commit f90490915aa8e0f7ea7279ad045b831d27359c5b Author: ModelHub XC Date: Wed Oct 14 03:04:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: matrixportalx/Llama3-8B-Instruct-Turkish-Finetuned-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..530ff7c --- /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 +llama3-8b-instruct-turkish-finetuned.q2_k.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-instruct-turkish-finetuned.q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-instruct-turkish-finetuned.q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-instruct-turkish-finetuned.q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-instruct-turkish-finetuned.q4_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-instruct-turkish-finetuned.q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-instruct-turkish-finetuned.q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-instruct-turkish-finetuned.q5_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-instruct-turkish-finetuned.q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-instruct-turkish-finetuned.q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-instruct-turkish-finetuned.q6_k.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-instruct-turkish-finetuned.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..679d542 --- /dev/null +++ b/README.md @@ -0,0 +1,41 @@ +--- +datasets: +- matrixportal/aya-turkish-alpaca +- cenfis/alpaca-turkish-combined +- merve/turkish_instructions +- CohereLabs/aya_collection_language_split +language: +- tr +- en +base_model: +- meta-llama/Meta-Llama-3-8B-Instruct +--- + +# Llama3-8B-Instruct-Turkish-Finetuned GGUF Quantized Models + +## Technical Details +- **Quantization Tool:** llama.cpp +- **Version:** version: 5162 (2016f07b) + +## Model Information +- **Base Model:** [matrixportal/Llama3-8B-Instruct-Turkish-Finetuned](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned) +- **Quantized by:** [matrixportal](https://huggingface.co/matrixportal) + +## Available Files +| 🚀 Download | 🔢 Type | 📝 Description | +|------------|---------|---------------| +| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q2_k.gguf) | Q2 K | Tiny size, lowest quality (emergency use only) | +| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q3_k_s.gguf) | Q3 K S | Very small, low quality (basic tasks) | +| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q3_k_m.gguf) | Q3 K M | Small, acceptable quality | +| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q3_k_l.gguf) | Q3 K L | Small, better than Q3_K_M (good for low RAM) | +| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q4_0.gguf) | Q4 0 | Standard 4-bit (fast on ARM) | +| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q4_k_s.gguf) | Q4 K S | 4-bit optimized (good space savings) | +| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q4_k_m.gguf) | Q4 K M | 4-bit balanced (recommended default) | +| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q5_0.gguf) | Q5 0 | 5-bit high quality | +| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q5_k_s.gguf) | Q5 K S | 5-bit optimized | +| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q5_k_m.gguf) | Q5 K M | 5-bit best (recommended HQ option) | +| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q6_k.gguf) | Q6 K | 6-bit near-perfect (premium quality) | +| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.q8_0.gguf) | Q8 0 | 8-bit maximum (overkill for most) | +| [Download](https://huggingface.co/matrixportal/Llama3-8B-Instruct-Turkish-Finetuned-GGUF/resolve/main/llama3-8b-instruct-turkish-finetuned.f16.gguf) | F16 | Full precision (maximum accuracy) | + +💡 **Q4 K M** provides the best balance for most use cases \ No newline at end of file diff --git a/llama3-8b-instruct-turkish-finetuned.f16.gguf b/llama3-8b-instruct-turkish-finetuned.f16.gguf new file mode 100644 index 0000000..7c72ad3 --- /dev/null +++ b/llama3-8b-instruct-turkish-finetuned.