commit d7562e194f70ee24a5b3062387da8355f931bb16 Author: ModelHub XC Date: Tue Jun 16 21:17:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: thuniverse-ai/SiliconMind-V1-Qwen3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..252fc4f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,44 @@ +*.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 +SiliconMind-V1-Qwen3-8B-F16.gguf filter=lfs diff=lfs merge=lfs -text +SiliconMind-V1-Qwen3-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SiliconMind-V1-Qwen3-8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SiliconMind-V1-Qwen3-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SiliconMind-V1-Qwen3-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SiliconMind-V1-Qwen3-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SiliconMind-V1-Qwen3-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SiliconMind-V1-Qwen3-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SiliconMind-V1-Qwen3-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..bd9fd0f --- /dev/null +++ b/README.md @@ -0,0 +1,56 @@ +--- +license: apache-2.0 +license_link: https://huggingface.co/AS-SiliconMind/SiliconMind-V1-Qwen3-8B/blob/main/LICENSE +language: +- en +base_model: +- AS-SiliconMind/SiliconMind-V1-Qwen3-8B +pipeline_tag: text-generation +tags: +- verilog +- reasoning +- multi-agent +- gguf +- quantized +- llama.cpp +- ollama +--- + +# SiliconMind-V1-Qwen3-8B GGUF + +GGUF quantizations of [AS-SiliconMind/SiliconMind-V1-Qwen3-8B](https://huggingface.co/AS-SiliconMind/SiliconMind-V1-Qwen3-8B), a 8B model specialized for Verilog code generation, testing, and debugging. + +Quantized with [llama.cpp](https://github.com/ggml-org/llama.cpp) b7437, which compatible with Ollama v0.17.4. + +## Available Quantizations + +| File | Size | Description | +|------|------|-------------| +| SiliconMind-V1-Qwen3-8B-F16.gguf | 25 GB | Full precision (F16) | +| SiliconMind-V1-Qwen3-8B-Q8_0.gguf | 13 GB | 8-bit, highest quality | +| SiliconMind-V1-Qwen3-8B-Q6_K.gguf | 10 GB | 6-bit | +| SiliconMind-V1-Qwen3-8B-Q5_K_M.gguf | 8.8 GB | 5-bit medium | +| SiliconMind-V1-Qwen3-8B-Q4_K_M.gguf | 7.6 GB | 4-bit medium **(recommended)** | +| SiliconMind-V1-Qwen3-8B-Q3_K_L.gguf | 6.7 GB | 3-bit large | +| SiliconMind-V1-Qwen3-8B-Q3_K_M.gguf | 6.3 GB | 3-bit medium | +| SiliconMind-V1-Qwen3-8B-Q3_K_S.gguf | 5.7 GB | 3-bit small | +| SiliconMind-V1-Qwen3-8B-Q2_K.gguf | 5.0 GB | 2-bit, smallest | + +## Usage + +```bash +ollama run hf.co/thuniverse-ai/SiliconMind-V1-Qwen3-8B-GGUF +``` + +Example prompt: +``` +I would like you to implement a module named TopModule with the following +interface. All input and output ports are one bit unless otherwise +specified. + +- input in (3 bits) +- output out (2 bits) + +The module should implement a "population count" circuit that counts the +number of '1's in the input vector. +``` diff --git a/SiliconMind-V1-Qwen3-8B-F16.gguf b/SiliconMind-V1-Qwen3-8B-F16.gguf new file mode 100644 index 0000000..80302bc --- /dev/null +++ b/SiliconMind-V1-Qwen3-8B-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67bc5046d53d0364eca2386d46d4cd4682f2b9f60884de04bd2855fe838e51ca +size 16388044256 diff --git a/SiliconMind-V1-Qwen3-8B-Q2_K.gguf b/SiliconMind-V1-Qwen3-8B-Q2_K.gguf new file mode 100644 index 0000000..526eee9 --- /dev/null +++ b/SiliconMind-V1-Qwen3-8B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d39e5d7f6f0979886f1c8f869d89073fd37b642f68baf632e680205129fb5f51 +size 3281733088 diff --git a/SiliconMind-V1-Qwen3-8B-Q3_K_L.gguf b/SiliconMind-V1-Qwen3-8B-Q3_K_L.gguf new file mode 100644 index 0000000..b0d1ec8 --- /dev/null +++ b/SiliconMind-V1-Qwen3-8B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e8c47aade3741be6cd10936c64111a5c2bf7281f8cc38b8bf61824d58f72971 +size 4431394272 diff --git a/SiliconMind-V1-Qwen3-8B-Q3_K_M.gguf b/SiliconMind-V1-Qwen3-8B-Q3_K_M.gguf new file mode 100644 index 0000000..6f2cdd4 --- /dev/null +++ b/SiliconMind-V1-Qwen3-8B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d6faa68003e89a04517da692707a794518eb0a0c656696dd6c5784443f2f229 +size 4124161504 diff --git a/SiliconMind-V1-Qwen3-8B-Q3_K_S.gguf b/SiliconMind-V1-Qwen3-8B-Q3_K_S.gguf new file mode 100644 index 0000000..4491547 --- /dev/null +++ b/SiliconMind-V1-Qwen3-8B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5165703a1aec84ce4d89516760f22d219f31df2568048d3f6fad6af86d90c026 +size 3769611744 diff --git a/SiliconMind-V1-Qwen3-8B-Q4_K_M.gguf b/SiliconMind-V1-Qwen3-8B-Q4_K_M.gguf new file mode 100644 index 0000000..3611df6 --- /dev/null +++ b/SiliconMind-V1-Qwen3-8B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92f383be0980c2712fdff2bf6e0abe7452ee3f1641db32a55a1a5411fb96e332 +size 5027784160 diff --git a/SiliconMind-V1-Qwen3-8B-Q5_K_M.gguf b/SiliconMind-V1-Qwen3-8B-Q5_K_M.gguf new file mode 100644 index 0000000..97420da --- /dev/null +++ b/SiliconMind-V1-Qwen3-8B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91d19a28c5f5ac177da76fa3d934e1a0708e8782e00409474182307a4c329a8a +size 5851112928 diff --git a/SiliconMind-V1-Qwen3-8B-Q6_K.gguf b/SiliconMind-V1-Qwen3-8B-Q6_K.gguf new file mode 100644 index 0000000..65985e6 --- /dev/null +++ b/SiliconMind-V1-Qwen3-8B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c31e966b4cd1cff7d309513a571c7fff0cf5a9e4f8f277af1026635516b3921 +size 6725899744 diff --git a/SiliconMind-V1-Qwen3-8B-Q8_0.gguf b/SiliconMind-V1-Qwen3-8B-Q8_0.gguf new file mode 100644 index 0000000..976fb3a --- /dev/null +++ b/SiliconMind-V1-Qwen3-8B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:464377766cc51ed328492d346a2c92ac1f8afc320bd1a45224f94e898cbe80b3 +size 8709518816