commit 9488d0a08c334384893a71ad1d743f66d76484d1 Author: ModelHub XC Date: Tue Apr 28 07:03:34 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/poemma-12B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..91c2e8f --- /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 +poemma-12B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +poemma-12B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +poemma-12B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +poemma-12B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +poemma-12B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +poemma-12B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +poemma-12B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +poemma-12B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +poemma-12B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +poemma-12B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +poemma-12B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +poemma-12B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4306e38 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: 0x7o/poemma-12B +datasets: +- 0x7o/poemma-10k +language: +- ru +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- mistral +- trl +- orpo +--- +## About + + + + + + +static quants of https://huggingface.co/0x7o/poemma-12B + + +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/poemma-12B-GGUF/resolve/main/poemma-12B.Q2_K.gguf) | Q2_K | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/poemma-12B-GGUF/resolve/main/poemma-12B.Q3_K_S.gguf) | Q3_K_S | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/poemma-12B-GGUF/resolve/main/poemma-12B.Q3_K_M.gguf) | Q3_K_M | 6.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/poemma-12B-GGUF/resolve/main/poemma-12B.Q3_K_L.gguf) | Q3_K_L | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/poemma-12B-GGUF/resolve/main/poemma-12B.IQ4_XS.gguf) | IQ4_XS | 6.9 | | +| [GGUF](https://huggingface.co/mradermacher/poemma-12B-GGUF/resolve/main/poemma-12B.Q4_0_4_4.gguf) | Q4_0_4_4 | 7.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/poemma-12B-GGUF/resolve/main/poemma-12B.Q4_K_S.gguf) | Q4_K_S | 7.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/poemma-12B-GGUF/resolve/main/poemma-12B.Q4_K_M.gguf) | Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/poemma-12B-GGUF/resolve/main/poemma-12B.Q5_K_S.gguf) | Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/poemma-12B-GGUF/resolve/main/poemma-12B.Q5_K_M.gguf) | Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/poemma-12B-GGUF/resolve/main/poemma-12B.Q6_K.gguf) | Q6_K | 10.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/poemma-12B-GGUF/resolve/main/poemma-12B.Q8_0.gguf) | Q8_0 | 13.1 | fast, best quality | + +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/poemma-12B.IQ4_XS.gguf b/poemma-12B.IQ4_XS.gguf new file mode 100644 index 0000000..587b804 --- /dev/null +++ b/poemma-12B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:731d16f7b66eff03309bea5a5744e3147ba2960277209b16eda50f403091ad03 +size 6800057504 diff --git a/poemma-12B.Q2_K.gguf b/poemma-12B.Q2_K.gguf new file mode 100644 index 0000000..20903ae --- /dev/null +++ b/poemma-12B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83248478d3e42eb1915035c7e04af306eb8573109af22288c14d5a8d0b090d53 +size 4791051424 diff --git a/poemma-12B.Q3_K_L.gguf b/poemma-12B.Q3_K_L.gguf new file mode 100644 index 0000000..c5c003e --- /dev/null +++ b/poemma-12B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aef04438f06d216d70057b06ed4a601f06e6e9d226e63dc1d770fcba65868cf9 +size 6561506464 diff --git a/poemma-12B.Q3_K_M.gguf b/poemma-12B.Q3_K_M.gguf new file mode 100644 index 0000000..adf7000 --- /dev/null +++ b/poemma-12B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d825439600b85677d58f949408143c2717a8491ceed74b00c246a4155c1d363c +size 6083093664 diff --git a/poemma-12B.Q3_K_S.gguf b/poemma-12B.Q3_K_S.gguf new file mode 100644 index 0000000..d45cc78 --- /dev/null +++ b/poemma-12B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03578a9cb8557c0f79183090af643908b6103d0b032eaeeb62f6e26b54c563fc +size 5534229664 diff --git a/poemma-12B.Q4_0_4_4.gguf b/poemma-12B.Q4_0_4_4.gguf new file mode 100644 index 0000000..ae86eac --- /dev/null +++ b/poemma-12B.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac63da74dbffec2604fedad07ff2f40217566ca7d5a979eb1b7d58288222593e +size 7071704224 diff --git a/poemma-12B.Q4_K_M.gguf b/poemma-12B.Q4_K_M.gguf new file mode 100644 index 0000000..26aed9f --- /dev/null +++ b/poemma-12B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cc5a9891df5b157c791a1b87a834510139dfb84d1f7f89166378ccc0bc15fcc +size 7477208224 diff --git a/poemma-12B.Q4_K_S.gguf b/poemma-12B.Q4_K_S.gguf new file mode 100644 index 0000000..b464979 --- /dev/null +++ b/poemma-12B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bda3bd07c0eb8c582feeefa8e45f54f0501414c01ac5721ddfaeda9c6c8a429 +size 7120200864 diff --git a/poemma-12B.Q5_K_M.gguf b/poemma-12B.Q5_K_M.gguf new file mode 100644 index 0000000..29d65fc --- /dev/null +++ b/poemma-12B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0c4369694dfb72fd966edcb6bf769ff082d4ab089d0cc3a83e6d4b631a8e8ba +size 8727635104 diff --git a/poemma-12B.Q5_K_S.gguf b/poemma-12B.Q5_K_S.gguf new file mode 100644 index 0000000..9768782 --- /dev/null +++ b/poemma-12B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aee1782a2d650b9d04100c05d528084697a18de0a79288018c9753fb03c08277 +size 8518739104 diff --git a/poemma-12B.Q6_K.gguf b/poemma-12B.Q6_K.gguf new file mode 100644 index 0000000..8a2114f --- /dev/null +++ b/poemma-12B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd8f3693b73e5f12bb704fa9309aac2a5e24dd702b70c154afd483da5a8cb4a1 +size 10056213664 diff --git a/poemma-12B.Q8_0.gguf b/poemma-12B.Q8_0.gguf new file mode 100644 index 0000000..21ada01 --- /dev/null +++ b/poemma-12B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73f054730b51a1611047f1dd782dea2cd98bd1f37db6457c9d7b7a2138c7a462 +size 13022373024