commit 73816fde4fcfaca444512331ed6962bfeb0556e6 Author: ModelHub XC Date: Thu Oct 22 04:02:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ToolGen-WoSystem-Llama-3-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e1611f1 --- /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 +ToolGen-WoSystem-Llama-3-8B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-WoSystem-Llama-3-8B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-WoSystem-Llama-3-8B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-WoSystem-Llama-3-8B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-WoSystem-Llama-3-8B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-WoSystem-Llama-3-8B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-WoSystem-Llama-3-8B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-WoSystem-Llama-3-8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-WoSystem-Llama-3-8B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-WoSystem-Llama-3-8B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-WoSystem-Llama-3-8B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-WoSystem-Llama-3-8B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c38ddde --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: reasonwang/ToolGen-WoSystem-Llama-3-8B-Instruct +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/reasonwang/ToolGen-WoSystem-Llama-3-8B-Instruct + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/ToolGen-WoSystem-Llama-3-8B-Instruct-GGUF/resolve/main/ToolGen-WoSystem-Llama-3-8B-Instruct.Q2_K.gguf) | Q2_K | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-WoSystem-Llama-3-8B-Instruct-GGUF/resolve/main/ToolGen-WoSystem-Llama-3-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-WoSystem-Llama-3-8B-Instruct-GGUF/resolve/main/ToolGen-WoSystem-Llama-3-8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-WoSystem-Llama-3-8B-Instruct-GGUF/resolve/main/ToolGen-WoSystem-Llama-3-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-WoSystem-Llama-3-8B-Instruct-GGUF/resolve/main/ToolGen-WoSystem-Llama-3-8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-WoSystem-Llama-3-8B-Instruct-GGUF/resolve/main/ToolGen-WoSystem-Llama-3-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-WoSystem-Llama-3-8B-Instruct-GGUF/resolve/main/ToolGen-WoSystem-Llama-3-8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-WoSystem-Llama-3-8B-Instruct-GGUF/resolve/main/ToolGen-WoSystem-Llama-3-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-WoSystem-Llama-3-8B-Instruct-GGUF/resolve/main/ToolGen-WoSystem-Llama-3-8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 6.1 | | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-WoSystem-Llama-3-8B-Instruct-GGUF/resolve/main/ToolGen-WoSystem-Llama-3-8B-Instruct.Q6_K.gguf) | Q6_K | 7.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-WoSystem-Llama-3-8B-Instruct-GGUF/resolve/main/ToolGen-WoSystem-Llama-3-8B-Instruct.Q8_0.gguf) | Q8_0 | 9.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-WoSystem-Llama-3-8B-Instruct-GGUF/resolve/main/ToolGen-WoSystem-Llama-3-8B-Instruct.f16.gguf) | f16 | 16.9 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + + diff --git a/ToolGen-WoSystem-Llama-3-8B-Instruct.IQ4_XS.gguf b/ToolGen-WoSystem-Llama-3-8B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..1bab35e --- /dev/null +++ b/ToolGen-WoSystem-Llama-3-8B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e169a126939f7657a2302a3047f64bc4310c61b456038d1105f938e6275b0829 +size 4746882464 diff --git a/ToolGen-WoSystem-Llama-3-8B-Instruct.Q2_K.gguf b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..764f094 --- /dev/null +++ b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31fc29014a417baf08a3166eead928922ee033c07342db73c239468ff462c03e +size 3402559584 diff --git a/ToolGen-WoSystem-Llama-3-8B-Instruct.Q3_K_L.gguf b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..ca5d139 --- /dev/null +++ b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b930ab88e99cdd2926acbc2df94f5540f9cb319d023180fef07ade138bd7687f +size 4564930304 diff --git a/ToolGen-WoSystem-Llama-3-8B-Instruct.Q3_K_M.gguf b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..405231e --- /dev/null +++ b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6702960bce611bdb420a2daa189a36adf81035577b4b4da424b7ab0076c15b8 +size 4261891840 diff --git a/ToolGen-WoSystem-Llama-3-8B-Instruct.Q3_K_S.gguf b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..55f9cc3 --- /dev/null +++ b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e79a04567c6bdf737bab42f23e05011ba40064ee7b64a5b6e5036887d9b5dcd5 +size 3907473152 diff --git a/ToolGen-WoSystem-Llama-3-8B-Instruct.Q4_K_M.gguf b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..9ac827b --- /dev/null +++ b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22b4cd0d3617f73ca0cfdad9e4d786b04554a9d4aaac546a8dc7e93f2d775f8d +size 5189268000 diff --git a/ToolGen-WoSystem-Llama-3-8B-Instruct.Q4_K_S.gguf b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..5c83346 --- /dev/null +++ b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a85b2b8a1d989ebf526561d711cd1fd48f35fcc466f01430136a6c05f5d2cc77 +size 4961202720 diff --git a/ToolGen-WoSystem-Llama-3-8B-Instruct.Q5_K_M.gguf b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..ec49863 --- /dev/null +++ b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d74ae80fa187af5cdfb1f4a66ef99ec2e2e48dcf398f80a2d697f674232e4d4 +size 6025577504 diff --git a/ToolGen-WoSystem-Llama-3-8B-Instruct.Q5_K_S.gguf b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..afaaf98 --- /dev/null +++ b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a26577ab447dd4cd782eddacf122763e84231ba28ce723cf490883a73783036 +size 5891884064 diff --git a/ToolGen-WoSystem-Llama-3-8B-Instruct.Q6_K.gguf b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..e87e79c --- /dev/null +++ b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c60c08f097f588d08668146fc35eab4e835da4c530f9ff70f8dc1d0a24ab33ca +size 6914156352 diff --git a/ToolGen-WoSystem-Llama-3-8B-Instruct.Q8_0.gguf b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..89f19fd --- /dev/null +++ b/ToolGen-WoSystem-Llama-3-8B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af325500a868852d490dcc1e7914e007947c410b33531d30b43fe0120b30e8ab +size 8952139008 diff --git a/ToolGen-WoSystem-Llama-3-8B-Instruct.f16.gguf b/ToolGen-WoSystem-Llama-3-8B-Instruct.f16.gguf new file mode 100644 index 0000000..938062c --- /dev/null +++ b/ToolGen-WoSystem-Llama-3-8B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78aff33a760abd41d4c57946e44abf0424a6446247063711104e8f37438016d8 +size 16841104128