commit f757ca07e84b87b7616a4d42a7e25b77724f592a Author: ModelHub XC Date: Mon Jun 15 22:26:30 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.3-8B-Instruct-128K-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3ff4cb5 --- /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 +Llama-3.3-8B-Instruct-128K.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-128K.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.3-8B-Instruct-128K.IQ4_XS.gguf b/Llama-3.3-8B-Instruct-128K.IQ4_XS.gguf new file mode 100644 index 0000000..e0dfad2 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebfcfbb421450c797ebb0ec2d7a89107bc758a82eb4a99c8d85195384846afc3 +size 4484368320 diff --git a/Llama-3.3-8B-Instruct-128K.Q2_K.gguf b/Llama-3.3-8B-Instruct-128K.Q2_K.gguf new file mode 100644 index 0000000..f6a335c --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adfda6d6dd58217a014aebf20b6c01faa5a140c2a2385dabc9e1c1fc7c622a8e +size 3179136960 diff --git a/Llama-3.3-8B-Instruct-128K.Q3_K_L.gguf b/Llama-3.3-8B-Instruct-128K.Q3_K_L.gguf new file mode 100644 index 0000000..d625e74 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:538d7fa6cb3dece01ce7837ebc3ec81af56f5c913bb1c466c59b99f03fd5e77b +size 4321961920 diff --git a/Llama-3.3-8B-Instruct-128K.Q3_K_M.gguf b/Llama-3.3-8B-Instruct-128K.Q3_K_M.gguf new file mode 100644 index 0000000..53f7862 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:642b5ba1aea61f3b8bfed2390b5232fd70173c5f0eaed06d181b6b7588fe1742 +size 4018923456 diff --git a/Llama-3.3-8B-Instruct-128K.Q3_K_S.gguf b/Llama-3.3-8B-Instruct-128K.Q3_K_S.gguf new file mode 100644 index 0000000..bcd9f41 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321eca3fd04df924aec56c75a33b2ffa04df5f35d3955c3536403a589229bae9 +size 3664504768 diff --git a/Llama-3.3-8B-Instruct-128K.Q4_K_M.gguf b/Llama-3.3-8B-Instruct-128K.Q4_K_M.gguf new file mode 100644 index 0000000..632dc86 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44113d84c56968a10451e24f15e08f5b94734904c69f56b6a201c28b20ab4cda +size 4920739776 diff --git a/Llama-3.3-8B-Instruct-128K.Q4_K_S.gguf b/Llama-3.3-8B-Instruct-128K.Q4_K_S.gguf new file mode 100644 index 0000000..1043092 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bf60268e909203af44b627131702c23ce9e8e8f9506682fddce31121eac507b +size 4692674496 diff --git a/Llama-3.3-8B-Instruct-128K.Q5_K_M.gguf b/Llama-3.3-8B-Instruct-128K.Q5_K_M.gguf new file mode 100644 index 0000000..90ff001 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae76a09965ecf70ca8b5b3f3a00877087468f2d0bc09671c33701e436edbcb40 +size 5732992960 diff --git a/Llama-3.3-8B-Instruct-128K.Q5_K_S.gguf b/Llama-3.3-8B-Instruct-128K.Q5_K_S.gguf new file mode 100644 index 0000000..9aa7e6b --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de6e3f157c43df977ab140090ff5a388b56056633b6f64b263e71eda6f6d5c0d +size 5599299520 diff --git a/Llama-3.3-8B-Instruct-128K.Q6_K.gguf b/Llama-3.3-8B-Instruct-128K.Q6_K.gguf new file mode 100644 index 0000000..d7b0c63 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bf84168c92997f0d2b621b7949c072ade16b03e5aacfe890370dfd8c09bf374 +size 6596011968 diff --git a/Llama-3.3-8B-Instruct-128K.Q8_0.gguf b/Llama-3.3-8B-Instruct-128K.Q8_0.gguf new file mode 100644 index 0000000..fe4e491 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf988684d30be55b0c144e27df3980e9dd095cbd0f5c7085a9a248d746f0f512 +size 8540776384 diff --git a/Llama-3.3-8B-Instruct-128K.f16.gguf b/Llama-3.3-8B-Instruct-128K.f16.gguf new file mode 100644 index 0000000..ce86b49 --- /dev/null +++ b/Llama-3.3-8B-Instruct-128K.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58117e384b2db5d2cf046882dd8c79dc80a7159003287b58d6821374f8770957 +size 16068896704 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cffdf6c --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: shb777/Llama-3.3-8B-Instruct-128K +language: +- en +library_name: transformers +license: llama3.3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/shb777/Llama-3.3-8B-Instruct-128K + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.3-8B-Instruct-128K-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-i1-GGUF +## 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-3.3-8B-Instruct-128K-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-128K-GGUF/resolve/main/Llama-3.3-8B-Instruct-128K.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. + +