commit 99ead9a8be00bfd35ec37a2cb9fa67fbcb820e66 Author: ModelHub XC Date: Thu Apr 16 14:55:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-shared_spaces-7972-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7890e13 --- /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-shared_spaces-7972.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-shared_spaces-7972.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-shared_spaces-7972.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-shared_spaces-7972.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-shared_spaces-7972.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-shared_spaces-7972.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-shared_spaces-7972.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-shared_spaces-7972.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-shared_spaces-7972.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-shared_spaces-7972.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-shared_spaces-7972.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-shared_spaces-7972.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-shared_spaces-7972.IQ4_XS.gguf b/Llama-3.2-1B-shared_spaces-7972.IQ4_XS.gguf new file mode 100644 index 0000000..0b4e490 --- /dev/null +++ b/Llama-3.2-1B-shared_spaces-7972.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:050ee026417813b91981413110b96fbfc4a59d2615695fe23ae5604d640e39ac +size 748381056 diff --git a/Llama-3.2-1B-shared_spaces-7972.Q2_K.gguf b/Llama-3.2-1B-shared_spaces-7972.Q2_K.gguf new file mode 100644 index 0000000..7960aa0 --- /dev/null +++ b/Llama-3.2-1B-shared_spaces-7972.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:531eb508e09e76439e970dd88195514761205afd880ca40b8361fae2d5bff7c3 +size 580871040 diff --git a/Llama-3.2-1B-shared_spaces-7972.Q3_K_L.gguf b/Llama-3.2-1B-shared_spaces-7972.Q3_K_L.gguf new file mode 100644 index 0000000..d3db6df --- /dev/null +++ b/Llama-3.2-1B-shared_spaces-7972.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56043666d764cd0a1ee33f2a70b980862ebc5a6ff97744d71eb13be431002780 +size 732521344 diff --git a/Llama-3.2-1B-shared_spaces-7972.Q3_K_M.gguf b/Llama-3.2-1B-shared_spaces-7972.Q3_K_M.gguf new file mode 100644 index 0000000..c4dc6ba --- /dev/null +++ b/Llama-3.2-1B-shared_spaces-7972.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4061858a3bf94ccf9a1bad4975367f26e661900e222f5d6125effab6336b0da +size 690840448 diff --git a/Llama-3.2-1B-shared_spaces-7972.Q3_K_S.gguf b/Llama-3.2-1B-shared_spaces-7972.Q3_K_S.gguf new file mode 100644 index 0000000..d4e67da --- /dev/null +++ b/Llama-3.2-1B-shared_spaces-7972.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cc2d4b91cd5d169f8f89af96c8ddbf9d889b3b0eb5e4886bba59f8053f4ab05 +size 641688448 diff --git a/Llama-3.2-1B-shared_spaces-7972.Q4_K_M.gguf b/Llama-3.2-1B-shared_spaces-7972.Q4_K_M.gguf new file mode 100644 index 0000000..7b491eb --- /dev/null +++ b/Llama-3.2-1B-shared_spaces-7972.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8dc1444931db19162c0b2605cfd1c8b2f0563a6580f8c4ff617f035867d71d3 +size 807691136 diff --git a/Llama-3.2-1B-shared_spaces-7972.Q4_K_S.gguf b/Llama-3.2-1B-shared_spaces-7972.Q4_K_S.gguf new file mode 100644 index 0000000..5133d7f --- /dev/null +++ b/Llama-3.2-1B-shared_spaces-7972.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fc1ee616603e65265c2d02ac71f7677d5188dd7b25e5ee8bdf6914483871aa8 +size 775644032 diff --git a/Llama-3.2-1B-shared_spaces-7972.Q5_K_M.gguf b/Llama-3.2-1B-shared_spaces-7972.Q5_K_M.gguf new file mode 100644 index 0000000..3ca6aa7 --- /dev/null +++ b/Llama-3.2-1B-shared_spaces-7972.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc894aeff23d2f82df43af314b5521b967801705ece4709cc24d1d2e337c9d37 +size 911500160 diff --git a/Llama-3.2-1B-shared_spaces-7972.Q5_K_S.gguf b/Llama-3.2-1B-shared_spaces-7972.Q5_K_S.gguf new file mode 100644 index 0000000..b6fdd4c --- /dev/null +++ b/Llama-3.2-1B-shared_spaces-7972.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2cc90647584c11d1d2b66fb0026f2b274692e67f2665ae5b131bba55de0e010 +size 892560256 diff --git a/Llama-3.2-1B-shared_spaces-7972.Q6_K.gguf b/Llama-3.2-1B-shared_spaces-7972.Q6_K.gguf new file mode 100644 index 0000000..ca162e4 --- /dev/null +++ b/Llama-3.2-1B-shared_spaces-7972.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3358652ab357f3ef515dab9c0a2e0cc866255aacd6678082adeec0edeb2d45b +size 1021797248 diff --git a/Llama-3.2-1B-shared_spaces-7972.Q8_0.gguf b/Llama-3.2-1B-shared_spaces-7972.Q8_0.gguf new file mode 100644 index 0000000..a689714 --- /dev/null +++ b/Llama-3.2-1B-shared_spaces-7972.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f27eb0f5573ec1b68babadbc21c3becbb21804daee39ba993ed55b3add237fc9 +size 1321079680 diff --git a/Llama-3.2-1B-shared_spaces-7972.f16.gguf b/Llama-3.2-1B-shared_spaces-7972.f16.gguf new file mode 100644 index 0000000..55f7a72 --- /dev/null +++ b/Llama-3.2-1B-shared_spaces-7972.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a1fc19bc7fbd6ae2dcfb0244a997e7eabf33ad512b98f3a40d0d493e2a49d14 +size 2479592320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dda41da --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: henokyemam/Llama-3.2-1B-shared_spaces-7972 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/henokyemam/Llama-3.2-1B-shared_spaces-7972 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-1B-shared_spaces-7972-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-3.2-1B-shared_spaces-7972-GGUF/resolve/main/Llama-3.2-1B-shared_spaces-7972.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-shared_spaces-7972-GGUF/resolve/main/Llama-3.2-1B-shared_spaces-7972.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-shared_spaces-7972-GGUF/resolve/main/Llama-3.2-1B-shared_spaces-7972.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-shared_spaces-7972-GGUF/resolve/main/Llama-3.2-1B-shared_spaces-7972.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-shared_spaces-7972-GGUF/resolve/main/Llama-3.2-1B-shared_spaces-7972.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-shared_spaces-7972-GGUF/resolve/main/Llama-3.2-1B-shared_spaces-7972.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-shared_spaces-7972-GGUF/resolve/main/Llama-3.2-1B-shared_spaces-7972.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-shared_spaces-7972-GGUF/resolve/main/Llama-3.2-1B-shared_spaces-7972.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-shared_spaces-7972-GGUF/resolve/main/Llama-3.2-1B-shared_spaces-7972.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-shared_spaces-7972-GGUF/resolve/main/Llama-3.2-1B-shared_spaces-7972.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-shared_spaces-7972-GGUF/resolve/main/Llama-3.2-1B-shared_spaces-7972.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-shared_spaces-7972-GGUF/resolve/main/Llama-3.2-1B-shared_spaces-7972.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. + +