初始化项目，由ModelHub XC社区提供模型

Model: worthdoing/SmolLM2-1.7B-Instruct-GGUF Source: Original Platform
2026-05-07 14:36:37 +08:00
commit 0d16d20950
9 changed files with 198 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,42 @@
+*.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
+smollm2-1.7b-instruct-Q4_K_M-worthdoing.gguf filter=lfs diff=lfs merge=lfs -text
+smollm2-1.7b-instruct-Q5_K_M-worthdoing.gguf filter=lfs diff=lfs merge=lfs -text
+smollm2-1.7b-instruct-Q8_0-worthdoing.gguf filter=lfs diff=lfs merge=lfs -text
+smollm2-1.7b-instruct-Q3_K_M-worthdoing.gguf filter=lfs diff=lfs merge=lfs -text
+smollm2-1.7b-instruct-Q4_K_S-worthdoing.gguf filter=lfs diff=lfs merge=lfs -text
+smollm2-1.7b-instruct-Q5_K_S-worthdoing.gguf filter=lfs diff=lfs merge=lfs -text
+smollm2-1.7b-instruct-Q6_K-worthdoing.gguf filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,135 @@
+---
+language:
+- en
+- fr
+- multilingual
+license: apache-2.0
+tags:
+- gguf
+- quantized
+- mac
+- apple-silicon
+- local-inference
+- worthdoing
+base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct
+quantized_by: worthdoing
+pipeline_tag: text-generation
+---
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/Worth-Doing/brand-assets/main/png/variants/04-horizontal.png" alt="worthdoing" width="400"/>
+</p>
+<p align="center"><strong>Author: Simon-Pierre Boucher</strong></p>
+
+<p align="center">
+  <img src="https://img.shields.io/badge/Format-GGUF-blue?style=for-the-badge" alt="GGUF"/>
+  <img src="https://img.shields.io/badge/Params-1.7B-orange?style=for-the-badge" alt="Parameters"/>
+  <img src="https://img.shields.io/badge/Platform-Apple_Silicon-black?style=for-the-badge&logo=apple" alt="Apple Silicon"/>
+  <img src="https://img.shields.io/badge/License-Apache_2.0-green?style=for-the-badge" alt="License"/>
+  <img src="https://img.shields.io/badge/Quantized_by-worthdoing-purple?style=for-the-badge" alt="worthdoing"/>
+</p>
+<p align="center">
+  <img src="https://img.shields.io/badge/Q4__K__M-0.9_GB-brightgreen?style=flat-square" alt="Q4_K_M"/>
+  <img src="https://img.shields.io/badge/Q5__K__M-1.1_GB-yellow?style=flat-square" alt="Q5_K_M"/>
+  <img src="https://img.shields.io/badge/Q8__0-1.6_GB-red?style=flat-square" alt="Q8_0"/>
+</p>
+
+# SmolLM2-1.7B-Instruct - GGUF Quantized by worthdoing
+
+> Quantized for local Mac inference (Apple Silicon / Metal) by **worthdoing**
+
+## About
+
+This is a GGUF quantized version of [SmolLM2-1.7B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct), optimized for running locally on Apple Silicon Macs with `llama.cpp`, `Ollama`, or `LM Studio`.
+
+- **Original model:** [HuggingFaceTB/SmolLM2-1.7B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct)
+- **Parameters:** 1.7B
+- **Quantized by:** worthdoing
+- **Pipeline:** corelm-model v1.0
+
+## Description
+
+Smallest viable general model. Perfect for edge/embedded use.
