commit cfb7d61127382ca5f39d6dd1c1acf1dcfa763b8f Author: ModelHub XC Date: Mon Jun 29 12:46:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/bookshop-llama3-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..be5e6ec --- /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 +bookshop-llama3-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text +bookshop-llama3-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bookshop-llama3-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +bookshop-llama3-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +bookshop-llama3-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +bookshop-llama3-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bookshop-llama3-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bookshop-llama3-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +bookshop-llama3-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bookshop-llama3-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bookshop-llama3-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bookshop-llama3-v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9668ca1 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: GasparDoesAI/bookshop-llama3-v1 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/GasparDoesAI/bookshop-llama3-v1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#bookshop-llama3-v1-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/bookshop-llama3-v1-GGUF/resolve/main/bookshop-llama3-v1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/bookshop-llama3-v1-GGUF/resolve/main/bookshop-llama3-v1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/bookshop-llama3-v1-GGUF/resolve/main/bookshop-llama3-v1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/bookshop-llama3-v1-GGUF/resolve/main/bookshop-llama3-v1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/bookshop-llama3-v1-GGUF/resolve/main/bookshop-llama3-v1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/bookshop-llama3-v1-GGUF/resolve/main/bookshop-llama3-v1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/bookshop-llama3-v1-GGUF/resolve/main/bookshop-llama3-v1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/bookshop-llama3-v1-GGUF/resolve/main/bookshop-llama3-v1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/bookshop-llama3-v1-GGUF/resolve/main/bookshop-llama3-v1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/bookshop-llama3-v1-GGUF/resolve/main/bookshop-llama3-v1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/bookshop-llama3-v1-GGUF/resolve/main/bookshop-llama3-v1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/bookshop-llama3-v1-GGUF/resolve/main/bookshop-llama3-v1.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/bookshop-llama3-v1.IQ4_XS.gguf b/bookshop-llama3-v1.IQ4_XS.gguf new file mode 100644 index 0000000..1f71df3 --- /dev/null +++ b/bookshop-llama3-v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dbaa87a1c40ae10dba4865344de64c50b76c6b2645272e2750e6dd642cd953b +size 4484363680 diff --git a/bookshop-llama3-v1.Q2_K.gguf b/bookshop-llama3-v1.Q2_K.gguf new file mode 100644 index 0000000..961fc10 --- /dev/null +++ b/bookshop-llama3-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ad7bac19905453f7674c5ac0623f91b77520873c1cabeb13232183944f36828 +size 3179132320 diff --git a/bookshop-llama3-v1.Q3_K_L.gguf b/bookshop-llama3-v1.Q3_K_L.gguf new file mode 100644 index 0000000..83a1de3 --- /dev/null +++ b/bookshop-llama3-v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d923733ea86a8a8355907b508b8adfff9a494c22fe3aabe65811ec4f28965c8 +size 4321957280 diff --git a/bookshop-llama3-v1.Q3_K_M.gguf b/bookshop-llama3-v1.Q3_K_M.gguf new file mode 100644 index 0000000..294f67e --- /dev/null +++ b/bookshop-llama3-v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:881dfdb233b7cf86acaa2ed52402ea93ed13210b229aaa3438cecc3a4e6129e5 +size 4018918816 diff --git a/bookshop-llama3-v1.Q3_K_S.gguf b/bookshop-llama3-v1.Q3_K_S.gguf new file mode 100644 index 0000000..488ba69 --- /dev/null +++ b/bookshop-llama3-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50fdc13628e61edce22b4383407aa381f9716a59d447022ba87fbe0977d70a1e +size 3664500128 diff --git a/bookshop-llama3-v1.Q4_K_M.gguf b/bookshop-llama3-v1.Q4_K_M.gguf new file mode 100644 index 0000000..c00820a --- /dev/null +++ b/bookshop-llama3-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5cabf691d7caf1a5a4c7f0f9cd7ac663e5df11c2d3bbb33a208966d115c8687 +size 4920735136 diff --git a/bookshop-llama3-v1.Q4_K_S.gguf b/bookshop-llama3-v1.Q4_K_S.gguf new file mode 100644 index 0000000..30ad74d --- /dev/null +++ b/bookshop-llama3-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d23afe66f5b793e19e52521216c57e34c5613703323000d64ad37104f1c30ea +size 4692669856 diff --git a/bookshop-llama3-v1.Q5_K_M.gguf b/bookshop-llama3-v1.Q5_K_M.gguf new file mode 100644 index 0000000..30d9497 --- /dev/null +++ b/bookshop-llama3-v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40e20e446e6fcdb5f88a759a83d9115baba5d9b1c0932179b473fa4ba4dc706c +size 5732988320 diff --git a/bookshop-llama3-v1.Q5_K_S.gguf b/bookshop-llama3-v1.Q5_K_S.gguf new file mode 100644 index 0000000..cc6d84b --- /dev/null +++ b/bookshop-llama3-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5313182b62ea27e7babd9277bf0f9240b135a9b301d7043e43ecc4c9927b7a88 +size 5599294880 diff --git a/bookshop-llama3-v1.Q6_K.gguf b/bookshop-llama3-v1.Q6_K.gguf new file mode 100644 index 0000000..1baac24 --- /dev/null +++ b/bookshop-llama3-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5035b3971817840dc5f178708f4c778e3c9e4cf81e7cd56a3bb93fa3a7ec27ac +size 6596007328 diff --git a/bookshop-llama3-v1.Q8_0.gguf b/bookshop-llama3-v1.Q8_0.gguf new file mode 100644 index 0000000..9483218 --- /dev/null +++ b/bookshop-llama3-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b67a6eefd2fdc3375b419c9a3dd5d2e3855fe35b4f408837ca197db0d6f37e3 +size 8540771744 diff --git a/bookshop-llama3-v1.f16.gguf b/bookshop-llama3-v1.f16.gguf new file mode 100644 index 0000000..80aab97 --- /dev/null +++ b/bookshop-llama3-v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c05731d1ad0a34ded09953579964f6c268cb3df0873164ad24533ae63e4c780 +size 16068892064