commit 92e83ba14fde39a7c06d2bfc4eeb93aad6480969 Author: ModelHub XC Date: Thu Jun 4 14:07:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/BitCPM4-CANN-8B-unquantized-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9e6ab99 --- /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 +BitCPM4-CANN-8B-unquantized.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-8B-unquantized.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-8B-unquantized.f16.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-8B-unquantized.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-8B-unquantized.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-8B-unquantized.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-8B-unquantized.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-8B-unquantized.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-8B-unquantized.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-8B-unquantized.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-8B-unquantized.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-8B-unquantized.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/BitCPM4-CANN-8B-unquantized.IQ4_XS.gguf b/BitCPM4-CANN-8B-unquantized.IQ4_XS.gguf new file mode 100644 index 0000000..86bd67d --- /dev/null +++ b/BitCPM4-CANN-8B-unquantized.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87954cd33266cf3e3740fef748ec61d5f0e0e444c2f963510d9c18bdd7102e08 +size 4485183648 diff --git a/BitCPM4-CANN-8B-unquantized.Q2_K.gguf b/BitCPM4-CANN-8B-unquantized.Q2_K.gguf new file mode 100644 index 0000000..51a123b --- /dev/null +++ b/BitCPM4-CANN-8B-unquantized.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fd876fb587e6a1096226f7e83a0b8a72bee89519a70bc034b19387c3edc5ee5 +size 3117024928 diff --git a/BitCPM4-CANN-8B-unquantized.Q3_K_L.gguf b/BitCPM4-CANN-8B-unquantized.Q3_K_L.gguf new file mode 100644 index 0000000..c12e849 --- /dev/null +++ b/BitCPM4-CANN-8B-unquantized.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45a0b08ce3e62d703e70f78b54c0aa9a7fd410cced883c9ec388a113b3718c97 +size 4337975200 diff --git a/BitCPM4-CANN-8B-unquantized.Q3_K_M.gguf b/BitCPM4-CANN-8B-unquantized.Q3_K_M.gguf new file mode 100644 index 0000000..78bdc96 --- /dev/null +++ b/BitCPM4-CANN-8B-unquantized.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edd0e5004c0b7f101ea730f122c323edce9e4191f8d27ef238d971b453f9d01b +size 4015275936 diff --git a/BitCPM4-CANN-8B-unquantized.Q3_K_S.gguf b/BitCPM4-CANN-8B-unquantized.Q3_K_S.gguf new file mode 100644 index 0000000..06faaf2 --- /dev/null +++ b/BitCPM4-CANN-8B-unquantized.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b80292b2e8ec6b0a0d0e7a43cc82ce18acebd94f1ff7eec51984f36e3e8b30c +size 3637264288 diff --git a/BitCPM4-CANN-8B-unquantized.Q4_K_M.gguf b/BitCPM4-CANN-8B-unquantized.Q4_K_M.gguf new file mode 100644 index 0000000..bd460a8 --- /dev/null +++ b/BitCPM4-CANN-8B-unquantized.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16104e651d22f8b4de3a4da223b25f254bd2938f265d61cb644618396e813e6d +size 4965526688 diff --git a/BitCPM4-CANN-8B-unquantized.Q4_K_S.gguf b/BitCPM4-CANN-8B-unquantized.Q4_K_S.gguf new file mode 100644 index 0000000..e6636d6 --- /dev/null +++ b/BitCPM4-CANN-8B-unquantized.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37c65c9c021150f280a915696639a221570c2752869ca56301db7afa301d74bd +size 4718455968 diff --git a/BitCPM4-CANN-8B-unquantized.Q5_K_M.gguf b/BitCPM4-CANN-8B-unquantized.Q5_K_M.gguf new file mode 100644 index 0000000..c56b4a5 --- /dev/null +++ b/BitCPM4-CANN-8B-unquantized.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47600a369ad4daaed7c440c00365cb7b156ac2e60a61672f641aad20ee506e3e +size 5814729888 diff --git a/BitCPM4-CANN-8B-unquantized.Q5_K_S.gguf b/BitCPM4-CANN-8B-unquantized.Q5_K_S.gguf new file mode 100644 index 0000000..2b19474 --- /dev/null +++ b/BitCPM4-CANN-8B-unquantized.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cc0c8c1f57fcc3e594a33ada7067e249d83c9ad7f069710b45da54916a91124 +size 5669895328 diff --git a/BitCPM4-CANN-8B-unquantized.Q6_K.gguf b/BitCPM4-CANN-8B-unquantized.Q6_K.gguf new file mode 100644 index 0000000..9659773 --- /dev/null +++ b/BitCPM4-CANN-8B-unquantized.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e472d4dd4bf1a3d7b770a70732d95094d58f369224119d55c5bd875fc8ed063 +size 6717008288 diff --git a/BitCPM4-CANN-8B-unquantized.Q8_0.gguf b/BitCPM4-CANN-8B-unquantized.Q8_0.gguf new file mode 100644 index 0000000..9918950 --- /dev/null +++ b/BitCPM4-CANN-8B-unquantized.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fb14c3ef0fce9aafb6687e12a647f2dc8dd2446f60dc5bf71a88247aeb7da7f +size 8699309984 diff --git a/BitCPM4-CANN-8B-unquantized.f16.gguf b/BitCPM4-CANN-8B-unquantized.f16.gguf new file mode 100644 index 0000000..06a40e5 --- /dev/null +++ b/BitCPM4-CANN-8B-unquantized.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18a2b968ddd4b6f0e4ac9f93fcc3cce88df9150162576dc16b67b51f2872aabc +size 16372735904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..caa42d3 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: openbmb/BitCPM-CANN-8B-unquantized +language: +- zh +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/openbmb/BitCPM-CANN-8B-unquantized + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#BitCPM4-CANN-8B-unquantized-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/BitCPM4-CANN-8B-unquantized-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/BitCPM4-CANN-8B-unquantized-GGUF/resolve/main/BitCPM4-CANN-8B-unquantized.Q2_K.gguf) | Q2_K | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-8B-unquantized-GGUF/resolve/main/BitCPM4-CANN-8B-unquantized.Q3_K_S.gguf) | Q3_K_S | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-8B-unquantized-GGUF/resolve/main/BitCPM4-CANN-8B-unquantized.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-8B-unquantized-GGUF/resolve/main/BitCPM4-CANN-8B-unquantized.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-8B-unquantized-GGUF/resolve/main/BitCPM4-CANN-8B-unquantized.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-8B-unquantized-GGUF/resolve/main/BitCPM4-CANN-8B-unquantized.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-8B-unquantized-GGUF/resolve/main/BitCPM4-CANN-8B-unquantized.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-8B-unquantized-GGUF/resolve/main/BitCPM4-CANN-8B-unquantized.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-8B-unquantized-GGUF/resolve/main/BitCPM4-CANN-8B-unquantized.Q5_K_M.gguf) | Q5_K_M | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-8B-unquantized-GGUF/resolve/main/BitCPM4-CANN-8B-unquantized.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-8B-unquantized-GGUF/resolve/main/BitCPM4-CANN-8B-unquantized.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-8B-unquantized-GGUF/resolve/main/BitCPM4-CANN-8B-unquantized.f16.gguf) | f16 | 16.5 | 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. + +