+
+## Available Quantizations
+
+| File | Quant | BPW | Size | Use Case |
+|------|-------|-----|------|----------|
+| `smollm2-1.7b-instruct-Q4_K_M-worthdoing.gguf` | Q4_K_M | 4.58 | ~0.9 GB | **Recommended** - Best quality/size ratio |
+| `smollm2-1.7b-instruct-Q5_K_M-worthdoing.gguf` | Q5_K_M | 5.33 | ~1.1 GB | Higher quality, still fast |
+| `smollm2-1.7b-instruct-Q8_0-worthdoing.gguf` | Q8_0 | 7.96 | ~1.6 GB | Near-original quality |
+
+## How to Use
+
+### With Ollama
+```bash
+# Create a Modelfile
+cat > Modelfile <<'MODELEOF'
+FROM ./smollm2-1.7b-instruct-Q4_K_M-worthdoing.gguf
+MODELEOF
+
+ollama create smollm2-1.7b-instruct -f Modelfile
+ollama run smollm2-1.7b-instruct
+```
+
+### With llama.cpp
+```bash
+llama-cli -m smollm2-1.7b-instruct-Q4_K_M-worthdoing.gguf -p "Your prompt here" -ngl 99
+```
+
+### With LM Studio
+1. Download the GGUF file
+2. Open LM Studio -> My Models -> Import
+3. Select the GGUF file and start chatting
+
+## Quantization Method
+
+Our quantization pipeline (**corelm-model v1.0**) follows a rigorous multi-step process to ensure maximum quality and compatibility:
+
+### Step 1 — Download & Validation
+- Model weights are downloaded from HuggingFace Hub in **SafeTensors** format (`.safetensors`)
+- Legacy formats (`.bin`, `.pt`) are excluded to ensure clean, verified weights
+- Tokenizer, configuration, and all metadata are preserved
+
+### Step 2 — Conversion to GGUF F16 Baseline
+- The original model is converted to **GGUF format at FP16 precision** using `convert_hf_to_gguf.py` from [llama.cpp](https://github.com/ggml-org/llama.cpp)
+- This lossless baseline preserves the full original model quality
+- Architecture-specific tensors (attention, FFN, embeddings, MoE routing) are mapped to their GGUF equivalents
+
+### Step 3 — K-Quant Quantization
+- The F16 baseline is quantized using `llama-quantize` with **k-quant methods**
+- K-quants use a mixed-precision approach: more important layers (attention, output) retain higher precision, while less sensitive layers (FFN) are compressed more aggressively
+- Each quantization level offers a different quality/size tradeoff:
+
+| Method | Bits per Weight | Strategy |
+|--------|----------------|----------|
+| **Q4_K_M** | ~4.58 bpw | Mixed 4/5-bit. Attention & output layers use Q5_K, FFN layers use Q4_K. Best balance of quality and size. |
+| **Q5_K_M** | ~5.33 bpw | Mixed 5/6-bit. Attention & output layers use Q6_K, FFN layers use Q5_K. Higher quality with moderate size increase. |
+| **Q8_0** | ~7.96 bpw | Uniform 8-bit. All layers quantized to 8-bit. Near-lossless quality, largest file size. |
+
+### Step 4 — Metadata Injection
+- Custom metadata is embedded directly in each GGUF file:
+  - `general.quantized_by`: worthdoing
+  - `general.quantization_version`: corelm-1.0
+- This ensures full traceability and provenance of every quantized file
+
+### Tools & Environment
+- **llama.cpp**: Used for both conversion and quantization — the industry-standard open-source LLM inference engine
+- **Target platform**: Apple Silicon Macs (M1/M2/M3/M4) with Metal GPU acceleration
+- **Inference runtimes**: Compatible with `llama.cpp`, `Ollama`, `LM Studio`, `koboldcpp`, and any GGUF-compatible runtime
+
+## Recommended Hardware
+
+| Quant | Min RAM | Recommended |
+|-------|---------|-------------|
+| Q4_K_M | 4 GB | Mac with 8 GB+ RAM |
+| Q5_K_M | 4 GB | Mac with 8 GB+ RAM |
+| Q8_0 | 4 GB | Mac with 8 GB+ RAM |
+
+## Tags
+
+`general`, `ultra-lightweight`, `edge`
+
+---
+
+*Quantized with corelm-model pipeline by **worthdoing** on 2026-04-17*
--- a/smollm2-1.7b-instruct-Q3_K_M-worthdoing.gguf
+++ b/smollm2-1.7b-instruct-Q3_K_M-worthdoing.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0892bc4816a4d7af24e02b266925c5e9ecc3ed56d03b6f12156f780806af8acb
+size 860181632
--- a/smollm2-1.7b-instruct-Q4_K_M-worthdoing.gguf
+++ b/smollm2-1.7b-instruct-Q4_K_M-worthdoing.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:776f20c2c0ccb1338509da80fc7d6a5041c9cc35dec5414fa90ba1a95dfa6754
+size 1055609984
--- a/smollm2-1.7b-instruct-Q4_K_S-worthdoing.gguf
+++ b/smollm2-1.7b-instruct-Q4_K_S-worthdoing.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4003d3560b4bfca2754ed91ca43abe146635eab0490ef63c0669a58781d9c43
+size 999117952
--- a/smollm2-1.7b-instruct-Q5_K_M-worthdoing.gguf
+++ b/smollm2-1.7b-instruct-Q5_K_M-worthdoing.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a12ae83fc3a041555c1a9a5f5cd7fe2793be563bbced7f4a5c81f152e3281476
+size 1225479296
--- a/smollm2-1.7b-instruct-Q5_K_S-worthdoing.gguf
+++ b/smollm2-1.7b-instruct-Q5_K_S-worthdoing.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e6f4edb065b6266a5916201bc20ac07ba7594a5e99ffeb46c19a8cfd3b6ac93
+size 1192055936
--- a/smollm2-1.7b-instruct-Q6_K-worthdoing.gguf
+++ b/smollm2-1.7b-instruct-Q6_K-worthdoing.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc8224dff88c053beb50fdbbb8499137b6dce97ac56742593c21975f2040e01d
+size 1405965440
--- a/smollm2-1.7b-instruct-Q8_0-worthdoing.gguf
+++ b/smollm2-1.7b-instruct-Q8_0-worthdoing.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:448108c82fabcd9ece4ac8bb482a86eabc20a67e6bbede4dbf1f9bd8df3afe86
+size 1820415104