commit 311a99e5d38e584a04a7e1cab58ed1e1438e584d Author: ModelHub XC Date: Thu Jul 30 10:03:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLaMA-3.1-8B-Function-Calling-FP16-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cb7f12d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-3.1-8B-Function-Calling-FP16.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Function-Calling-FP16.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Function-Calling-FP16.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Function-Calling-FP16.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Function-Calling-FP16.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Function-Calling-FP16.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Function-Calling-FP16.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Function-Calling-FP16.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Function-Calling-FP16.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Function-Calling-FP16.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Function-Calling-FP16.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Function-Calling-FP16.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Function-Calling-FP16.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Function-Calling-FP16.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Function-Calling-FP16.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLaMA-3.1-8B-Function-Calling-FP16.IQ3_M.gguf b/LLaMA-3.1-8B-Function-Calling-FP16.IQ3_M.gguf new file mode 100644 index 0000000..7709448 --- /dev/null +++ b/LLaMA-3.1-8B-Function-Calling-FP16.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17c48f05b176f6d07e435bade5458ee71ec0d11e0681ba18cc487a020f355718 +size 3784824160 diff --git a/LLaMA-3.1-8B-Function-Calling-FP16.IQ3_S.gguf b/LLaMA-3.1-8B-Function-Calling-FP16.IQ3_S.gguf new file mode 100644 index 0000000..667f2c4 --- /dev/null +++ b/LLaMA-3.1-8B-Function-Calling-FP16.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d54d8e96cf75bcfb7a69eafbf46e1b6a6ff2efda936d5276c7b32dd816d6d16 +size 3682325856 diff --git a/LLaMA-3.1-8B-Function-Calling-FP16.IQ3_XS.gguf b/LLaMA-3.1-8B-Function-Calling-FP16.IQ3_XS.gguf new file mode 100644 index 0000000..713dad8 --- /dev/null +++ b/LLaMA-3.1-8B-Function-Calling-FP16.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e119d13362c22576ce3270dbf228c462043f9a4fec1435daf8585580686f9a7 +size 3518748000 diff --git a/LLaMA-3.1-8B-Function-Calling-FP16.IQ4_XS.gguf b/LLaMA-3.1-8B-Function-Calling-FP16.IQ4_XS.gguf new file mode 100644 index 0000000..bef88f9 --- /dev/null +++ b/LLaMA-3.1-8B-Function-Calling-FP16.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58c3de4e544b6a653943092c00356c63914d9df9470058b7c89555d45bc6b35a +size 4484363616 diff --git a/LLaMA-3.1-8B-Function-Calling-FP16.Q2_K.gguf b/LLaMA-3.1-8B-Function-Calling-FP16.Q2_K.gguf new file mode 100644 index 0000000..63d8794 --- /dev/null +++ b/LLaMA-3.1-8B-Function-Calling-FP16.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67edb2022eb76b2d32196d6d902d6060f604e7cf8b41e175cc31fa443c5df5d8 +size 3179132256 diff --git a/LLaMA-3.1-8B-Function-Calling-FP16.Q3_K_L.gguf b/LLaMA-3.1-8B-Function-Calling-FP16.Q3_K_L.gguf new file mode 100644 index 0000000..9105ba7 --- /dev/null +++ b/LLaMA-3.1-8B-Function-Calling-FP16.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b38b59335a5b48d3bc1c0161eaa755260635a7a7c5f10445f3a5a22a4afb9fc +size 4321957216 diff --git a/LLaMA-3.1-8B-Function-Calling-FP16.Q3_K_M.gguf b/LLaMA-3.1-8B-Function-Calling-FP16.Q3_K_M.gguf new file mode 100644 index 0000000..26f21f8 --- /dev/null +++ b/LLaMA-3.1-8B-Function-Calling-FP16.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28852b3cdd85af3ffcda784ca61b5395885302ac5061be0f215ccf734d296304 +size 4018918752 diff --git a/LLaMA-3.1-8B-Function-Calling-FP16.Q3_K_S.gguf b/LLaMA-3.1-8B-Function-Calling-FP16.Q3_K_S.gguf new file mode 100644 index 0000000..f0e7fa3 --- /dev/null +++ b/LLaMA-3.1-8B-Function-Calling-FP16.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a296b21b8bd8cd3f770c4979448ca1fc7ab46031da1a432dd73a04494d2dc195 +size 3664500064 diff --git a/LLaMA-3.1-8B-Function-Calling-FP16.Q4_K_M.gguf b/LLaMA-3.1-8B-Function-Calling-FP16.Q4_K_M.gguf new file mode 100644 index 0000000..1ba4fe9 --- /dev/null +++ b/LLaMA-3.1-8B-Function-Calling-FP16.