commit de3d620ca78b342d4af6388c95b22eebb67c0dc6 Author: ModelHub XC Date: Mon Apr 27 22:09:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: akumaburn/llama-3-8b-bnb-4bit-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1022f62 --- /dev/null +++ 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 +llama-3-8b-bnb-4bit-GGUF-unsloth.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-bnb-4bit-GGUF-unsloth.F16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-bnb-4bit-GGUF-unsloth.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-bnb-4bit-GGUF-unsloth.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-bnb-4bit-GGUF-unsloth.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-bnb-4bit-GGUF-unsloth.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-bnb-4bit-GGUF-unsloth.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..641007e --- /dev/null +++ b/README.md @@ -0,0 +1,24 @@ +--- +language: +- en +license: apache-2.0 +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- gguf +base_model: unsloth/llama-3-8b-bnb-4bit +--- + +# Uploaded model + +- **Developed by:** akumaburn +- **License:** apache-2.0 +- **Un-finetuned model :** unsloth/llama-3-8b-bnb-4bit + +This llama model was quantized from https://huggingface.co/unsloth/llama-3-8b-bnb-4bit/tree/main without any finetuning. + +Using [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. + +[](https://github.com/unslothai/unsloth) diff --git a/config.json b/config.json new file mode 100644 index 0000000..a4ba21b --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "llama" +} \ No newline at end of file diff --git a/llama-3-8b-bnb-4bit-GGUF-unsloth.F16.gguf b/llama-3-8b-bnb-4bit-GGUF-unsloth.F16.gguf new file mode 100644 index 0000000..1dcfab8 --- /dev/null +++ b/llama-3-8b-bnb-4bit-GGUF-unsloth.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:050931f88854437307c46890425319737adc99c937e5a1d88baeb726e8cc94b1 +size 16069403488 diff --git a/llama-3-8b-bnb-4bit-GGUF-unsloth.Q2_K.gguf b/llama-3-8b-bnb-4bit-GGUF-unsloth.Q2_K.gguf new file mode 100644 index 0000000..3767f64 --- /dev/null +++ b/llama-3-8b-bnb-4bit-GGUF-unsloth.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bab9802c3f8291ca9bd1958cd8d376d76b6ede0595d157909ad4d8f49fc773d +size 3179643776 diff --git a/llama-3-8b-bnb-4bit-GGUF-unsloth.Q3_K_M.gguf b/llama-3-8b-bnb-4bit-GGUF-unsloth.Q3_K_M.gguf new file mode 100644 index 0000000..ce1bd1e --- /dev/null +++ b/llama-3-8b-bnb-4bit-GGUF-unsloth.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4662b8597625441207e922e284fc6a75d487ab372711e6fef86f1e4d6874b148 +size 4019430272 diff --git a/llama-3-8b-bnb-4bit-GGUF-unsloth.Q4_K_M.gguf b/llama-3-8b-bnb-4bit-GGUF-unsloth.Q4_K_M.gguf new file mode 100644 index 0000000..4528881 --- /dev/null +++ b/llama-3-8b-bnb-4bit-GGUF-unsloth.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fe82f8cefe27c8640aac332a281482ca6157fa5331d178133eaa5eaf0fd27bc +size 4921246592 diff --git a/llama-3-8b-bnb-4bit-GGUF-unsloth.Q5_K_M.gguf b/llama-3-8b-bnb-4bit-GGUF-unsloth.Q5_K_M.gguf new file mode 100644 index 0000000..1466fcd --- /dev/null +++ b/llama-3-8b-bnb-4bit-GGUF-unsloth.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:351ba68e6c781a2d541f8d4282544b821abf04198e55a1852b1f7510cd3d14d4 +size 5733499776 diff --git a/llama-3-8b-bnb-4bit-GGUF-unsloth.Q6_K.gguf b/llama-3-8b-bnb-4bit-GGUF-unsloth.Q6_K.gguf new file mode 100644 index 0000000..bdd996a --- /dev/null +++ b/llama-3-8b-bnb-4bit-GGUF-unsloth.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f3b31923649a6ead55d0226916e49bd64d57d8fae8a7b8a7fcdf0d1e40519ae +size 6596518784 diff --git a/llama-3-8b-bnb-4bit-GGUF-unsloth.Q8_0.gguf b/llama-3-8b-bnb-4bit-GGUF-unsloth.Q8_0.gguf new file mode 100644 index 0000000..57acdbb --- /dev/null +++ b/llama-3-8b-bnb-4bit-GGUF-unsloth.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0c6b5b50923e7691f3c84a1473212daea0ca71a520670cdf5381efb426a95d8 +size 8541283168