commit 1d4ce8548e286c7941063a7f08d1541f03ff769a Author: ModelHub XC Date: Sun Sep 20 18:54:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.1-8b-sarcasm-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4207cc3 --- /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-3.1-8b-sarcasm.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-sarcasm.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-sarcasm.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-sarcasm.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-sarcasm.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-sarcasm.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-sarcasm.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-sarcasm.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-sarcasm.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-sarcasm.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-sarcasm.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-sarcasm.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9a66385 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Gauri-tr/llama-3.1-8b-sarcasm +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Gauri-tr/llama-3.1-8b-sarcasm + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3.1-8b-sarcasm-GGUF).*** + +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-sarcasm-GGUF/resolve/main/llama-3.1-8b-sarcasm.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-sarcasm-GGUF/resolve/main/llama-3.1-8b-sarcasm.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-sarcasm-GGUF/resolve/main/llama-3.1-8b-sarcasm.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-sarcasm-GGUF/resolve/main/llama-3.1-8b-sarcasm.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-sarcasm-GGUF/resolve/main/llama-3.1-8b-sarcasm.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-sarcasm-GGUF/resolve/main/llama-3.1-8b-sarcasm.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-sarcasm-GGUF/resolve/main/llama-3.1-8b-sarcasm.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-sarcasm-GGUF/resolve/main/llama-3.1-8b-sarcasm.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-sarcasm-GGUF/resolve/main/llama-3.1-8b-sarcasm.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-sarcasm-GGUF/resolve/main/llama-3.1-8b-sarcasm.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-sarcasm-GGUF/resolve/main/llama-3.1-8b-sarcasm.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-sarcasm-GGUF/resolve/main/llama-3.1-8b-sarcasm.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. + + diff --git a/llama-3.1-8b-sarcasm.IQ4_XS.gguf b/llama-3.1-8b-sarcasm.IQ4_XS.gguf new file mode 100644 index 0000000..9ca5012 --- /dev/null +++ b/llama-3.1-8b-sarcasm.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2a6f4d56b4f7be9f4a4947442f9193958ccc865dc7a8a280d5e44e144262e69 +size 4484367808 diff --git a/llama-3.1-8b-sarcasm.Q2_K.gguf b/llama-3.1-8b-sarcasm.Q2_K.gguf new file mode 100644 index 0000000..6a04985 --- /dev/null +++ b/llama-3.1-8b-sarcasm.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e737a143abf713834c42355a3524aae5523c029735f92a3636a7cceb203c0607 +size 3179136448 diff --git a/llama-3.1-8b-sarcasm.Q3_K_L.gguf b/llama-3.1-8b-sarcasm.Q3_K_L.gguf new file mode 100644 index 0000000..048b81e --- /dev/null +++ b/llama-3.1-8b-sarcasm.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0033a0606517389b046144ef8f2d4a8e89a1090a5c0aa535cb05f43508932bf +size 4321961408 diff --git a/llama-3.1-8b-sarcasm.Q3_K_M.gguf b/llama-3.1-8b-sarcasm.Q3_K_M.gguf new file mode 100644 index 0000000..0c4462c --- /dev/null +++ b/llama-3.1-8b-sarcasm.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6168a0a456df31296f3afcca6c67b1453bae8e97213160447f2de78a01cb822 +size 4018922944 diff --git a/llama-3.1-8b-sarcasm.Q3_K_S.gguf b/llama-3.1-8b-sarcasm.Q3_K_S.gguf new file mode 100644 index 0000000..ed69e16 --- /dev/null +++ b/llama-3.1-8b-sarcasm.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f787e622bfd3204f10233675591b216126960e7e4ccef2fc23646528ed35b812 +size 3664504256 diff --git a/llama-3.1-8b-sarcasm.Q4_K_M.gguf b/llama-3.1-8b-sarcasm.Q4_K_M.gguf new file mode 100644 index 0000000..03d474b --- /dev/null +++ b/llama-3.1-8b-sarcasm.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2efcbbc290ff9ec2fc5d908cbf16110f42a64b1bcecd094f97799e96f38a44a +size 4920739264 diff --git a/llama-3.1-8b-sarcasm.Q4_K_S.gguf b/llama-3.1-8b-sarcasm.Q4_K_S.gguf new file mode 100644 index 0000000..46dff78 --- /dev/null +++ b/llama-3.1-8b-sarcasm.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe0a13e502e00a9744ffb2d4c86659eab6919ba2bb26bc6967de955b0ca9a06c +size 4692673984 diff --git a/llama-3.1-8b-sarcasm.Q5_K_M.gguf b/llama-3.1-8b-sarcasm.Q5_K_M.gguf new file mode 100644 index 0000000..4e6991e --- /dev/null +++ b/llama-3.1-8b-sarcasm.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:270667bdd48d7fb7343b1bf18861ef69d635dc5323dd4f601ab49c7627a681d5 +size 5732992448 diff --git a/llama-3.1-8b-sarcasm.Q5_K_S.gguf b/llama-3.1-8b-sarcasm.Q5_K_S.gguf new file mode 100644 index 0000000..a24f9c9 --- /dev/null +++ b/llama-3.1-8b-sarcasm.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56fd7053dc141079e3ff0241355811865f5fc550807acc8fd32dab886d748985 +size 5599299008 diff --git a/llama-3.1-8b-sarcasm.Q6_K.gguf b/llama-3.1-8b-sarcasm.Q6_K.gguf new file mode 100644 index 0000000..d2a6f84 --- /dev/null +++ b/llama-3.1-8b-sarcasm.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b15909ef9919a4f13ef12edd9b653329c30843a5c2fe22fe444e37d6197ab46 +size 6596011456 diff --git a/llama-3.1-8b-sarcasm.Q8_0.gguf b/llama-3.1-8b-sarcasm.Q8_0.gguf new file mode 100644 index 0000000..6f2ca3b --- /dev/null +++ b/llama-3.1-8b-sarcasm.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ce19a801c41c80551779b248d55f15ac1aaffee988917d7db6915fe61525604 +size 8540775872 diff --git a/llama-3.1-8b-sarcasm.f16.gguf b/llama-3.1-8b-sarcasm.f16.gguf new file mode 100644 index 0000000..d935d33 --- /dev/null +++ b/llama-3.1-8b-sarcasm.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee81250aa2b12cc771dd9627555237800863e9ac0d0e453bca1c111e97feaf95 +size 16068896192