commit 7252c7b178995e222b41ad7b6f4f8b71b5c72810 Author: ModelHub XC Date: Mon Jun 15 02:40:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-Instruct-Complaint-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a31f7ed --- /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-3.2-1B-Instruct-Complaint.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Complaint.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Complaint.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Complaint.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Complaint.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Complaint.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Complaint.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Complaint.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Complaint.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Complaint.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Complaint.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-Complaint.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-Instruct-Complaint.IQ4_XS.gguf b/Llama-3.2-1B-Instruct-Complaint.IQ4_XS.gguf new file mode 100644 index 0000000..c78a4eb --- /dev/null +++ b/Llama-3.2-1B-Instruct-Complaint.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d62d7375bae6bfb97f86852c721b19aba3d88155c6b6e91326644d9ed086fa2 +size 748385216 diff --git a/Llama-3.2-1B-Instruct-Complaint.Q2_K.gguf b/Llama-3.2-1B-Instruct-Complaint.Q2_K.gguf new file mode 100644 index 0000000..cec8a82 --- /dev/null +++ b/Llama-3.2-1B-Instruct-Complaint.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:834fb3d6ab1293ea53d5a15d90a2745a2312c3672a33f33ccbdf2ca80f7fa78e +size 580875200 diff --git a/Llama-3.2-1B-Instruct-Complaint.Q3_K_L.gguf b/Llama-3.2-1B-Instruct-Complaint.Q3_K_L.gguf new file mode 100644 index 0000000..e5b038c --- /dev/null +++ b/Llama-3.2-1B-Instruct-Complaint.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:723f3cc8fa07216bcfdedb15520fb414be72d90c7ec56f433aca4a77da5e3d55 +size 732525504 diff --git a/Llama-3.2-1B-Instruct-Complaint.Q3_K_M.gguf b/Llama-3.2-1B-Instruct-Complaint.Q3_K_M.gguf new file mode 100644 index 0000000..959b8b7 --- /dev/null +++ b/Llama-3.2-1B-Instruct-Complaint.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:907773a759cab9e469fadbfb6eb5f706630c9dfbe90f13f4afcbcbb3f085f379 +size 690844608 diff --git a/Llama-3.2-1B-Instruct-Complaint.Q3_K_S.gguf b/Llama-3.2-1B-Instruct-Complaint.Q3_K_S.gguf new file mode 100644 index 0000000..e7f101d --- /dev/null +++ b/Llama-3.2-1B-Instruct-Complaint.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:885d034cc0953400b8f44264e85901d140c5a5eafc619371b318e6bba369bc83 +size 641692608 diff --git a/Llama-3.2-1B-Instruct-Complaint.Q4_K_M.gguf b/Llama-3.2-1B-Instruct-Complaint.Q4_K_M.gguf new file mode 100644 index 0000000..fd11899 --- /dev/null +++ b/Llama-3.2-1B-Instruct-Complaint.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49f50c4341d7a576b87385d6190289913aa2769c1a591c3c8c6615b02baf21d1 +size 807695296 diff --git a/Llama-3.2-1B-Instruct-Complaint.Q4_K_S.gguf b/Llama-3.2-1B-Instruct-Complaint.Q4_K_S.gguf new file mode 100644 index 0000000..d69c3d4 --- /dev/null +++ b/Llama-3.2-1B-Instruct-Complaint.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bad5a183ae2349e66d946a156fe5624be2bbeb8fa3049064e4b26c6d36c6f32 +size 775648192 diff --git a/Llama-3.2-1B-Instruct-Complaint.Q5_K_M.gguf b/Llama-3.2-1B-Instruct-Complaint.Q5_K_M.gguf new file mode 100644 index 0000000..57f7604 --- /dev/null +++ b/Llama-3.2-1B-Instruct-Complaint.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e422c7466b4c1c52c9d3bb449f70d8ba24442c5a13d216522fe46546dace045 +size 911504320 diff --git a/Llama-3.2-1B-Instruct-Complaint.Q5_K_S.gguf b/Llama-3.2-1B-Instruct-Complaint.Q5_K_S.gguf new file mode 100644 index 0000000..7dd7e0a --- /dev/null +++ b/Llama-3.2-1B-Instruct-Complaint.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9271bd4dd528b16cb0a7be8d70fea885899ca9945013b42f29b25956cb27bee2 +size 892564416 diff --git a/Llama-3.2-1B-Instruct-Complaint.Q6_K.gguf b/Llama-3.2-1B-Instruct-Complaint.Q6_K.gguf new file mode 100644 index 0000000..b68e912 --- /dev/null +++ b/Llama-3.2-1B-Instruct-Complaint.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c2ae14de206ee9557bc4529bd11733c8483b472440a39a3f7332892e3c1a2b6 +size 1021801408 diff --git a/Llama-3.2-1B-Instruct-Complaint.Q8_0.gguf b/Llama-3.2-1B-Instruct-Complaint.Q8_0.gguf new file mode 100644 index 0000000..989f1a2 --- /dev/null +++ b/Llama-3.2-1B-Instruct-Complaint.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24a8edcc372b465c1934ba3715f395d180cacb39047a0f17ca35217f076dbf89 +size 1321083840 diff --git a/Llama-3.2-1B-Instruct-Complaint.f16.gguf b/Llama-3.2-1B-Instruct-Complaint.f16.gguf new file mode 100644 index 0000000..e0883fb --- /dev/null +++ b/Llama-3.2-1B-Instruct-Complaint.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd4261162a5475d9f1cfe992fb582c1834c27047402285dc2397503da35c8187 +size 2479596480 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ccdf115 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: leonvanbokhorst/Llama-3.2-1B-Instruct-Complaint +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/leonvanbokhorst/Llama-3.2-1B-Instruct-Complaint + + +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-3.2-1B-Instruct-Complaint-GGUF/resolve/main/Llama-3.2-1B-Instruct-Complaint.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Complaint-GGUF/resolve/main/Llama-3.2-1B-Instruct-Complaint.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Complaint-GGUF/resolve/main/Llama-3.2-1B-Instruct-Complaint.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Complaint-GGUF/resolve/main/Llama-3.2-1B-Instruct-Complaint.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Complaint-GGUF/resolve/main/Llama-3.2-1B-Instruct-Complaint.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Complaint-GGUF/resolve/main/Llama-3.2-1B-Instruct-Complaint.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Complaint-GGUF/resolve/main/Llama-3.2-1B-Instruct-Complaint.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Complaint-GGUF/resolve/main/Llama-3.2-1B-Instruct-Complaint.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Complaint-GGUF/resolve/main/Llama-3.2-1B-Instruct-Complaint.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Complaint-GGUF/resolve/main/Llama-3.2-1B-Instruct-Complaint.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Complaint-GGUF/resolve/main/Llama-3.2-1B-Instruct-Complaint.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-Complaint-GGUF/resolve/main/Llama-3.2-1B-Instruct-Complaint.f16.gguf) | f16 | 2.6 | 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. + +