commit d88e8f101ef1f423d69f12007b1a7cb9d9307778 Author: ModelHub XC Date: Sun May 31 01:32:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/chat-anything-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..722fecb --- /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 +chat-anything-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +chat-anything-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +chat-anything-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +chat-anything-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +chat-anything-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +chat-anything-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +chat-anything-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +chat-anything-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +chat-anything-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +chat-anything-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +chat-anything-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +chat-anything-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a40807e --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: jCool10/chat-anything-3B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/jCool10/chat-anything-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#chat-anything-3B-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/chat-anything-3B-GGUF/resolve/main/chat-anything-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/chat-anything-3B-GGUF/resolve/main/chat-anything-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/chat-anything-3B-GGUF/resolve/main/chat-anything-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/chat-anything-3B-GGUF/resolve/main/chat-anything-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/chat-anything-3B-GGUF/resolve/main/chat-anything-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/chat-anything-3B-GGUF/resolve/main/chat-anything-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/chat-anything-3B-GGUF/resolve/main/chat-anything-3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/chat-anything-3B-GGUF/resolve/main/chat-anything-3B.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/chat-anything-3B-GGUF/resolve/main/chat-anything-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/chat-anything-3B-GGUF/resolve/main/chat-anything-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/chat-anything-3B-GGUF/resolve/main/chat-anything-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/chat-anything-3B-GGUF/resolve/main/chat-anything-3B.f16.gguf) | f16 | 6.5 | 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/chat-anything-3B.IQ4_XS.gguf b/chat-anything-3B.IQ4_XS.gguf new file mode 100644 index 0000000..8058f30 --- /dev/null +++ b/chat-anything-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fab1fbbc81055f714845effd24ca1f3421adc11fd3547cb8ffd2bec393eb88e +size 1840908000 diff --git a/chat-anything-3B.Q2_K.gguf b/chat-anything-3B.Q2_K.gguf new file mode 100644 index 0000000..9c265d6 --- /dev/null +++ b/chat-anything-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b11b0bbf45e99cac1c5750728cb362d548b7dbe21e7d246e1616e18a61e3e539 +size 1363936992 diff --git a/chat-anything-3B.Q3_K_L.gguf b/chat-anything-3B.Q3_K_L.gguf new file mode 100644 index 0000000..1b47157 --- /dev/null +++ b/chat-anything-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e23d2d610bc612c36de97c30cc403478a7005c0da5723f3cb794eaa31741312c +size 1815348960 diff --git a/chat-anything-3B.Q3_K_M.gguf b/chat-anything-3B.Q3_K_M.gguf new file mode 100644 index 0000000..d50f237 --- /dev/null +++ b/chat-anything-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95d583ad33a4f951b5a835f1d46dec21eea1fde4d75f7e66d373679dda584bef +size 1687160544 diff --git a/chat-anything-3B.Q3_K_S.gguf b/chat-anything-3B.Q3_K_S.gguf new file mode 100644 index 0000000..cc94995 --- /dev/null +++ b/chat-anything-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1370830a96897aed6ab24e52ef57f1d95d7d2c31f79e1ee27b666ff88e158857 +size 1542850272 diff --git a/chat-anything-3B.Q4_K_M.gguf b/chat-anything-3B.Q4_K_M.gguf new file mode 100644 index 0000000..a2fc7e0 --- /dev/null +++ b/chat-anything-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8794aa6f1236f101e19d8bc42327201349e2eeb3c5473c90f316d7906bc7c86f +size 2019378912 diff --git a/chat-anything-3B.Q4_K_S.gguf b/chat-anything-3B.Q4_K_S.gguf new file mode 100644 index 0000000..90eb48f --- /dev/null +++ b/chat-anything-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5b671f5615648930a1f05fe76363775e237e5a903f939d504f5999ec73c7f2b +size 1928201952 diff --git a/chat-anything-3B.Q5_K_M.gguf b/chat-anything-3B.Q5_K_M.gguf new file mode 100644 index 0000000..db69c99 --- /dev/null +++ b/chat-anything-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2f6edb375a0a41c60b7bd5f174ff3fb947363f712fd7dbf409fd8f0311b073d +size 2322155232 diff --git a/chat-anything-3B.Q5_K_S.gguf b/chat-anything-3B.Q5_K_S.gguf new file mode 100644 index 0000000..0c4d901 --- /dev/null +++ b/chat-anything-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:898478aad215b75f98b0d7423f314244b6ee3e2eaea30baa96950bbeed1f96fe +size 2269513440 diff --git a/chat-anything-3B.Q6_K.gguf b/chat-anything-3B.Q6_K.gguf new file mode 100644 index 0000000..1c73ce8 --- /dev/null +++ b/chat-anything-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4cbef89dfe7c68c102f3e6a818c936382b41313beafbc3c7f81af155f6a2e8f +size 2643855072 diff --git a/chat-anything-3B.Q8_0.gguf b/chat-anything-3B.Q8_0.gguf new file mode 100644 index 0000000..b6fbb11 --- /dev/null +++ b/chat-anything-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c97790c6c6706b54bd4fd9655f9dc15ae9e81ccf7860649268f4f8716067f6d3 +size 3421900512 diff --git a/chat-anything-3B.f16.gguf b/chat-anything-3B.f16.gguf new file mode 100644 index 0000000..d088978 --- /dev/null +++ b/chat-anything-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7f79a1a456db28da0bd5c1908cd5c52f6156411eceb8ea0bec2c47e7621b470 +size 6433689312