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:949835a88c1f5978e6e1647962915dc283ae5e9f3c3c2e5ed9ddc38a9bf0976d +size 16068891328 diff --git a/llama3-8b-instruct-turkish-finetuned.q2_k.gguf b/llama3-8b-instruct-turkish-finetuned.q2_k.gguf new file mode 100644 index 0000000..2b0964f --- /dev/null +++ b/llama3-8b-instruct-turkish-finetuned.q2_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d350841a91487a9429bf9377c1646318996738b78740a01b677c5593f4883275 +size 3179131584 diff --git a/llama3-8b-instruct-turkish-finetuned.q3_k_l.gguf b/llama3-8b-instruct-turkish-finetuned.q3_k_l.gguf new file mode 100644 index 0000000..ad6fb56 --- /dev/null +++ b/llama3-8b-instruct-turkish-finetuned.q3_k_l.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c92d8a4321572224bca6fbf18827785c675e98b2059a2c2b2c5c286fbc06c10c +size 4321956544 diff --git a/llama3-8b-instruct-turkish-finetuned.q3_k_m.gguf b/llama3-8b-instruct-turkish-finetuned.q3_k_m.gguf new file mode 100644 index 0000000..8de0ae2 --- /dev/null +++ b/llama3-8b-instruct-turkish-finetuned.q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51a4410e0b33463c42e870e62ff12ffb6f13b80249fbb1eb219e3ed26eb455b6 +size 4018918080 diff --git a/llama3-8b-instruct-turkish-finetuned.q3_k_s.gguf b/llama3-8b-instruct-turkish-finetuned.q3_k_s.gguf new file mode 100644 index 0000000..6e1337b --- /dev/null +++ b/llama3-8b-instruct-turkish-finetuned.q3_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acd79ee3d88555e107a7ecef4efe4d82560d9944545362584a031333491e89f2 +size 3664499392 diff --git a/llama3-8b-instruct-turkish-finetuned.q4_0.gguf b/llama3-8b-instruct-turkish-finetuned.q4_0.gguf new file mode 100644 index 0000000..94099c1 --- /dev/null +++ b/llama3-8b-instruct-turkish-finetuned.q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c1cc233b0280ee74d2bab95a9e646d69fd38840e69c4dbe566c441a459fbeea +size 4661211840 diff --git a/llama3-8b-instruct-turkish-finetuned.q4_k_m.gguf b/llama3-8b-instruct-turkish-finetuned.q4_k_m.gguf new file mode 100644 index 0000000..3362485 --- /dev/null +++ b/llama3-8b-instruct-turkish-finetuned.q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebd6ae4ed5d6a4eb39d12b85865f2a9f5d6b7dc2e36bd2a62eb3ee14c8c49e12 +size 4920734400 diff --git a/llama3-8b-instruct-turkish-finetuned.q4_k_s.gguf b/llama3-8b-instruct-turkish-finetuned.q4_k_s.gguf new file mode 100644 index 0000000..4e2d320 --- /dev/null +++ b/llama3-8b-instruct-turkish-finetuned.q4_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5d0d56945084d4d90d37fcbc2b2d4ceceba91450a4ef16d87b33e6921eaf4c5 +size 4692669120 diff --git a/llama3-8b-instruct-turkish-finetuned.q5_0.gguf b/llama3-8b-instruct-turkish-finetuned.q5_0.gguf new file mode 100644 index 0000000..b9f080b --- /dev/null +++ b/llama3-8b-instruct-turkish-finetuned.q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15fd2170b1dcd00bd1e6d9dd9e000c0365febdeb4c6d9a1d5dc27fe3c31f0f01 +size 5599294144 diff --git a/llama3-8b-instruct-turkish-finetuned.q5_k_m.gguf b/llama3-8b-instruct-turkish-finetuned.q5_k_m.gguf new file mode 100644 index 0000000..57b3030 --- /dev/null +++ b/llama3-8b-instruct-turkish-finetuned.q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:658e71a5ba515084a278aaa68d528253ab55edfdba46a49e6fb2141cdf97b6db +size 5732987584 diff --git a/llama3-8b-instruct-turkish-finetuned.q5_k_s.gguf b/llama3-8b-instruct-turkish-finetuned.q5_k_s.gguf new file mode 100644 index 0000000..464ff17 --- /dev/null +++ b/llama3-8b-instruct-turkish-finetuned.q5_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d084df1857d4b01884e5a50f7d05b06fbe5c0302aed362740c17c05997a803f +size 5599294144 diff --git a/llama3-8b-instruct-turkish-finetuned.q6_k.gguf b/llama3-8b-instruct-turkish-finetuned.q6_k.gguf new file mode 100644 index 0000000..3a34e56 --- /dev/null +++ b/llama3-8b-instruct-turkish-finetuned.q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c2e2bacf0dc30c423f27a4042d3c55a889ba48bcb26af58fa8295dcb63faeb8 +size 6596006592