commit 3f682330ab018262ad6fa12b61b01d63da007009 Author: ModelHub XC Date: Fri Apr 17 15:41:37 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KamalaHarris-Llama-3.1-8B-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5f33d8b --- /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 +KamalaHarris-Llama-3.1-8B-Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KamalaHarris-Llama-3.1-8B-Chat.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +KamalaHarris-Llama-3.1-8B-Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KamalaHarris-Llama-3.1-8B-Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text +KamalaHarris-Llama-3.1-8B-Chat.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +KamalaHarris-Llama-3.1-8B-Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KamalaHarris-Llama-3.1-8B-Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KamalaHarris-Llama-3.1-8B-Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KamalaHarris-Llama-3.1-8B-Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KamalaHarris-Llama-3.1-8B-Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KamalaHarris-Llama-3.1-8B-Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KamalaHarris-Llama-3.1-8B-Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KamalaHarris-Llama-3.1-8B-Chat.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +KamalaHarris-Llama-3.1-8B-Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KamalaHarris-Llama-3.1-8B-Chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KamalaHarris-Llama-3.1-8B-Chat.IQ3_M.gguf b/KamalaHarris-Llama-3.1-8B-Chat.IQ3_M.gguf new file mode 100644 index 0000000..c894afe --- /dev/null +++ b/KamalaHarris-Llama-3.1-8B-Chat.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7434b8bb60b28e1527f288bbf859e6f4817f95743db5926613968257d283a5d8 +size 3784824320 diff --git a/KamalaHarris-Llama-3.1-8B-Chat.IQ3_S.gguf b/KamalaHarris-Llama-3.1-8B-Chat.IQ3_S.gguf new file mode 100644 index 0000000..8b93b33 --- /dev/null +++ b/KamalaHarris-Llama-3.1-8B-Chat.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7a15dde619d1022f3207ded8014ef248f4c4de8d99184ab66d891083df6903a +size 3682326016 diff --git a/KamalaHarris-Llama-3.1-8B-Chat.IQ3_XS.gguf b/KamalaHarris-Llama-3.1-8B-Chat.IQ3_XS.gguf new file mode 100644 index 0000000..82e63a5 --- /dev/null +++ b/KamalaHarris-Llama-3.1-8B-Chat.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:090eeacb76aac0bd97c438036ce402847c621d4fd66a62647bec0915c8cfb5ea +size 3518748160 diff --git a/KamalaHarris-Llama-3.1-8B-Chat.IQ4_XS.gguf b/KamalaHarris-Llama-3.1-8B-Chat.IQ4_XS.gguf new file mode 100644 index 0000000..4ba4555 --- /dev/null +++ b/KamalaHarris-Llama-3.1-8B-Chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63c16c5f91cb62dcea072bb9a5669e7f4694d0bab7d7585d1f2da774c926f199 +size 4484363776 diff --git a/KamalaHarris-Llama-3.1-8B-Chat.Q2_K.gguf b/KamalaHarris-Llama-3.1-8B-Chat.Q2_K.gguf new file mode 100644 index 0000000..ca50e57 --- /dev/null +++ b/KamalaHarris-Llama-3.1-8B-Chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa6f20260d0fff3c659af943f610618d94a7feeef1fd17f0918a07d7b1ae98dd +size 3179132416 diff --git a/KamalaHarris-Llama-3.1-8B-Chat.Q3_K_L.gguf b/KamalaHarris-Llama-3.1-8B-Chat.Q3_K_L.gguf new file mode 100644 index 0000000..b368b87 --- /dev/null +++ b/KamalaHarris-Llama-3.1-8B-Chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fa6724ede0f9d4f045ebc7232a0411a7aa02b9f39df5480ce02143bd262edf4 +size 4321957376 diff --git a/KamalaHarris-Llama-3.1-8B-Chat.Q3_K_M.gguf b/KamalaHarris-Llama-3.1-8B-Chat.Q3_K_M.gguf new file mode 100644 index 0000000..f837e28 --- /dev/null +++ b/KamalaHarris-Llama-3.1-8B-Chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92a2366b043c4d4d833497489e3772d6f7bf665a947ef30327b6e1d57edc94c5 +size 4018918912 diff --git a/KamalaHarris-Llama-3.1-8B-Chat.Q3_K_S.gguf b/KamalaHarris-Llama-3.1-8B-Chat.Q3_K_S.gguf new file mode 100644 index 0000000..67e768c --- /dev/null +++ b/KamalaHarris-Llama-3.1-8B-Chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a03ff171955934c550507a838b9219a780846bf3eba21502180c7c6010688088 +size 3664500224 diff --git a/KamalaHarris-Llama-3.1-8B-Chat.Q4_K_M.gguf b/KamalaHarris-Llama-3.1-8B-Chat.Q4_K_M.gguf new file mode 100644 index 0000000..0852890 --- /dev/null +++ b/KamalaHarris-Llama-3.1-8B-Chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11f96dedaaa2fd19aa2a77060444833b624e7841f00f5c22eabd67b0c8fb68da +size 4920735232 diff --git a/KamalaHarris-Llama-3.1-8B-Chat.Q4_K_S.gguf b/KamalaHarris-Llama-3.1-8B-Chat.Q4_K_S.gguf new file mode 100644 index 0000000..3de12e0 --- /dev/null +++ b/KamalaHarris-Llama-3.1-8B-Chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb1f599e5468d2f42c7040a7f3b591fd820b7709f00dd8c92b3e76727659d455 +size 4692669952 diff --git a/KamalaHarris-Llama-3.1-8B-Chat.Q5_K_M.gguf b/KamalaHarris-Llama-3.1-8B-Chat.Q5_K_M.gguf new file mode 100644 index 0000000..c5b3836 --- /dev/null +++ b/KamalaHarris-Llama-3.1-8B-Chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1762b139f1c28c6a6b8cf651ce8935142e6885ea87b9ed9a5405f5807c1d2d45 +size 5732988416 diff --git a/KamalaHarris-Llama-3.1-8B-Chat.Q5_K_S.gguf b/KamalaHarris-Llama-3.1-8B-Chat.Q5_K_S.gguf new file mode 100644 index 0000000..acda0e8 --- /dev/null +++ b/KamalaHarris-Llama-3.1-8B-Chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7641c224b5616914cd0f721f06871de88437e828cd5122261ce39d1f28dad77b +size 5599294976 diff --git a/KamalaHarris-Llama-3.1-8B-Chat.Q6_K.gguf b/KamalaHarris-Llama-3.1-8B-Chat.Q6_K.gguf new file mode 100644 index 0000000..bef82ff --- /dev/null +++ b/KamalaHarris-Llama-3.1-8B-Chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ba49906ac874507abcfe7ddaf265052945c81bf524af9ef339f7842c719556d +size 6596007424 diff --git a/KamalaHarris-Llama-3.1-8B-Chat.Q8_0.gguf b/KamalaHarris-Llama-3.1-8B-Chat.Q8_0.gguf new file mode 100644 index 0000000..5cc6047 --- /dev/null +++ b/KamalaHarris-Llama-3.1-8B-Chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb0d65b824f5b94651e5500ab01dbfb7a2fccbaa35903182631e6b0d575b8cc8 +size 8540771840 diff --git a/KamalaHarris-Llama-3.1-8B-Chat.f16.gguf b/KamalaHarris-Llama-3.1-8B-Chat.f16.gguf new file mode 100644 index 0000000..2f49994 --- /dev/null +++ b/KamalaHarris-Llama-3.1-8B-Chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2788cc82ee440879313d121b05415ca0bd201cf2bb0ffbbf308135801f8ad90a +size 16068892160 diff --git a/README.md b/README.md new file mode 100644 index 0000000..56be404 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: nawhgnuj/KamalaHarris-Llama-3.1-8B-Chat +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- llama-factory +--- +## About + + + + + + +static quants of https://huggingface.co/nawhgnuj/KamalaHarris-Llama-3.1-8B-Chat + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/KamalaHarris-Llama-3.1-8B-Chat-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/KamalaHarris-Llama-3.1-8B-Chat-GGUF/resolve/main/KamalaHarris-Llama-3.1-8B-Chat.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/KamalaHarris-Llama-3.1-8B-Chat-GGUF/resolve/main/KamalaHarris-Llama-3.1-8B-Chat.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/KamalaHarris-Llama-3.1-8B-Chat-GGUF/resolve/main/KamalaHarris-Llama-3.1-8B-Chat.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/KamalaHarris-Llama-3.1-8B-Chat-GGUF/resolve/main/KamalaHarris-Llama-3.1-8B-Chat.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/KamalaHarris-Llama-3.1-8B-Chat-GGUF/resolve/main/KamalaHarris-Llama-3.1-8B-Chat.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/KamalaHarris-Llama-3.1-8B-Chat-GGUF/resolve/main/KamalaHarris-Llama-3.1-8B-Chat.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KamalaHarris-Llama-3.1-8B-Chat-GGUF/resolve/main/KamalaHarris-Llama-3.1-8B-Chat.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/KamalaHarris-Llama-3.1-8B-Chat-GGUF/resolve/main/KamalaHarris-Llama-3.1-8B-Chat.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/KamalaHarris-Llama-3.1-8B-Chat-GGUF/resolve/main/KamalaHarris-Llama-3.1-8B-Chat.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KamalaHarris-Llama-3.1-8B-Chat-GGUF/resolve/main/KamalaHarris-Llama-3.1-8B-Chat.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KamalaHarris-Llama-3.1-8B-Chat-GGUF/resolve/main/KamalaHarris-Llama-3.1-8B-Chat.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/KamalaHarris-Llama-3.1-8B-Chat-GGUF/resolve/main/KamalaHarris-Llama-3.1-8B-Chat.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/KamalaHarris-Llama-3.1-8B-Chat-GGUF/resolve/main/KamalaHarris-Llama-3.1-8B-Chat.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KamalaHarris-Llama-3.1-8B-Chat-GGUF/resolve/main/KamalaHarris-Llama-3.1-8B-Chat.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KamalaHarris-Llama-3.1-8B-Chat-GGUF/resolve/main/KamalaHarris-Llama-3.1-8B-Chat.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. + +