commit 324c42b6ed8dccaa5a8c9740ecf53252b0a6cf47 Author: ModelHub XC Date: Mon Jun 1 08:21:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/BitCPM4-CANN-0.5B-unquantized-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4a22b1e --- /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-0.5B-unquantized.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/BitCPM4-CANN-0.5B-unquantized.IQ4_XS.gguf b/BitCPM4-CANN-0.5B-unquantized.IQ4_XS.gguf new file mode 100644 index 0000000..07b2c5f --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b405b08586b8a454b79cd15126aa257d1427c088192cb5e52d5e0b95646e1be8 +size 256558720 diff --git a/BitCPM4-CANN-0.5B-unquantized.Q2_K.gguf b/BitCPM4-CANN-0.5B-unquantized.Q2_K.gguf new file mode 100644 index 0000000..65b45a6 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4def09bd513c3b97517e68db1446e90e685a9dba0249caf9d79172270ab00761 +size 194774656 diff --git a/BitCPM4-CANN-0.5B-unquantized.Q3_K_L.gguf b/BitCPM4-CANN-0.5B-unquantized.Q3_K_L.gguf new file mode 100644 index 0000000..4ce692e --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1855d71367b42f77827f2aa94f3d6d994677466839c676d17ed472fb0dca810f +size 250930816 diff --git a/BitCPM4-CANN-0.5B-unquantized.Q3_K_M.gguf b/BitCPM4-CANN-0.5B-unquantized.Q3_K_M.gguf new file mode 100644 index 0000000..4e92fd9 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27dd920aadc8db04ca6ccfca858e6c6ab3d5197e1628fc4dcc02acb42a167154 +size 235366016 diff --git a/BitCPM4-CANN-0.5B-unquantized.Q3_K_S.gguf b/BitCPM4-CANN-0.5B-unquantized.Q3_K_S.gguf new file mode 100644 index 0000000..9c87f54 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61986c98c7b0eed4a1c889b4715434c7d42ad314ce2cf930eca637486435d1a9 +size 217679488 diff --git a/BitCPM4-CANN-0.5B-unquantized.Q4_K_M.gguf b/BitCPM4-CANN-0.5B-unquantized.Q4_K_M.gguf new file mode 100644 index 0000000..2638dc0 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9871a6e45d6f4bb0e2ac69cdd519cb5d751e3ba352fdf253c2ad3404c45e40f7 +size 278689408 diff --git a/BitCPM4-CANN-0.5B-unquantized.Q4_K_S.gguf b/BitCPM4-CANN-0.5B-unquantized.Q4_K_S.gguf new file mode 100644 index 0000000..b3d6d40 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95024b86d1267b7de67ebc89025f538439ca815fec364bf466c8e0e1c3b69b1b +size 266946176 diff --git a/BitCPM4-CANN-0.5B-unquantized.Q5_K_M.gguf b/BitCPM4-CANN-0.5B-unquantized.Q5_K_M.gguf new file mode 100644 index 0000000..17b7803 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:098ee600b0244daac2fe7d52bd0212f02c6e243e9288acfcff08b9881bdf0fcc +size 317027968 diff --git a/BitCPM4-CANN-0.5B-unquantized.Q5_K_S.gguf b/BitCPM4-CANN-0.5B-unquantized.Q5_K_S.gguf new file mode 100644 index 0000000..ac5f25a --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a70fb5851da2812c6eea6588a0998e9d9e5a98d07657bedb419b1f6b1832060 +size 310134400 diff --git a/BitCPM4-CANN-0.5B-unquantized.Q6_K.gguf b/BitCPM4-CANN-0.5B-unquantized.Q6_K.gguf new file mode 100644 index 0000000..f9cfdb8 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee9e0eddbf1df39f2da697f858c4163348e6513228402773cf10a77bd03f0e58 +size 357762688 diff --git a/BitCPM4-CANN-0.5B-unquantized.Q8_0.gguf b/BitCPM4-CANN-0.5B-unquantized.Q8_0.gguf new file mode 100644 index 0000000..e3ecc53 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5e7a8969bad8090bdf1d67651a897c3f109df1900e7dd3fb77a56a6b8507fea +size 462829376 diff --git a/BitCPM4-CANN-0.5B-unquantized.f16.gguf b/BitCPM4-CANN-0.5B-unquantized.f16.gguf new file mode 100644 index 0000000..fdd0def --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:605a31e01a3451d2f606341e72539eb59f8aa68dc252f7801d3785ea14ce7675 +size 869539136 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a61d9f3 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: openbmb/BitCPM-CANN-0.5B-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-0.5B-unquantized + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#BitCPM4-CANN-0.5B-unquantized-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-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-0.5B-unquantized-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.Q3_K_L.gguf) | Q3_K_L | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.IQ4_XS.gguf) | IQ4_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.Q4_K_S.gguf) | Q4_K_S | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.Q4_K_M.gguf) | Q4_K_M | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.Q5_K_M.gguf) | Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.Q6_K.gguf) | Q6_K | 0.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.f16.gguf) | f16 | 1.0 | 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. + +