commit 5d97dcb2b62989e45035c36f321bd4ade6628b10 Author: ModelHub XC Date: Thu Sep 24 04:43:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/HuatuoGPT2-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f7224a1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +HuatuoGPT2-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT2-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT2-7B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT2-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT2-7B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT2-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT2-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT2-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT2-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT2-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT2-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT2-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT2-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT2-7B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT2-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/HuatuoGPT2-7B.IQ3_M.gguf b/HuatuoGPT2-7B.IQ3_M.gguf new file mode 100644 index 0000000..8286a34 --- /dev/null +++ b/HuatuoGPT2-7B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90f0ee5bc08bce7b600585e4546b51f406ec504db768fdd15c99e357cf021efa +size 3596726496 diff --git a/HuatuoGPT2-7B.IQ3_S.gguf b/HuatuoGPT2-7B.IQ3_S.gguf new file mode 100644 index 0000000..56d9865 --- /dev/null +++ b/HuatuoGPT2-7B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ef42bc17bbb10a2eac01f0342c66b4230213582ff320480ce9e55a52d98a9ba +size 3430166752 diff --git a/HuatuoGPT2-7B.IQ3_XS.gguf b/HuatuoGPT2-7B.IQ3_XS.gguf new file mode 100644 index 0000000..e74d0a3 --- /dev/null +++ b/HuatuoGPT2-7B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:117fa91e987695c5454a7778347a52076cd55d8108fbf493bdb21aaf76d37b4f +size 3278385376 diff --git a/HuatuoGPT2-7B.IQ4_XS.gguf b/HuatuoGPT2-7B.IQ4_XS.gguf new file mode 100644 index 0000000..a1325f3 --- /dev/null +++ b/HuatuoGPT2-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2ad51e30d4ffccab8ffcc89e69b155b33da6140e32bc5fe3341897960676d6a +size 4168356064 diff --git a/HuatuoGPT2-7B.Q2_K.gguf b/HuatuoGPT2-7B.Q2_K.gguf new file mode 100644 index 0000000..846ead0 --- /dev/null +++ b/HuatuoGPT2-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d19d8f16becbfb08705eabf161c48d219dfb629f5a43b26a8b3e242892e39ba0 +size 2975748320 diff --git a/HuatuoGPT2-7B.Q3_K_L.gguf b/HuatuoGPT2-7B.Q3_K_L.gguf new file mode 100644 index 0000000..1b78484 --- /dev/null +++ b/HuatuoGPT2-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:409bb92e46e6f2ae994ae950d9c4e358115ad20f600d933970f6611373b426d9 +size 4078973152 diff --git a/HuatuoGPT2-7B.Q3_K_M.gguf b/HuatuoGPT2-7B.Q3_K_M.gguf new file mode 100644 index 0000000..50941fe --- /dev/null +++ b/HuatuoGPT2-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e2487c12c812b02ce1109c0fb9343e95dddbd063138e39deb40645ee74e4aab +size 3779866848 diff --git a/HuatuoGPT2-7B.Q3_K_S.gguf b/HuatuoGPT2-7B.Q3_K_S.gguf new file mode 100644 index 0000000..81a6ae7 --- /dev/null +++ b/HuatuoGPT2-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d4745cd06b190e6779f534ba405c85df5072523083f1ba7a0ef5a4a94c97e28 +size 3430166752 diff --git a/HuatuoGPT2-7B.Q4_K_M.gguf b/HuatuoGPT2-7B.Q4_K_M.gguf new file mode 100644 index 0000000..480f7ab --- /dev/null +++ b/HuatuoGPT2-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c965262f7423c4f497cedbed08c54e46bb710425bcbe3239e10a75423edd71f +size 