commit bae243b9ec8bec29c30656b9838baeda8642509a Author: ModelHub XC Date: Thu Oct 8 14:23:24 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: prithivMLmods/Qwen3-4B-Esper3-F32-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/Qwen3-4B-Esper3.BF16.gguf b/Qwen3-4B-Esper3.BF16.gguf new file mode 100644 index 0000000..b6d22ad --- /dev/null +++ b/Qwen3-4B-Esper3.BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e504681e0a691153bb99dc41bf75d72b9563ac0521bd1d9a945a3a0700fb3e2f +size 8051280480 diff --git a/Qwen3-4B-Esper3.F16.gguf b/Qwen3-4B-Esper3.F16.gguf new file mode 100644 index 0000000..ed9394f --- /dev/null +++ b/Qwen3-4B-Esper3.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fee60ab1bbdbf353764a34171f944ea87ecb7429e376ed5c20688310bdc5289 +size 8051280480 diff --git a/Qwen3-4B-Esper3.F32.gguf b/Qwen3-4B-Esper3.F32.gguf new file mode 100644 index 0000000..8663537 --- /dev/null +++ b/Qwen3-4B-Esper3.F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98e1b33c6ab1d96c16fdfeef1901c377b76190bf911b227091ab2a936cf7a082 +size 16095824480 diff --git a/Qwen3-4B-Esper3.Q2_K.gguf b/Qwen3-4B-Esper3.Q2_K.gguf new file mode 100644 index 0000000..da3fc36 --- /dev/null +++ b/Qwen3-4B-Esper3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39aa83d4ee944ff353e7f6d44ba61ddc082074642222422f16cfd40437c81bcd +size 1669494880 diff --git a/Qwen3-4B-Esper3.Q3_K_L.gguf b/Qwen3-4B-Esper3.Q3_K_L.gguf new file mode 100644 index 0000000..efec7de --- /dev/null +++ b/Qwen3-4B-Esper3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec82f83765dff424ed8e427b7008eb931be1945cbe352104ca56146be51caa8a +size 2239780960 diff --git a/Qwen3-4B-Esper3.Q3_K_M.gguf b/Qwen3-4B-Esper3.Q3_K_M.gguf new file mode 100644 index 0000000..d3dfc99 --- /dev/null +++ b/Qwen3-4B-Esper3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b9fbe913c5df87e1eda78dec74a67c23fe46178dc4f550dbc081d71f6a1c85f +size 2075613280 diff --git a/Qwen3-4B-Esper3.Q3_K_S.gguf b/Qwen3-4B-Esper3.Q3_K_S.gguf new file mode 100644 index 0000000..f2842f3 --- /dev/null +++ b/Qwen3-4B-Esper3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6491a45ffcf186a1d59b070ae4440926be046e4c1d1c324052b2cb33b28a59b8 +size 1886992480 diff --git a/Qwen3-4B-Esper3.Q4_K_M.gguf b/Qwen3-4B-Esper3.Q4_K_M.gguf new file mode 100644 index 0000000..b990206 --- /dev/null +++ b/Qwen3-4B-Esper3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21f666eaea0469ea653806908dfe5bf83ee69cec6a3416eb4153fab3b56af590 +size 2497276000 diff --git a/Qwen3-4B-Esper3.Q4_K_S.gguf b/Qwen3-4B-Esper3.Q4_K_S.gguf new file mode 100644 index 0000000..69a78e5 --- /dev/null +++ b/Qwen3-4B-Esper3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a42150ee55828340e9c6b6ef9df8ac8c1110ad8d7e23b81e0d08c7a6e81edc47 +size 2383304800 diff --git a/Qwen3-4B-Esper3.Q5_K_M.gguf b/Qwen3-4B-Esper3.Q5_K_M.gguf new file mode 100644 index 0000000..b4ca702 --- /dev/null +++ b/Qwen3-4B-Esper3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bad1a92a23c5eebdc6db776b504a6ba06069d8fdfb84effe9575e1d5e3ae7aa7 +size 2889508960 diff --git a/Qwen3-4B-Esper3.Q5_K_S.gguf b/Qwen3-4B-Esper3.Q5_K_S.gguf new file mode 100644 index 0000000..9f3b366 --- /dev/null +++ b/Qwen3-4B-Esper3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:708b381839e1c3f6d97617bc16c49f7ff213d2976d83081ce352aba7e7ad2733 +size 2823706720 diff --git a/Qwen3-4B-Esper3.Q6_K.gguf b/Qwen3-4B-Esper3.Q6_K.gguf new file mode 100644 index 0000000..79e61c1 --- /dev/null +++ b/Qwen3-4B-Esper3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c27079fd53df7a71a83bd662ba7e0967ee2b4b1470bc1895a56e78e4b8e3ee1c +size 3306256480 diff --git a/Qwen3-4B-Esper3.Q8_0.gguf b/Qwen3-4B-Esper3.Q8_0.gguf new file mode 100644 index 0000000..21d4941 --- /dev/null +++ b/Qwen3-4B-Esper3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6064edd15cfa4b5c0a5e2f688f9a3c14c7a58915d092476f78f11377ece34338 +size 4280400480 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5222ccd --- /dev/null +++ b/README.md @@ -0,0 +1,50 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- ValiantLabs/Qwen3-4B-Esper3 +pipeline_tag: text-generation +library_name: transformers +tags: +- text-generation-inference +--- + +# **Qwen3-4B-Esper3-F32-GGUF** + +> Esper 3 is a specialist model built on Qwen 3, designed for coding, architecture, and DevOps reasoning. It has been fine-tuned using our proprietary DevOps, architecture, and code reasoning dataset generated with Deepseek R1. This tuning enhances its general and creative reasoning abilities, making it effective not only in problem-solving but also in general conversation. With its small model sizes, Esper 3 is optimized for fast inference, making it suitable for deployment on local desktops, mobile devices, and high-speed server environments. + +## Model Files + +| Filename | Size | Format | Description | +|----------|------|--------|-------------| +| Qwen3-4B-Esper3.BF16.gguf | 8.05 GB | BF16 | Brain Float 16-bit quantization | +| Qwen3-4B-Esper3.F16.gguf | 8.05 GB | F16 | Half precision (16-bit) floating point | +| Qwen3-4B-Esper3.F32.gguf | 16.1 GB | F32 | Full precision (32-bit) floating point | +| Qwen3-4B-Esper3.Q2_K.gguf | 1.67 GB | Q2_K | 2-bit quantization with K-quant | +| Qwen3-4B-Esper3.Q3_K_L.gguf | 2.24 GB | Q3_K_L | 3-bit quantization (Large) with K-quant | +| Qwen3-4B-Esper3.Q3_K_M.gguf | 2.08 GB | Q3_K_M | 3-bit quantization (Medium) with K-quant | +| Qwen3-4B-Esper3.Q3_K_S.gguf | 1.89 GB | Q3_K_S | 3-bit quantization (Small) with K-quant | +| Qwen3-4B-Esper3.Q4_K_M.gguf | 2.5 GB | Q4_K_M | 4-bit quantization (Medium) with K-quant | +| Qwen3-4B-Esper3.Q4_K_S.gguf | 2.38 GB | Q4_K_S | 4-bit quantization (Small) with K-quant | +| Qwen3-4B-Esper3.Q5_K_M.gguf | 2.89 GB | Q5_K_M | 5-bit quantization (Medium) with K-quant | +| Qwen3-4B-Esper3.Q5_K_S.gguf | 2.82 GB | Q5_K_S | 5-bit quantization (Small) with K-quant | +| Qwen3-4B-Esper3.Q6_K.gguf | 3.31 GB | Q6_K | 6-bit quantization with K-quant | +| Qwen3-4B-Esper3.Q8_0.gguf | 4.28 GB | Q8_0 | 8-bit quantization | + +### Recommended Usage + +- **Q4_K_M** or **Q5_K_M**: Best balance of quality and performance for most users +- **Q6_K** or **Q8_0**: Higher quality, larger file sizes +- **Q2_K** or **Q3_K_S**: Fastest inference, lower quality +- **F16** or **BF16**: High quality, requires more VRAM +- **F32**: Highest quality, requires significant VRAM + +## Quants Usage + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..d1b8b99 --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "qwen3" +} \ No newline at end of file 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