commit 7e54c12c7e2b1df1cc76b490ce9cdef95308ce2c Author: ModelHub XC Date: Sat Jun 13 10:22:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/cpa-qwen3-8b-v0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b21e767 --- /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 +cpa-qwen3-8b-v0.f16.gguf filter=lfs diff=lfs merge=lfs -text +cpa-qwen3-8b-v0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +cpa-qwen3-8b-v0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +cpa-qwen3-8b-v0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +cpa-qwen3-8b-v0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +cpa-qwen3-8b-v0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +cpa-qwen3-8b-v0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +cpa-qwen3-8b-v0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +cpa-qwen3-8b-v0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +cpa-qwen3-8b-v0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +cpa-qwen3-8b-v0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +cpa-qwen3-8b-v0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..cdc8798 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: AudCor/cpa-qwen3-8b-v0 +datasets: +- Josephgflowers/Finance-Instruct-500k +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation +- finance +- economics +- cpa +- audcor +--- +## About + + + + + + + + + +static quants of https://huggingface.co/AudCor/cpa-qwen3-8b-v0 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#cpa-qwen3-8b-v0-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/cpa-qwen3-8b-v0-GGUF/resolve/main/cpa-qwen3-8b-v0.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/cpa-qwen3-8b-v0-GGUF/resolve/main/cpa-qwen3-8b-v0.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/cpa-qwen3-8b-v0-GGUF/resolve/main/cpa-qwen3-8b-v0.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/cpa-qwen3-8b-v0-GGUF/resolve/main/cpa-qwen3-8b-v0.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/cpa-qwen3-8b-v0-GGUF/resolve/main/cpa-qwen3-8b-v0.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/cpa-qwen3-8b-v0-GGUF/resolve/main/cpa-qwen3-8b-v0.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/cpa-qwen3-8b-v0-GGUF/resolve/main/cpa-qwen3-8b-v0.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/cpa-qwen3-8b-v0-GGUF/resolve/main/cpa-qwen3-8b-v0.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/cpa-qwen3-8b-v0-GGUF/resolve/main/cpa-qwen3-8b-v0.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/cpa-qwen3-8b-v0-GGUF/resolve/main/cpa-qwen3-8b-v0.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/cpa-qwen3-8b-v0-GGUF/resolve/main/cpa-qwen3-8b-v0.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/cpa-qwen3-8b-v0-GGUF/resolve/main/cpa-qwen3-8b-v0.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. + + diff --git a/cpa-qwen3-8b-v0.IQ4_XS.gguf b/cpa-qwen3-8b-v0.IQ4_XS.gguf new file mode 100644 index 0000000..1b64987 --- /dev/null +++ b/cpa-qwen3-8b-v0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3aae59848b09c784ecb477de724070627f264a9b8d8daef6d6ae8c81f65d389c +size 4593297920 diff --git a/cpa-qwen3-8b-v0.Q2_K.gguf b/cpa-qwen3-8b-v0.Q2_K.gguf new file mode 100644 index 0000000..9771517 --- /dev/null +++ b/cpa-qwen3-8b-v0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb235ff1994ee6c56186b546d2c2aba3b03f3141cbdf6200acf2fe1a7874d497 +size 3281734144 diff --git a/cpa-qwen3-8b-v0.Q3_K_L.gguf b/cpa-qwen3-8b-v0.Q3_K_L.gguf new file mode 100644 index 0000000..1113ff0 --- /dev/null +++ b/cpa-qwen3-8b-v0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a51f300ab88ff0f3488c7f49d56d3a36dd65434ce5b378e3bd3ff2a07977ea5f +size 4431395328 diff --git a/cpa-qwen3-8b-v0.Q3_K_M.gguf b/cpa-qwen3-8b-v0.Q3_K_M.gguf new file mode 100644 index 0000000..f3f29bf --- /dev/null +++ b/cpa-qwen3-8b-v0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85a631840d114130cd209155d5d27e465b89334750085826350ef4aa297879ac +size 4124162560 diff --git a/cpa-qwen3-8b-v0.Q3_K_S.gguf b/cpa-qwen3-8b-v0.Q3_K_S.gguf new file mode 100644 index 0000000..40b7d91 --- /dev/null +++ b/cpa-qwen3-8b-v0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39f9079374eaaf944a2196c875f66bf35c4362484f4399cc080e67d0d19f4f6e +size 3769612800 diff --git a/cpa-qwen3-8b-v0.Q4_K_M.gguf b/cpa-qwen3-8b-v0.Q4_K_M.gguf new file mode 100644 index 0000000..1ea3181 --- /dev/null +++ b/cpa-qwen3-8b-v0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c18b06d8c66bdb4968a9cadf496dce85178492901e29730c1a327545df5d966c +size 5027785216 diff --git a/cpa-qwen3-8b-v0.Q4_K_S.gguf b/cpa-qwen3-8b-v0.Q4_K_S.gguf new file mode 100644 index 0000000..8b128d3 --- /dev/null +++ b/cpa-qwen3-8b-v0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4839287b004e5f24afd2ecc74cabfbdebfc43396be2ea547c4778aec353bcc81 +size 4802013696 diff --git a/cpa-qwen3-8b-v0.Q5_K_M.gguf b/cpa-qwen3-8b-v0.Q5_K_M.gguf new file mode 100644 index 0000000..1bafa37 --- /dev/null +++ b/cpa-qwen3-8b-v0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26d665a6632db5a5eed9abcb2fce81c849e3d97163a8325746adf229ad9f3478 +size 5851113984 diff --git a/cpa-qwen3-8b-v0.Q5_K_S.gguf b/cpa-qwen3-8b-v0.Q5_K_S.gguf new file mode 100644 index 0000000..1ab9752 --- /dev/null +++ b/cpa-qwen3-8b-v0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84ed90fa98659b34366bea17c98d483122fe0e1817506eae7dd008647f516348 +size 5720762880 diff --git a/cpa-qwen3-8b-v0.Q6_K.gguf b/cpa-qwen3-8b-v0.Q6_K.gguf new file mode 100644 index 0000000..5595f4b --- /dev/null +++ b/cpa-qwen3-8b-v0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89e3ddf037715593ec74a793cd8c1ff8cadec9e1437431b835a36130e1e3efe2 +size 6725900800 diff --git a/cpa-qwen3-8b-v0.Q8_0.gguf b/cpa-qwen3-8b-v0.Q8_0.gguf new file mode 100644 index 0000000..058ec1d --- /dev/null +++ b/cpa-qwen3-8b-v0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e7d9cf88059245f56af6cb19f7dd5b23cf1f8fcbcd8ddfad92bcb1068b0985f +size 8709519872 diff --git a/cpa-qwen3-8b-v0.f16.gguf b/cpa-qwen3-8b-v0.f16.gguf new file mode 100644 index 0000000..68b7cd2 --- /dev/null +++ b/cpa-qwen3-8b-v0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ecf848bd50fc5fbfc5cd2756c19a43206e3f9e52341f1a54b54466db6b60286 +size 16388045312