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa3c4962fe2932219be773994b73009281950a2aa70c2ddea91fdbdce698771d +size 4920735072 diff --git a/LLaMA-3.1-8B-Function-Calling-FP16.Q4_K_S.gguf b/LLaMA-3.1-8B-Function-Calling-FP16.Q4_K_S.gguf new file mode 100644 index 0000000..8f4181e --- /dev/null +++ b/LLaMA-3.1-8B-Function-Calling-FP16.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:104617878c8d43eb9d9efb16bb0871f1e13439cc2363cf763a053fb1822332ef +size 4692669792 diff --git a/LLaMA-3.1-8B-Function-Calling-FP16.Q5_K_M.gguf b/LLaMA-3.1-8B-Function-Calling-FP16.Q5_K_M.gguf new file mode 100644 index 0000000..4fdb1ab --- /dev/null +++ b/LLaMA-3.1-8B-Function-Calling-FP16.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12227f37fa5636db5f1a3b0420ff98a31aa7becc7f434f50c88e076932cf9e84 +size 5732988256 diff --git a/LLaMA-3.1-8B-Function-Calling-FP16.Q5_K_S.gguf b/LLaMA-3.1-8B-Function-Calling-FP16.Q5_K_S.gguf new file mode 100644 index 0000000..c028f5a --- /dev/null +++ b/LLaMA-3.1-8B-Function-Calling-FP16.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:242a925a84f5b5ca0b971d045034f22b631b8d587a8554a40402caa96344eec9 +size 5599294816 diff --git a/LLaMA-3.1-8B-Function-Calling-FP16.Q6_K.gguf b/LLaMA-3.1-8B-Function-Calling-FP16.Q6_K.gguf new file mode 100644 index 0000000..1ed84d0 --- /dev/null +++ b/LLaMA-3.1-8B-Function-Calling-FP16.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c95a5f5c34b2656096fb624b5e9ed0975aa7cc8a60a726a8f0fbc0af1b076e0 +size 6596007264 diff --git a/LLaMA-3.1-8B-Function-Calling-FP16.Q8_0.gguf b/LLaMA-3.1-8B-Function-Calling-FP16.Q8_0.gguf new file mode 100644 index 0000000..e4af3f4 --- /dev/null +++ b/LLaMA-3.1-8B-Function-Calling-FP16.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4226ba6d1aa5c4fce0be17961d121c734b208e6929a9101aaa8455435e95e715 +size 8540771680 diff --git a/LLaMA-3.1-8B-Function-Calling-FP16.f16.gguf b/LLaMA-3.1-8B-Function-Calling-FP16.f16.gguf new file mode 100644 index 0000000..87497c7 --- /dev/null +++ b/LLaMA-3.1-8B-Function-Calling-FP16.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1270faad61d7379509eb5bc9886ca20aadfa748fb8b7771cf0a06bc520237253 +size 16068892000 diff --git a/README.md b/README.md new file mode 100644 index 0000000..016b20d --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: OpenSourceEnjoyer/LLaMA-3.1-8B-Function-Calling-FP16 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/OpenSourceEnjoyer/LLaMA-3.1-8B-Function-Calling-FP16 + + +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/LLaMA-3.1-8B-Function-Calling-FP16-GGUF/resolve/main/LLaMA-3.1-8B-Function-Calling-FP16.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Function-Calling-FP16-GGUF/resolve/main/LLaMA-3.1-8B-Function-Calling-FP16.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Function-Calling-FP16-GGUF/resolve/main/LLaMA-3.1-8B-Function-Calling-FP16.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Function-Calling-FP16-GGUF/resolve/main/LLaMA-3.1-8B-Function-Calling-FP16.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Function-Calling-FP16-GGUF/resolve/main/LLaMA-3.1-8B-Function-Calling-FP16.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Function-Calling-FP16-GGUF/resolve/main/LLaMA-3.1-8B-Function-Calling-FP16.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Function-Calling-FP16-GGUF/resolve/main/LLaMA-3.1-8B-Function-Calling-FP16.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Function-Calling-FP16-GGUF/resolve/main/LLaMA-3.1-8B-Function-Calling-FP16.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Function-Calling-FP16-GGUF/resolve/main/LLaMA-3.1-8B-Function-Calling-FP16.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Function-Calling-FP16-GGUF/resolve/main/LLaMA-3.1-8B-Function-Calling-FP16.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Function-Calling-FP16-GGUF/resolve/main/LLaMA-3.1-8B-Function-Calling-FP16.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Function-Calling-FP16-GGUF/resolve/main/LLaMA-3.1-8B-Function-Calling-FP16.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Function-Calling-FP16-GGUF/resolve/main/LLaMA-3.1-8B-Function-Calling-FP16.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Function-Calling-FP16-GGUF/resolve/main/LLaMA-3.1-8B-Function-Calling-FP16.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Function-Calling-FP16-GGUF/resolve/main/LLaMA-3.1-8B-Function-Calling-FP16.f16.gguf) | f16 | 16.2 | 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. + +