commit 9be1141cd3af86993fe18a00738d2f022e296635 Author: ModelHub XC Date: Fri May 8 23:59:52 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Anole-7b-v0.1-hf-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6244a36 --- /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 +Anole-7b-v0.1-hf.f16.gguf filter=lfs diff=lfs merge=lfs -text +Anole-7b-v0.1-hf.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Anole-7b-v0.1-hf.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Anole-7b-v0.1-hf.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Anole-7b-v0.1-hf.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Anole-7b-v0.1-hf.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Anole-7b-v0.1-hf.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Anole-7b-v0.1-hf.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Anole-7b-v0.1-hf.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Anole-7b-v0.1-hf.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Anole-7b-v0.1-hf.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Anole-7b-v0.1-hf.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Anole-7b-v0.1-hf.IQ4_XS.gguf b/Anole-7b-v0.1-hf.IQ4_XS.gguf new file mode 100644 index 0000000..3e8f32f --- /dev/null +++ b/Anole-7b-v0.1-hf.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5fa9ae43303163891a6a72cdefd0b0a56de98ea64f801355ee361335865fb6d +size 3836685664 diff --git a/Anole-7b-v0.1-hf.Q2_K.gguf b/Anole-7b-v0.1-hf.Q2_K.gguf new file mode 100644 index 0000000..f3ffcbf --- /dev/null +++ b/Anole-7b-v0.1-hf.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dc7112067f0efe900bd8e0bfd0d4c97bab9c2fdd6588b787d778fb51bcfe870 +size 2694131040 diff --git a/Anole-7b-v0.1-hf.Q3_K_L.gguf b/Anole-7b-v0.1-hf.Q3_K_L.gguf new file mode 100644 index 0000000..2ec76b0 --- /dev/null +++ b/Anole-7b-v0.1-hf.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96e13af74db431c51ffd6763db7ca456add2be2912726521d2c8fb46f612490d +size 3772329312 diff --git a/Anole-7b-v0.1-hf.Q3_K_M.gguf b/Anole-7b-v0.1-hf.Q3_K_M.gguf new file mode 100644 index 0000000..6ce5ec2 --- /dev/null +++ b/Anole-7b-v0.1-hf.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bfa22875541a304c67750f34aab716c3d89db73bdb8bb02e029e8a659ca3e86 +size 3473223008 diff --git a/Anole-7b-v0.1-hf.Q3_K_S.gguf b/Anole-7b-v0.1-hf.Q3_K_S.gguf new file mode 100644 index 0000000..b5cd00e --- /dev/null +++ b/Anole-7b-v0.1-hf.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a39bc88c8cc6dda6415260f75aabd0750c56819957298914b8b7e37e3ab3274 +size 3123522912 diff --git a/Anole-7b-v0.1-hf.Q4_K_M.gguf b/Anole-7b-v0.1-hf.Q4_K_M.gguf new file mode 100644 index 0000000..e86c8df --- /dev/null +++ b/Anole-7b-v0.1-hf.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49a64c6d0a145822a6b1e5bd2491f62ca03e1ae4bbd202c79a1bbb21469bd6da +size 4274466144 diff --git a/Anole-7b-v0.1-hf.Q4_K_S.gguf b/Anole-7b-v0.1-hf.Q4_K_S.gguf new file mode 100644 index 0000000..d4eb286 --- /dev/null +++ b/Anole-7b-v0.1-hf.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08128b4c8d34924b6548b78b4032f3aa645eb433e944ef62332ad29f74470fa4 +size 4050201952 diff --git a/Anole-7b-v0.1-hf.Q5_K_M.gguf b/Anole-7b-v0.1-hf.Q5_K_M.gguf new file mode 100644 index 0000000..6271214 --- /dev/null +++ b/Anole-7b-v0.1-hf.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c60916bafb9165b3686fa3bd0ed8ea3cb9d8ff496ec51b9107edcedc188762f6 +size 4993789280 diff --git a/Anole-7b-v0.1-hf.Q5_K_S.gguf b/Anole-7b-v0.1-hf.Q5_K_S.gguf new file mode 100644 index 0000000..b6686e7 --- /dev/null +++ b/Anole-7b-v0.1-hf.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cc02afe7e89cf2e9fecb07be14e2c44fffb86ed2408407663493f425d61d5db +size 4862324064 diff --git a/Anole-7b-v0.1-hf.Q6_K.gguf b/Anole-7b-v0.1-hf.Q6_K.gguf new file mode 100644 index 0000000..a8db0e2 --- /dev/null +++ b/Anole-7b-v0.1-hf.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c741bf0c2ff57b6a763b6e9717a9e33370a66a9833ecfe6df64b1b47b814c36 +size 5758070112 diff --git a/Anole-7b-v0.1-hf.Q8_0.gguf b/Anole-7b-v0.1-hf.Q8_0.gguf new file mode 100644 index 0000000..578dd3b --- /dev/null +++ b/Anole-7b-v0.1-hf.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fba0a94d2463794b14710fb326690eefb84366c16d9a30c5d7e7f562d8c3472 +size 7456501088 diff --git a/Anole-7b-v0.1-hf.f16.gguf b/Anole-7b-v0.1-hf.f16.gguf new file mode 100644 index 0000000..5ee47ba --- /dev/null +++ b/Anole-7b-v0.1-hf.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7630b22c8f3870067ab41888610aa7246c3dbaa3a02e788cd4a915207faf83b7 +size 14031072608 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b2ef7ba --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: leloy/Anole-7b-v0.1-hf +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/leloy/Anole-7b-v0.1-hf + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Anole-7b-v0.1-hf-i1-GGUF +## 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/Anole-7b-v0.1-hf-GGUF/resolve/main/Anole-7b-v0.1-hf.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Anole-7b-v0.1-hf-GGUF/resolve/main/Anole-7b-v0.1-hf.Q3_K_S.gguf) | Q3_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Anole-7b-v0.1-hf-GGUF/resolve/main/Anole-7b-v0.1-hf.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Anole-7b-v0.1-hf-GGUF/resolve/main/Anole-7b-v0.1-hf.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Anole-7b-v0.1-hf-GGUF/resolve/main/Anole-7b-v0.1-hf.IQ4_XS.gguf) | IQ4_XS | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Anole-7b-v0.1-hf-GGUF/resolve/main/Anole-7b-v0.1-hf.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Anole-7b-v0.1-hf-GGUF/resolve/main/Anole-7b-v0.1-hf.Q4_K_M.gguf) | Q4_K_M | 4.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Anole-7b-v0.1-hf-GGUF/resolve/main/Anole-7b-v0.1-hf.Q5_K_S.gguf) | Q5_K_S | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Anole-7b-v0.1-hf-GGUF/resolve/main/Anole-7b-v0.1-hf.Q5_K_M.gguf) | Q5_K_M | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Anole-7b-v0.1-hf-GGUF/resolve/main/Anole-7b-v0.1-hf.Q6_K.gguf) | Q6_K | 5.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Anole-7b-v0.1-hf-GGUF/resolve/main/Anole-7b-v0.1-hf.Q8_0.gguf) | Q8_0 | 7.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Anole-7b-v0.1-hf-GGUF/resolve/main/Anole-7b-v0.1-hf.f16.gguf) | f16 | 14.1 | 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. + +