commit 8bcd8c0bee2691539e6effd52c38df953562ffeb Author: ModelHub XC Date: Sat Jun 20 23:27:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: DuoNeural/Ministral-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..675e5fd --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +Ministral-8B-Instruct-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Ministral-8B-Instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Ministral-8B-Instruct-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Ministral-8B-Instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ministral-8B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ministral-8B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ministral-8B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ministral-8B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Ministral-8B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Ministral-8B-Instruct-fp16.gguf filter=lfs diff=lfs merge=lfs -text +imatrix.dat filter=lfs diff=lfs merge=lfs -text diff --git a/Ministral-8B-Instruct-IQ1_S.gguf b/Ministral-8B-Instruct-IQ1_S.gguf new file mode 100644 index 0000000..026b927 --- /dev/null +++ b/Ministral-8B-Instruct-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec20ed484fb99a529e5991be58270cd5c2c4de5463172ecad42e5477464ecbbb +size 2030865120 diff --git a/Ministral-8B-Instruct-IQ2_M.gguf b/Ministral-8B-Instruct-IQ2_M.gguf new file mode 100644 index 0000000..fb34ba7 --- /dev/null +++ b/Ministral-8B-Instruct-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9343ffad4c7c71f656fea47d47dadb2fbd664c707040bf419650a152b309c3f +size 2958330592 diff --git a/Ministral-8B-Instruct-IQ3_XXS.gguf b/Ministral-8B-Instruct-IQ3_XXS.gguf new file mode 100644 index 0000000..0799e9f --- /dev/null +++ b/Ministral-8B-Instruct-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20919cf4476819b84cabb10b0619655f0744123608755faaba4d96c7601f4f19 +size 3276049120 diff --git a/Ministral-8B-Instruct-IQ4_XS.gguf b/Ministral-8B-Instruct-IQ4_XS.gguf new file mode 100644 index 0000000..a1d6a30 --- /dev/null +++ b/Ministral-8B-Instruct-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e5074db5573b9fd2e70b5d30c2f822df4a2ec90b7f8c09f55d98597bab3e822 +size 4448226016 diff --git a/Ministral-8B-Instruct-Q3_K_M.gguf b/Ministral-8B-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..d3e3672 --- /dev/null +++ b/Ministral-8B-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:712c56adf36074777926428993f2d800478bac154febfc66b0cdd7d83a54393b +size 4019227104 diff --git a/Ministral-8B-Instruct-Q4_K_M.gguf b/Ministral-8B-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..a460e17 --- /dev/null +++ b/Ministral-8B-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7033c3bf14aa067a2f37d2615fa83444741c8693f466a8909cfcb593b5526b58 +size 4911499744 diff --git a/Ministral-8B-Instruct-Q5_K_M.gguf b/Ministral-8B-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..815d431 --- /dev/null +++ b/Ministral-8B-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdcdeb0e741801c8016fbc7f86cfebd6c1511804654f4e986f4f559f3691b1ae +size 5724146144 diff --git a/Ministral-8B-Instruct-Q6_K.gguf b/Ministral-8B-Instruct-Q6_K.gguf new file mode 100644 index 0000000..8459bfc --- /dev/null +++ b/Ministral-8B-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6404f2f83297c5b35eb54357f898ca092c8f2fae18a687bf153bee9c7dacd48c +size 6587582944 diff --git a/Ministral-8B-Instruct-Q8_0.gguf b/Ministral-8B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..05fe82f --- /dev/null +++ b/Ministral-8B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e642e9fa9fcd028b9fa70d1b3c561d7b13448895bad3dd9fc8dddfa9a8ba1d9d +size 8529807840 diff --git a/Ministral-8B-Instruct-fp16.gguf b/Ministral-8B-Instruct-fp16.gguf new file mode 100644 index 0000000..93ae529 --- /dev/null +++ b/Ministral-8B-Instruct-fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:987263e3328b6ffb59330e4021d73e057a90033b671f6f0015f019a7f066d757 +size 16048097760 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2e87990 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +license: apache-2.0 +base_model: mistralai/Ministral-8B-Instruct-2410 +tags: +- gguf +- quantized +- mistral +- ministral +- text-generation +language: +- en +pipeline_tag: text-generation +--- + +# Ministral-8B-Instruct — GGUF Quants + +Quantized GGUF versions of [mistralai/Ministral-8B-Instruct-2410](https://huggingface.co/mistralai/Ministral-8B-Instruct-2410) — Mistral AI's Ministral 8B instruct model, optimized for edge and on-device deployment. Features sliding window attention for efficient long-context processing. + +## Available Files + +| File | Quant | Size | Use Case | +|------|-------|------|----------| +| `Ministral-8B-Instruct-Q8_0.gguf` | Q8_0 | ~8.5GB | Maximum quality | +| `Ministral-8B-Instruct-Q6_K.gguf` | Q6_K | ~6.6GB | Near-lossless | +| `Ministral-8B-Instruct-Q5_K_M.gguf` | Q5_K_M | ~5.7GB | High quality | +| `Ministral-8B-Instruct-Q4_K_M.gguf` | Q4_K_M | ~4.9GB | **Recommended default** | +| `Ministral-8B-Instruct-Q3_K_M.gguf` | Q3_K_M | ~3.9GB | Low VRAM | +| `Ministral-8B-Instruct-IQ4_XS.gguf` | IQ4_XS | ~4.3GB | Imatrix 4-bit | +| `Ministral-8B-Instruct-IQ3_XXS.gguf` | IQ3_XXS | ~3.2GB | Imatrix 3-bit | +| `Ministral-8B-Instruct-IQ2_M.gguf` | IQ2_M | ~2.8GB | Imatrix 2-bit | +| `Ministral-8B-Instruct-IQ1_S.gguf` | IQ1_S | ~2.0GB | Extreme compression | +| `Ministral-8B-Instruct-fp16.gguf` | FP16 | ~16.0GB | Full precision | +| `imatrix.dat` | — | — | Importance matrix | + +## Usage + +```bash +./llama-cli -m Ministral-8B-Instruct-Q4_K_M.gguf \ + --ctx-size 8192 -n 512 \ + -p "[INST] Hello! [/INST]" + +ollama run hf.co/DuoNeural/Ministral-8B-Instruct-GGUF:Q4_K_M +``` + +- **Parameters**: 8B | **License**: Apache 2.0 | **Context**: 32K (SWA) + +--- + +*Quantized by DuoNeural using llama.cpp on RTX 5090.* + +--- + +## DuoNeural + +**DuoNeural** is an open AI research lab — human + AI in collaboration. + +| Platform | Link | +|----------|------| +| HuggingFace | [huggingface.co/DuoNeural](https://huggingface.co/DuoNeural) | +| Website | [duoneural.com](https://duoneural.com) | +| GitHub | [github.com/DuoNeural](https://github.com/DuoNeural) | +| X / Twitter | [@DuoNeural](https://x.com/DuoNeural) | +| Email | duoneural@proton.me | +| Newsletter | [duoneural.beehiiv.com](https://duoneural.beehiiv.com) | +| Support | [buymeacoffee.com/duoneural](https://buymeacoffee.com/duoneural) | + +### DuoNeural Research Publications + +| Title | DOI | +|-------|-----| +| [Nano-CTM: Ternary Continuous Thought Machines with Thought-Space Self-Prediction for Efficient Iterative Reasoning](https://doi.org/10.5281/zenodo.19775622) | [10.5281/zenodo.19775622](https://doi.org/10.5281/zenodo.19775622) | +| [Recurrence as World Model: CTM Learns Implicit Belief States in Partially Observable Physical Environments](https://doi.org/10.5281/zenodo.19810620) | [10.5281/zenodo.19810620](https://doi.org/10.5281/zenodo.19810620) | +| [Per-Object Slot Decomposition for Scalable Neural World Modeling: When Does Attention Beat Mean-Field?](https://doi.org/10.5281/zenodo.19846804) | [10.5281/zenodo.19846804](https://doi.org/10.5281/zenodo.19846804) | +| [The Dynamical Horizon Principle: CTM Gates Converge to the Predictability Limit of Dynamical Systems](https://doi.org/10.5281/zenodo.19952612) | [10.5281/zenodo.19952612](https://doi.org/10.5281/zenodo.19952612) | + +*Open access, CC BY 4.0. Authored by Archon, Jesse Caldwell, Aura — DuoNeural.* diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..2fc1cbe --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3369625f66d996ea225fe8bc5896f61365fc5997f09af7b91d62be807e9838b +size 5347200