commit 5d90ac8bc198a6e106ddd7d779b1ea957730a296 Author: ModelHub XC Date: Sat Jun 20 18:38:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: featherless-ai-quants/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2968a9d --- /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 +*.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 +featherless-quants.png filter=lfs diff=lfs merge=lfs -text +neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7e2be35 --- /dev/null +++ b/README.md @@ -0,0 +1,47 @@ +--- +base_model: neuralmagic/Sparse-Llama-3.1-8B-ultrachat_200k-2of4 +pipeline_tag: text-generation +quantized_by: featherless-ai-quants +--- + +# neuralmagic/Sparse-Llama-3.1-8B-ultrachat_200k-2of4 GGUF Quantizations 🚀 + +![Featherless AI Quants](./featherless-quants.png) + +*Optimized GGUF quantization files for enhanced model performance* + +> Powered by [Featherless AI](https://featherless.ai) - run any model you'd like for a simple small fee. +--- + +## Available Quantizations 📊 + +| Quantization Type | File | Size | +|-------------------|------|------| +| IQ4_XS | [neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-IQ4_XS.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUF/blob/main/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-IQ4_XS.gguf) | 4276.63 MB | +| Q2_K | [neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q2_K.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUF/blob/main/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q2_K.gguf) | 3031.86 MB | +| Q3_K_L | [neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q3_K_L.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUF/blob/main/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q3_K_L.gguf) | 4121.74 MB | +| Q3_K_M | [neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q3_K_M.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUF/blob/main/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q3_K_M.gguf) | 3832.74 MB | +| Q3_K_S | [neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q3_K_S.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUF/blob/main/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q3_K_S.gguf) | 3494.74 MB | +| Q4_K_M | [neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q4_K_M.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUF/blob/main/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q4_K_M.gguf) | 4692.78 MB | +| Q4_K_S | [neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q4_K_S.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUF/blob/main/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q4_K_S.gguf) | 4475.28 MB | +| Q5_K_M | [neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q5_K_M.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUF/blob/main/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q5_K_M.gguf) | 5467.41 MB | +| Q5_K_S | [neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q5_K_S.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUF/blob/main/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q5_K_S.gguf) | 5339.91 MB | +| Q6_K | [neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q6_K.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUF/blob/main/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q6_K.gguf) | 6290.45 MB | +| Q8_0 | [neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q8_0.gguf](https://huggingface.co/featherless-ai-quants/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUF/blob/main/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q8_0.gguf) | 8145.12 MB | + + +--- + +## ⚡ Powered by [Featherless AI](https://featherless.ai) + +### Key Features + +- 🔥 **Instant Hosting** - Deploy any Llama model on HuggingFace instantly +- 🛠️ **Zero Infrastructure** - No server setup or maintenance required +- 📚 **Vast Compatibility** - Support for 2400+ models and counting +- 💎 **Affordable Pricing** - Starting at just $10/month + +--- + +**Links:** +[Get Started](https://featherless.ai) | [Documentation](https://featherless.ai/docs) | [Models](https://featherless.ai/models) \ No newline at end of file diff --git a/featherless-quants.png b/featherless-quants.png new file mode 100644 index 0000000..3e0eab9 --- /dev/null +++ b/featherless-quants.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e1b4d66c8306c7b0614089381fdf86ea4efb02dffb78d22767a084cb8b88d6b +size 1614532 diff --git a/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-IQ4_XS.gguf b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-IQ4_XS.gguf new file mode 100644 index 0000000..8939a14 --- /dev/null +++ b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a37db790e4be14258644d59a46b0ec2f1d18adca870cc9a4f661d2fc67297ae +size 4484368096 diff --git a/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q2_K.gguf b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q2_K.gguf new file mode 100644 index 0000000..796a201 --- /dev/null +++ b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8291d29a99f0c8a4b2cc93615ac3bb4ba42eaedb8fc14b88291ee8eb0ea3858b +size 3179136736 diff --git a/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q3_K_L.gguf b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q3_K_L.gguf new file mode 100644 index 0000000..8d568a7 --- /dev/null +++ b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab8376866d80d0feffd2b968c378db1e6e3a75fe3c59e41c154e5d52e9e00900 +size 4321961696 diff --git a/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q3_K_M.gguf b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q3_K_M.gguf new file mode 100644 index 0000000..1a3fb91 --- /dev/null +++ b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b56a3cff0bac43f0862f4b8a584ea60bdaaffcb7b2cb2c16d09c17dc8ce809 +size 4018923232 diff --git a/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q3_K_S.gguf b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q3_K_S.gguf new file mode 100644 index 0000000..730b11c --- /dev/null +++ b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4224d89c183ae428c19fb305ddb3c71c8dfd8daa639a056712d57f33aa55b4a6 +size 3664504544 diff --git a/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q4_K_M.gguf b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q4_K_M.gguf new file mode 100644 index 0000000..6d2075a --- /dev/null +++ b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:197fb0699f73374971865b9cd5a2e1664f5239306e619b1637f844682384dc3d +size 4920739552 diff --git a/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q4_K_S.gguf b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q4_K_S.gguf new file mode 100644 index 0000000..d6833e2 --- /dev/null +++ b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bb534e04970295d853de13d30897b977aa3925466866b05a743deb72e8e417d +size 4692674272 diff --git a/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q5_K_M.gguf b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q5_K_M.gguf new file mode 100644 index 0000000..fc3ff59 --- /dev/null +++ b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a09ae3351d494453cd7dd5ea50e90bd02168fb29a25ef08355f305a274b32d0a +size 5732992736 diff --git a/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q5_K_S.gguf b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q5_K_S.gguf new file mode 100644 index 0000000..cb1774b --- /dev/null +++ b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8174e9a7a27c4c61530d15d005553a19f625312fce75ba7788240eac355123c7 +size 5599299296 diff --git a/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q6_K.gguf b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q6_K.gguf new file mode 100644 index 0000000..18ffa2d --- /dev/null +++ b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a999e96c175d91294234fded479159d0e88f8477bd14fa3e5a8c531821b2d7e0 +size 6596011744 diff --git a/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q8_0.gguf b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q8_0.gguf new file mode 100644 index 0000000..51a9348 --- /dev/null +++ b/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:084a8a9db20318e12f49d35b9d8f35daf4c999dba2b2f399ed2e6f8999f0a3ec +size 8540776160