commit f27df2aaba7b13af55dc0ad4bae6909a5db43376 Author: ModelHub XC Date: Mon Oct 5 03:11:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/tongyi-model-v2.0-1b-th-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d16dc77 --- /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 +tongyi-model-v2.0-1b-th.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +tongyi-model-v2.0-1b-th.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +tongyi-model-v2.0-1b-th.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +tongyi-model-v2.0-1b-th.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tongyi-model-v2.0-1b-th.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tongyi-model-v2.0-1b-th.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tongyi-model-v2.0-1b-th.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tongyi-model-v2.0-1b-th.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tongyi-model-v2.0-1b-th.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tongyi-model-v2.0-1b-th.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +tongyi-model-v2.0-1b-th.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +tongyi-model-v2.0-1b-th.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c48117e --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: wannaphong/tongyi-model-v2.0-1b-th +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/wannaphong/tongyi-model-v2.0-1b-th + + +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/tongyi-model-v2.0-1b-th-GGUF/resolve/main/tongyi-model-v2.0-1b-th.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/tongyi-model-v2.0-1b-th-GGUF/resolve/main/tongyi-model-v2.0-1b-th.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/tongyi-model-v2.0-1b-th-GGUF/resolve/main/tongyi-model-v2.0-1b-th.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/tongyi-model-v2.0-1b-th-GGUF/resolve/main/tongyi-model-v2.0-1b-th.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/tongyi-model-v2.0-1b-th-GGUF/resolve/main/tongyi-model-v2.0-1b-th.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/tongyi-model-v2.0-1b-th-GGUF/resolve/main/tongyi-model-v2.0-1b-th.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/tongyi-model-v2.0-1b-th-GGUF/resolve/main/tongyi-model-v2.0-1b-th.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/tongyi-model-v2.0-1b-th-GGUF/resolve/main/tongyi-model-v2.0-1b-th.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/tongyi-model-v2.0-1b-th-GGUF/resolve/main/tongyi-model-v2.0-1b-th.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/tongyi-model-v2.0-1b-th-GGUF/resolve/main/tongyi-model-v2.0-1b-th.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/tongyi-model-v2.0-1b-th-GGUF/resolve/main/tongyi-model-v2.0-1b-th.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/tongyi-model-v2.0-1b-th-GGUF/resolve/main/tongyi-model-v2.0-1b-th.f16.gguf) | f16 | 2.6 | 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/tongyi-model-v2.0-1b-th.IQ4_XS.gguf b/tongyi-model-v2.0-1b-th.IQ4_XS.gguf new file mode 100644 index 0000000..5fc4bcb --- /dev/null +++ b/tongyi-model-v2.0-1b-th.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d885d5cb4fa1e33167c5de6654a40cf968b196d9b20566c0754ce9a27bbfeb8 +size 748385792 diff --git a/tongyi-model-v2.0-1b-th.Q2_K.gguf b/tongyi-model-v2.0-1b-th.Q2_K.gguf new file mode 100644 index 0000000..9b9bbbe --- /dev/null +++ b/tongyi-model-v2.0-1b-th.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b786caa2ca5331bdf6f929caad5157fdf74750ad4c57a9fa251894990550370 +size 580875776 diff --git a/tongyi-model-v2.0-1b-th.Q3_K_L.gguf b/tongyi-model-v2.0-1b-th.Q3_K_L.gguf new file mode 100644 index 0000000..4738712 --- /dev/null +++ b/tongyi-model-v2.0-1b-th.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:628a566e9bf053e47c77d72a48050bcedd662f4240504df175db020740b03153 +size 732526080 diff --git a/tongyi-model-v2.0-1b-th.Q3_K_M.gguf b/tongyi-model-v2.0-1b-th.Q3_K_M.gguf new file mode 100644 index 0000000..199af36 --- /dev/null +++ b/tongyi-model-v2.0-1b-th.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57ef382ac70270bfb74bbdd8032bc65e0712a51b7fbd64d48dbbd22d007e069a +size 690845184 diff --git a/tongyi-model-v2.0-1b-th.Q3_K_S.gguf b/tongyi-model-v2.0-1b-th.Q3_K_S.gguf new file mode 100644 index 0000000..2cdc371 --- /dev/null +++ b/tongyi-model-v2.0-1b-th.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8a867272d0a2e4ee0a68b026da8db4574498fe31a485c8774ae15e61ddb915b +size 641693184 diff --git a/tongyi-model-v2.0-1b-th.Q4_K_M.gguf b/tongyi-model-v2.0-1b-th.Q4_K_M.gguf new file mode 100644 index 0000000..19a7dbf --- /dev/null +++ b/tongyi-model-v2.0-1b-th.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcbdbf78aadf2e0ed4eeb030d7895344245c70237fd4b74a75501dbd138c8c78 +size 807695872 diff --git a/tongyi-model-v2.0-1b-th.Q4_K_S.gguf b/tongyi-model-v2.0-1b-th.Q4_K_S.gguf new file mode 100644 index 0000000..032ae0a --- /dev/null +++ b/tongyi-model-v2.0-1b-th.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af50a228823894cff2ac605ed39b981d6b900d94ff03695b484ddc56a31115bb +size 775648768 diff --git a/tongyi-model-v2.0-1b-th.Q5_K_M.gguf b/tongyi-model-v2.0-1b-th.Q5_K_M.gguf new file mode 100644 index 0000000..f7c8406 --- /dev/null +++ b/tongyi-model-v2.0-1b-th.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eabd3989a516b2985519c16dc6da0e5a8c81562da77e4e6f4dfaf46796b0bfb +size 911504896 diff --git a/tongyi-model-v2.0-1b-th.Q5_K_S.gguf b/tongyi-model-v2.0-1b-th.Q5_K_S.gguf new file mode 100644 index 0000000..5eb9f1a --- /dev/null +++ b/tongyi-model-v2.0-1b-th.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:877db520dbb2a09d10a8b046473e2fccee5e24cae567d0084eb169146710ef6a +size 892564992 diff --git a/tongyi-model-v2.0-1b-th.Q6_K.gguf b/tongyi-model-v2.0-1b-th.Q6_K.gguf new file mode 100644 index 0000000..8022256 --- /dev/null +++ b/tongyi-model-v2.0-1b-th.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29b8e18ec27ff95def626adac64c5dd1fd967118338f15da7a09cfbe7ff9a744 +size 1021801984 diff --git a/tongyi-model-v2.0-1b-th.Q8_0.gguf b/tongyi-model-v2.0-1b-th.Q8_0.gguf new file mode 100644 index 0000000..1320172 --- /dev/null +++ b/tongyi-model-v2.0-1b-th.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25a415928435a4682fc6a4dc4a1812bc6bb47cc04d31580051fca74b7b2c7d8e +size 1321084416 diff --git a/tongyi-model-v2.0-1b-th.f16.gguf b/tongyi-model-v2.0-1b-th.f16.gguf new file mode 100644 index 0000000..98b0908 --- /dev/null +++ b/tongyi-model-v2.0-1b-th.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb0b9f92124ebfe082a814b8400217a21d35b128b1aa1deea2e7705b257d8772 +size 2479597056