commit e1af997e03b8e4af92008a509fba0e57d7199035 Author: ModelHub XC Date: Tue Jun 16 17:27:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: AksaraLLM/Kiel-Pro-0.5B-v3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6a89f94 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,40 @@ +*.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 +Kiel-Pro-0.5B-v3.f16.gguf filter=lfs diff=lfs merge=lfs -text +Kiel-Pro-0.5B-v3.q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Kiel-Pro-0.5B-v3.q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +Kiel-Pro-0.5B-v3.q6_k.gguf filter=lfs diff=lfs merge=lfs -text +Kiel-Pro-0.5B-v3.q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Kiel-Pro-0.5B-v3.f16.gguf b/Kiel-Pro-0.5B-v3.f16.gguf new file mode 100644 index 0000000..d3dd6fc --- /dev/null +++ b/Kiel-Pro-0.5B-v3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33a99968435b780f47636b25f395fea6e6ccce7129dc5705b1d47d5a0bc44830 +size 994154240 diff --git a/Kiel-Pro-0.5B-v3.q4_k_m.gguf b/Kiel-Pro-0.5B-v3.q4_k_m.gguf new file mode 100644 index 0000000..d37a7dd --- /dev/null +++ b/Kiel-Pro-0.5B-v3.q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7b1f7baa74396c4f5a5bf0f7d929fc348fbd1f8b590576c8eb44782badba48e +size 397805312 diff --git a/Kiel-Pro-0.5B-v3.q5_k_m.gguf b/Kiel-Pro-0.5B-v3.q5_k_m.gguf new file mode 100644 index 0000000..784cd73 --- /dev/null +++ b/Kiel-Pro-0.5B-v3.q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03f1819b3fa854b1958d1b14e74fb3f1a942dae20514b85185a3e3e33d9288c0 +size 420083456 diff --git a/Kiel-Pro-0.5B-v3.q6_k.gguf b/Kiel-Pro-0.5B-v3.q6_k.gguf new file mode 100644 index 0000000..20f52bb --- /dev/null +++ b/Kiel-Pro-0.5B-v3.q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f48e1538fb017d58e5f5bf0404d0277b3188ed638d390c3822260a562c704d81 +size 505733888 diff --git a/Kiel-Pro-0.5B-v3.q8_0.gguf b/Kiel-Pro-0.5B-v3.q8_0.gguf new file mode 100644 index 0000000..aa8f7e2 --- /dev/null +++ b/Kiel-Pro-0.5B-v3.q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:115de9127227e3c7683bad0599d29354f161b0bbe5a705ebd1a488f74be81c70 +size 531065600 diff --git a/Modelfile b/Modelfile new file mode 100644 index 0000000..f10ba43 --- /dev/null +++ b/Modelfile @@ -0,0 +1,26 @@ +# Ollama Modelfile for AksaraLLM/Kiel-Pro-0.5B-v3-GGUF +# Quick start: +# ollama create aksara-kiel-pro-0.5b-v3 -f Modelfile +# ollama run aksara-kiel-pro-0.5b-v3 "Indonesia adalah" +# +# Or pull a quant directly with: +# huggingface-cli download AksaraLLM/Kiel-Pro-0.5B-v3-GGUF Kiel-Pro-0.5B-v3.q4_k_m.gguf --local-dir . + +FROM ./Kiel-Pro-0.5B-v3.q4_k_m.gguf + +TEMPLATE """{{ if .System }}<|im_start|>system +{{ .System }}<|im_end|> +{{ end }}{{ if .Prompt }}<|im_start|>user +{{ .Prompt }}<|im_end|> +{{ end }}<|im_start|>assistant +{{ .Response }}<|im_end|> +""" + +SYSTEM """Kamu adalah asisten AI berbahasa Indonesia. Jawab dengan jelas, ringkas, dan akurat.""" + +PARAMETER temperature 0.7 +PARAMETER top_p 0.9 +PARAMETER repeat_penalty 1.15 +PARAMETER num_ctx 4096 +PARAMETER stop "<|im_end|>" +PARAMETER stop "<|im_start|>" diff --git a/README.md b/README.md new file mode 100644 index 0000000..5dd4d0d --- /dev/null +++ b/README.md @@ -0,0 +1,62 @@ +--- +language: +- id +license: apache-2.0 +library_name: gguf +pipeline_tag: text-generation +base_model: AksaraLLM/Kiel-Pro-0.5B-v3 +tags: +- gguf +- llama.cpp +- ollama +- indonesian +- aksarallm +- qwen2 +--- +# Kiel-Pro-0.5B-v3-GGUF + +GGUF quantizations of [`AksaraLLM/Kiel-Pro-0.5B-v3`](https://huggingface.co/AksaraLLM/Kiel-Pro-0.5B-v3) for inference with [llama.cpp](https://github.com/ggml-org/llama.cpp), [Ollama](https://ollama.ai), [LM Studio](https://lmstudio.ai), and other GGUF runtimes. + +## Files + +| File | Quant | Size | Recommended use | +|---|---|---|---| +| `Kiel-Pro-0.5B-v3.f16.gguf` | F16 | 0.99 GB | lossless from safetensors | +| `Kiel-Pro-0.5B-v3.q8_0.gguf` | Q8_0 | 0.53 GB | near-lossless, ~2× smaller | +| `Kiel-Pro-0.5B-v3.q6_k.gguf` | Q6_K | 0.51 GB | high quality, ~2.5× smaller | +| `Kiel-Pro-0.5B-v3.q5_k_m.gguf` | Q5_K_M | 0.42 GB | good quality, ~3× smaller | +| `Kiel-Pro-0.5B-v3.q4_k_m.gguf` | Q4_K_M | 0.40 GB | recommended default, ~4× smaller | + +## CPU benchmark (AMD EPYC 7763, 2 threads, AVX2) + +| Quant | Prompt eval (32 tok) | Generation (16 tok) | +|---|---:|---:| +| `q4_k_m` | **36.7 tok/s** | **20.1 tok/s** | + +So a 494M model at q4_k_m runs comfortably on a CPU laptop. Larger quants (q5_k_m, q6_k, q8_0) trade a bit of speed for better quality. + +## Quick start — llama.cpp + +```bash +huggingface-cli download AksaraLLM/Kiel-Pro-0.5B-v3-GGUF Kiel-Pro-0.5B-v3.q4_k_m.gguf --local-dir . +./llama-cli -m Kiel-Pro-0.5B-v3.q4_k_m.gguf -p "Indonesia adalah" -n 64 +``` + +## Quick start — Ollama + +```bash +huggingface-cli download AksaraLLM/Kiel-Pro-0.5B-v3-GGUF Kiel-Pro-0.5B-v3.q4_k_m.gguf Modelfile --local-dir . +ollama create aksara-kiel-pro-0.5b-v3 -f Modelfile +ollama run aksara-kiel-pro-0.5b-v3 "Apa ibukota Indonesia?" +``` + +## Source model + +See [`AksaraLLM/Kiel-Pro-0.5B-v3`](https://huggingface.co/AksaraLLM/Kiel-Pro-0.5B-v3) for architecture, training data, eval results, and limitations. + +## Conversion provenance + +- Converted with [`convert_hf_to_gguf.py`](https://github.com/ggml-org/llama.cpp/blob/master/convert_hf_to_gguf.py) from llama.cpp +- Quantized with `llama-quantize` from the same build +- Architecture detected as `qwen2` +- All files listed above are reproducible from the source HF safetensors