commit 301f941251b31c04a3a7f919b797ef43f280cc5b Author: ModelHub XC Date: Fri May 15 23:06:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: s3nh/ToolBench-ToolLLaMA-2-7b-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6753b85 --- /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 +ToolBench-ToolLLaMA-2-7b-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ToolBench-ToolLLaMA-2-7b-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ToolBench-ToolLLaMA-2-7b-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ToolBench-ToolLLaMA-2-7b-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ToolBench-ToolLLaMA-2-7b-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ToolBench-ToolLLaMA-2-7b-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ToolBench-ToolLLaMA-2-7b-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..072fea3 --- /dev/null +++ b/README.md @@ -0,0 +1,47 @@ + +--- +license: openrail +pipeline_tag: text-generation +library_name: transformers +language: +- zh +- en +--- + + +## Original model card + +Buy me a coffee if you like this project ;) + + +#### Description + +GGUF Format model files for [This project](https://huggingface.co/ToolBench/ToolLLaMA-2-7b-v1). + +### GGUF Specs + +GGUF is a format based on the existing GGJT, but makes a few changes to the format to make it more extensible and easier to use. The following features are desired: + +Single-file deployment: they can be easily distributed and loaded, and do not require any external files for additional information. +Extensible: new features can be added to GGML-based executors/new information can be added to GGUF models without breaking compatibility with existing models. +mmap compatibility: models can be loaded using mmap for fast loading and saving. +Easy to use: models can be easily loaded and saved using a small amount of code, with no need for external libraries, regardless of the language used. +Full information: all information needed to load a model is contained in the model file, and no additional information needs to be provided by the user. +The key difference between GGJT and GGUF is the use of a key-value structure for the hyperparameters (now referred to as metadata), rather than a list of untyped values. +This allows for new metadata to be added without breaking compatibility with existing models, and to annotate the model with additional information that may be useful for +inference or for identifying the model. + +### Perplexity params + +Model Measure Q2_K Q3_K_S Q3_K_M Q3_K_L Q4_0 Q4_1 Q4_K_S Q4_K_M Q5_0 Q5_1 Q5_K_S Q5_K_M Q6_K Q8_0 F16 +7B perplexity 6.7764 6.4571 6.1503 6.0869 6.1565 6.0912 6.0215 5.9601 5.9862 5.9481 5.9419 5.9208 5.9110 5.9070 5.9066 +13B perplexity 5.8545 5.6033 5.4498 5.4063 5.3860 5.3608 5.3404 5.3002 5.2856 5.2706 5.2785 5.2638 5.2568 5.2548 5.2543 + + + +### inference + + +TODO + +# Original model card diff --git a/ToolBench-ToolLLaMA-2-7b-v1.Q2_K.gguf b/ToolBench-ToolLLaMA-2-7b-v1.Q2_K.gguf new file mode 100644 index 0000000..77aca9b --- /dev/null +++ b/ToolBench-ToolLLaMA-2-7b-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b2ed3da68452b4b19d191bcf4de6b4a53da8c9369cc227ededd608d4b4b6786 +size 2825940672 diff --git a/ToolBench-ToolLLaMA-2-7b-v1.Q3_K_S.gguf b/ToolBench-ToolLLaMA-2-7b-v1.Q3_K_S.gguf new file mode 100644 index 0000000..0ebbe18 --- /dev/null +++ b/ToolBench-ToolLLaMA-2-7b-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdafc3d088f26f9305ab76cc2cca30df5580bc8aa37599c0e60f63b50c7d50a0 +size 2948304576 diff --git a/ToolBench-ToolLLaMA-2-7b-v1.Q4_K_M.gguf b/ToolBench-ToolLLaMA-2-7b-v1.Q4_K_M.gguf new file mode 100644 index 0000000..25d66bc --- /dev/null +++ b/ToolBench-ToolLLaMA-2-7b-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da23907003003b46650a832371f8ba02432442d6a57b4a9cf18ebc617f7782ad +size 4081004224 diff --git a/ToolBench-ToolLLaMA-2-7b-v1.Q4_K_S.gguf b/ToolBench-ToolLLaMA-2-7b-v1.Q4_K_S.gguf new file mode 100644 index 0000000..2209cb6 --- /dev/null +++ b/ToolBench-ToolLLaMA-2-7b-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19cb98550a98e8589e57b755359160ab720261f48cb0b4433dd67ca893a2fa97 +size 3856740032 diff --git a/ToolBench-ToolLLaMA-2-7b-v1.Q5_K_S.gguf b/ToolBench-ToolLLaMA-2-7b-v1.Q5_K_S.gguf new file mode 100644 index 0000000..7ffeb36 --- /dev/null +++ b/ToolBench-ToolLLaMA-2-7b-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bb07edc5a90f963c60e6de14d271bed9745305b2a6f4db15cf019787663c97e +size 4651691712 diff --git a/ToolBench-ToolLLaMA-2-7b-v1.Q6_K.gguf b/ToolBench-ToolLLaMA-2-7b-v1.Q6_K.gguf new file mode 100644 index 0000000..0cfe2c3 --- /dev/null +++ b/ToolBench-ToolLLaMA-2-7b-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67c5fff07a1bb921b873b9953a65c0fb3f2594f17676c399f5445d3b57e5cf59 +size 5529194176 diff --git a/ToolBench-ToolLLaMA-2-7b-v1.Q8_0.gguf b/ToolBench-ToolLLaMA-2-7b-v1.Q8_0.gguf new file mode 100644 index 0000000..187dbc3 --- /dev/null +++ b/ToolBench-ToolLLaMA-2-7b-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:955a68ce418250b849ef77d4aa95bce0c63421d24e3896e47bb8eb1985b9d4e6 +size 7161089728