4613837024 diff --git a/HuatuoGPT2-7B.Q4_K_S.gguf b/HuatuoGPT2-7B.Q4_K_S.gguf new file mode 100644 index 0000000..02df849 --- /dev/null +++ b/HuatuoGPT2-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:142c8cc028356413b774fca58361c193c83f6016b4e868446e29155b04076756 +size 4389572832 diff --git a/HuatuoGPT2-7B.Q5_K_M.gguf b/HuatuoGPT2-7B.Q5_K_M.gguf new file mode 100644 index 0000000..657c9c9 --- /dev/null +++ b/HuatuoGPT2-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12c459ccf2fd4cdc84c9625cbcbb0b26c5fda495bc898c74e9db6e3432417acb +size 5363962080 diff --git a/HuatuoGPT2-7B.Q5_K_S.gguf b/HuatuoGPT2-7B.Q5_K_S.gguf new file mode 100644 index 0000000..fda8cfd --- /dev/null +++ b/HuatuoGPT2-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3d2ad78523f9467ca65cfd3fd085e55a4a74b4180575ed68f493a484bb15536 +size 5232496864 diff --git a/HuatuoGPT2-7B.Q6_K.gguf b/HuatuoGPT2-7B.Q6_K.gguf new file mode 100644 index 0000000..ddd5353 --- /dev/null +++ b/HuatuoGPT2-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32a5bf8e93f975d49602d2db9dd4bb7b5b18679152eb349bd0bdb2ad010ff5fa +size 6160969952 diff --git a/HuatuoGPT2-7B.Q8_0.gguf b/HuatuoGPT2-7B.Q8_0.gguf new file mode 100644 index 0000000..5f0c88c --- /dev/null +++ b/HuatuoGPT2-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfae671ee08dee6e12ffed8a4c474de258f3b421d66f07f5323155941d8b0b4c +size 7978758368 diff --git a/HuatuoGPT2-7B.f16.gguf b/HuatuoGPT2-7B.f16.gguf new file mode 100644 index 0000000..853bb5e --- /dev/null +++ b/HuatuoGPT2-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e03b557cb76dbd6f3bfff2cae8207bc933fa3e7aba366704ab42c1324ab70330 +size 15015358688 diff --git a/README.md b/README.md new file mode 100644 index 0000000..adbaf5e --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: FreedomIntelligence/HuatuoGPT2-7B +language: +- zh +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/FreedomIntelligence/HuatuoGPT2-7B + + +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/HuatuoGPT2-7B-GGUF/resolve/main/HuatuoGPT2-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT2-7B-GGUF/resolve/main/HuatuoGPT2-7B.IQ3_XS.gguf) | IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT2-7B-GGUF/resolve/main/HuatuoGPT2-7B.IQ3_S.gguf) | IQ3_S | 3.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT2-7B-GGUF/resolve/main/HuatuoGPT2-7B.Q3_K_S.gguf) | Q3_K_S | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT2-7B-GGUF/resolve/main/HuatuoGPT2-7B.IQ3_M.gguf) | IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT2-7B-GGUF/resolve/main/HuatuoGPT2-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT2-7B-GGUF/resolve/main/HuatuoGPT2-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT2-7B-GGUF/resolve/main/HuatuoGPT2-7B.IQ4_XS.gguf) | IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT2-7B-GGUF/resolve/main/HuatuoGPT2-7B.Q4_K_S.gguf) | Q4_K_S | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT2-7B-GGUF/resolve/main/HuatuoGPT2-7B.Q4_K_M.gguf) | Q4_K_M | 4.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT2-7B-GGUF/resolve/main/HuatuoGPT2-7B.Q5_K_S.gguf) | Q5_K_S | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT2-7B-GGUF/resolve/main/HuatuoGPT2-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT2-7B-GGUF/resolve/main/HuatuoGPT2-7B.Q6_K.gguf) | Q6_K | 6.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT2-7B-GGUF/resolve/main/HuatuoGPT2-7B.Q8_0.gguf) | Q8_0 | 8.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT2-7B-GGUF/resolve/main/HuatuoGPT2-7B.f16.gguf) | f16 | 15.1 | 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. + +