commit 660f17f7a8abe2324712e142d9b8f3c835ea942f Author: ModelHub XC Date: Fri Sep 4 21:42:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/tarot-qwen2.5-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..535b55c --- /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 +tarot-qwen2.5-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +tarot-qwen2.5-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tarot-qwen2.5-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +tarot-qwen2.5-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +tarot-qwen2.5-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +tarot-qwen2.5-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tarot-qwen2.5-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tarot-qwen2.5-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +tarot-qwen2.5-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tarot-qwen2.5-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tarot-qwen2.5-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tarot-qwen2.5-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f5b0101 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: AutoBot000/tarot-qwen2.5-7b +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/AutoBot000/tarot-qwen2.5-7b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#tarot-qwen2.5-7b-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/tarot-qwen2.5-7b-GGUF/resolve/main/tarot-qwen2.5-7b.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/tarot-qwen2.5-7b-GGUF/resolve/main/tarot-qwen2.5-7b.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/tarot-qwen2.5-7b-GGUF/resolve/main/tarot-qwen2.5-7b.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/tarot-qwen2.5-7b-GGUF/resolve/main/tarot-qwen2.5-7b.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/tarot-qwen2.5-7b-GGUF/resolve/main/tarot-qwen2.5-7b.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/tarot-qwen2.5-7b-GGUF/resolve/main/tarot-qwen2.5-7b.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/tarot-qwen2.5-7b-GGUF/resolve/main/tarot-qwen2.5-7b.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/tarot-qwen2.5-7b-GGUF/resolve/main/tarot-qwen2.5-7b.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/tarot-qwen2.5-7b-GGUF/resolve/main/tarot-qwen2.5-7b.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/tarot-qwen2.5-7b-GGUF/resolve/main/tarot-qwen2.5-7b.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/tarot-qwen2.5-7b-GGUF/resolve/main/tarot-qwen2.5-7b.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/tarot-qwen2.5-7b-GGUF/resolve/main/tarot-qwen2.5-7b.f16.gguf) | f16 | 15.3 | 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/tarot-qwen2.5-7b.IQ4_XS.gguf b/tarot-qwen2.5-7b.IQ4_XS.gguf new file mode 100644 index 0000000..3a77809 --- /dev/null +++ b/tarot-qwen2.5-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d73e958d5614415d442f4935ed1579b2d42d79ba6b4e3c2ab86e4216f7f792c9 +size 4250298752 diff --git a/tarot-qwen2.5-7b.Q2_K.gguf b/tarot-qwen2.5-7b.Q2_K.gguf new file mode 100644 index 0000000..65e6d5f --- /dev/null +++ b/tarot-qwen2.5-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f29cd1fec71a859d819ccedf09a06473175b345293719ea1751dc120380adcf0 +size 3015940480 diff --git a/tarot-qwen2.5-7b.Q3_K_L.gguf b/tarot-qwen2.5-7b.Q3_K_L.gguf new file mode 100644 index 0000000..5802b00 --- /dev/null +++ b/tarot-qwen2.5-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7bc19283e6a5667b560ac4143bf6fea937e03c835ddc0aea9c1d99f5545f8c7 +size 4088459648 diff --git a/tarot-qwen2.5-7b.Q3_K_M.gguf b/tarot-qwen2.5-7b.Q3_K_M.gguf new file mode 100644 index 0000000..955d2fd --- /dev/null +++ b/tarot-qwen2.5-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12c94398231e886e0f0113c8f996cfbad9da7d2a2ecd35305330fcbae55d0f8e +size 3808391552 diff --git a/tarot-qwen2.5-7b.Q3_K_S.gguf b/tarot-qwen2.5-7b.Q3_K_S.gguf new file mode 100644 index 0000000..dc92a82 --- /dev/null +++ b/tarot-qwen2.5-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fd3575bf0e0308efe75ced29f6f30e96a4b1fe8d97a624eb023f5e54255c25d +size 3492368768 diff --git a/tarot-qwen2.5-7b.Q4_K_M.gguf b/tarot-qwen2.5-7b.Q4_K_M.gguf new file mode 100644 index 0000000..1f81011 --- /dev/null +++ b/tarot-qwen2.5-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48473d2fc0e61bb97872bb0b6da0baa76af1d78ea4c092fd94a360713fd73910 +size 4683073920 diff --git a/tarot-qwen2.5-7b.Q4_K_S.gguf b/tarot-qwen2.5-7b.Q4_K_S.gguf new file mode 100644 index 0000000..2ca4f4a --- /dev/null +++ b/tarot-qwen2.5-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08f18c923f195924321d9c54219caeb81225cf2fa8ee850a64ec795615f8ee08 +size 4457769344 diff --git a/tarot-qwen2.5-7b.Q5_K_M.gguf b/tarot-qwen2.5-7b.Q5_K_M.gguf new file mode 100644 index 0000000..380996b --- /dev/null +++ b/tarot-qwen2.5-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cba91c58b4ec06cf3be34155e864b83a533b1db272266cd560232fe77af7af1 +size 5444831616 diff --git a/tarot-qwen2.5-7b.Q5_K_S.gguf b/tarot-qwen2.5-7b.Q5_K_S.gguf new file mode 100644 index 0000000..cd28053 --- /dev/null +++ b/tarot-qwen2.5-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5bf200bfca2f10c31eface8107869b63b71e2ef93ae8da5a4ab9981821437e4 +size 5315176832 diff --git a/tarot-qwen2.5-7b.Q6_K.gguf b/tarot-qwen2.5-7b.Q6_K.gguf new file mode 100644 index 0000000..0a1de14 --- /dev/null +++ b/tarot-qwen2.5-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ff68709f88c76383635934cf6a218bb2d524a339af08d7f298470ffdbb8ce13 +size 6254199168 diff --git a/tarot-qwen2.5-7b.Q8_0.gguf b/tarot-qwen2.5-7b.Q8_0.gguf new file mode 100644 index 0000000..4f1ca39 --- /dev/null +++ b/tarot-qwen2.5-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd80f69049d595f86133b29360a85432c79df0ff4b978ab71b9b950368a9c695 +size 8098525568 diff --git a/tarot-qwen2.5-7b.f16.gguf b/tarot-qwen2.5-7b.f16.gguf new file mode 100644 index 0000000..6eaf7df --- /dev/null +++ b/tarot-qwen2.5-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20e6e30d4ee297729c10d94ad71921004bbf8f46a7e4396e62bcf44e9443453 +size 15237853568