, unrestricted scenarios. + +#### Benchmark Summary Table + +| **Benchmark** | **Metric** | **LLaMA 3.2 3B** | **Nidum 3.2 3B** | **Observation** | +|-------------------|-----------------------------------|--------------|--------------|-----------------------------------------------------------------------------------------------------| +| **GPQA** | Exact Match (Flexible) | 0.3 | 0.5 | Nidum 3B demonstrates significant improvement, particularly in **generative tasks**. | +| | Accuracy | 0.4 | 0.5 | Consistent improvement, especially in **zero-shot** scenarios. | +| **HellaSwag** | Accuracy | 0.3 | 0.4 | Better performance in **common sense reasoning** tasks. | +| | Normalized Accuracy | 0.3 | 0.4 | Enhanced ability to understand and predict context in sentence completion. | +| | Normalized Accuracy (Stderr) | 0.15275 | 0.1633 | Slightly improved consistency in normalized accuracy. | +| | Accuracy (Stderr) | 0.15275 | 0.1633 | Shows robustness in reasoning accuracy compared to LLaMA 3B. | + +--- + +### Insights: +1. **GPQA Results**: Fine-tuning on uncensored data has boosted **Nidum 3B's Exact Match and Accuracy**, particularly excelling in **generative** and **zero-shot** tasks involving domain-specific knowledge. +2. **HellaSwag Results**: **Nidum 3B** consistently outperforms **LLaMA 3B** in **common sense reasoning benchmarks**, indicating enhanced contextual and semantic understanding. + +--- + +### Contributing + +We welcome contributions to improve and extend the model’s capabilities. Stay tuned for updates on how to contribute. + +--- + +### Contact + +For inquiries, collaborations, or further information, please reach out to us at **info@nidum.ai**. + +--- + +### Explore the Possibilities + +Dive into unrestricted creativity and innovation with **Nidum Llama 3.2 3B Uncensored**! \ No newline at end of file diff --git a/model-Q2_K.gguf b/model-Q2_K.gguf new file mode 100644 index 0000000..25ba5e6 --- /dev/null +++ b/model-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eafb04b1efc61aeb5828da51e3f84529878df702adcebe604670d1150490d5b +size 1363935712 diff --git a/model-Q3_K_L.gguf b/model-Q3_K_L.gguf new file mode 100644 index 0000000..e40b156 --- /dev/null +++ b/model-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5d496388a257ebef8d0515da29c571d11afc6d053df8395828eaac10f46154f +size 1815347680 diff --git a/model-Q3_K_M.gguf b/model-Q3_K_M.gguf new file mode 100644 index 0000000..698ed9d --- /dev/null +++ b/model-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01004ee1572e35af05173508bb4c1b3b693d65eda2fcf408cf0cb064b8f9a897 +size 1687159264 diff --git a/model-Q3_K_S.gguf b/model-Q3_K_S.gguf new file mode 100644 index 0000000..64c7983 --- /dev/null +++ b/model-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76570e9965eb3affc896a375aa81df4e3993348f9b94b0edfaaaf5aec5626b47 +size 1542848992 diff --git a/model-Q4_0_4_4.gguf b/model-Q4_0_4_4.gguf new file mode 100644 index 0000000..5f7bb53 --- /dev/null +++ b/model-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b0e2a8cd2fa282ed7083d6493b519bc4abf4624c26843b8bb588cc809b02ac3 +size 1917190624 diff --git a/model-Q4_0_4_8.gguf b/model-Q4_0_4_8.gguf new file mode 100644 index 0000000..11a9b67 --- /dev/null +++ b/model-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90cfd651466305fe62d4e04de71fcade9d66a54faab3805f89e7815a6dba8eee +size 1917190624 diff --git a/model-Q4_0_8_8.gguf b/model-Q4_0_8_8.gguf new file mode 100644 index 0000000..f53332f --- /dev/null +++ b/model-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b6d63532e6da1a64056e9a12b798bd78befc1540a178a8e1ff9be0b3afac950 +size 1917190624 diff --git a/model-Q4_K_M.gguf b/model-Q4_K_M.gguf new file mode 100644 index 0000000..3246121 --- /dev/null +++ b/model-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f71ffc4383890374d140a69cd8d6da6179ab4cc00cc9609deadcb3c8766bb387 +size 2019377632 diff --git a/model-Q4_K_S.gguf b/model-Q4_K_S.gguf new file mode 100644 index 0000000..7ab92a5 --- /dev/null +++ b/model-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcde8577e5963a0a10f7b3de5fa299e2d24bc03bd2bb22b2c953440b0c23a9df +size 1928200672 diff --git a/model-Q5_K_M.gguf b/model-Q5_K_M.gguf new file mode 100644 index 0000000..8a256d1 --- /dev/null +++ b/model-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c91827f6e1285b60b901f38a6100ac977af1570c9389b547f4470c3f7e7bc3d +size 2322153952 diff --git a/model-Q5_K_S.gguf b/model-Q5_K_S.gguf new file mode 100644 index 0000000..f6df6ac --- /dev/null +++ b/model-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a132d8b1ca9243358ee0277d1b6b03be71e87196e402f553828f2b6db4b3127e +size 2269512160 diff --git a/model-Q6_K.gguf b/model-Q6_K.gguf new file mode 100644 index 0000000..123d300 --- /dev/null +++ b/model-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8a147548a4ccdc51b958a7fc09f311283893621845ccb1f15db413ed06cd9ae +size 2643853792 diff --git a/model-TQ1_0.gguf b/model-TQ1_0.gguf new file mode 100644 index 0000000..d0d851b --- /dev/null +++ b/model-TQ1_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b494f733a564dae0020a78178c33bbfa8bf5d23627a618bf60d574c68df2c2ec +size 926286304 diff --git a/model-TQ2_0.gguf b/model-TQ2_0.gguf new file mode 100644 index 0000000..c7f458f --- /dev/null +++ b/model-TQ2_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:153693c8664c367ce62a3d2247d4308ff1994cfda6e4354b476b5b3c7cb1577f +size 1058406880