commit 07a6607ab797fb18de975553f16027c1a3aff79f Author: ModelHub XC Date: Tue Jun 16 02:26:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GWQ2b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..50e6d6b --- /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 +GWQ2b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GWQ2b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GWQ2b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GWQ2b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GWQ2b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GWQ2b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GWQ2b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GWQ2b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GWQ2b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GWQ2b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GWQ2b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GWQ2b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GWQ2b.IQ4_XS.gguf b/GWQ2b.IQ4_XS.gguf new file mode 100644 index 0000000..a8c12f9 --- /dev/null +++ b/GWQ2b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f25f7de599b63c677d21650469ca8f05986f45f499b7b90a1e7bec4797e0351 +size 1576204640 diff --git a/GWQ2b.Q2_K.gguf b/GWQ2b.Q2_K.gguf new file mode 100644 index 0000000..b6b52aa --- /dev/null +++ b/GWQ2b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd690f471cd5fac118498b62680d25a69988f40a1dc7f06fbbb8c9ef80a43a87 +size 1229830496 diff --git a/GWQ2b.Q3_K_L.gguf b/GWQ2b.Q3_K_L.gguf new file mode 100644 index 0000000..3f45152 --- /dev/null +++ b/GWQ2b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cfe540c87ddd8801d26f398fb45279387417a16ba63675f4abed0a0501c98c8 +size 1550436704 diff --git a/GWQ2b.Q3_K_M.gguf b/GWQ2b.Q3_K_M.gguf new file mode 100644 index 0000000..180471e --- /dev/null +++ b/GWQ2b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea3756c1190289b450d30594163ed8343ac48fd502f033cd60a665c78d12e1f1 +size 1461668192 diff --git a/GWQ2b.Q3_K_S.gguf b/GWQ2b.Q3_K_S.gguf new file mode 100644 index 0000000..716fd70 --- /dev/null +++ b/GWQ2b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6856636bbecc3a96a3f13208ac62ec3064c82d9766a928452f6ef9d0677e0884 +size 1360660832 diff --git a/GWQ2b.Q4_K_M.gguf b/GWQ2b.Q4_K_M.gguf new file mode 100644 index 0000000..6cb3dc6 --- /dev/null +++ b/GWQ2b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c536d84d1caca04dba61e0fb2ce489d93cc5eb702d2039df8b4de7c646d7e634 +size 1708583264 diff --git a/GWQ2b.Q4_K_S.gguf b/GWQ2b.Q4_K_S.gguf new file mode 100644 index 0000000..c949b9f --- /dev/null +++ b/GWQ2b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ae65ef72553b3f8a3dca8efaa5c2e6feb64a4215ddd27f809e36b3321122f87 +size 1638652256 diff --git a/GWQ2b.Q5_K_M.gguf b/GWQ2b.Q5_K_M.gguf new file mode 100644 index 0000000..1036046 --- /dev/null +++ b/GWQ2b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ce8368ce67ebb2b8515831fbfea9e90fa901a031d25c7128c9c0db3de3fe826 +size 1923279200 diff --git a/GWQ2b.Q5_K_S.gguf b/GWQ2b.Q5_K_S.gguf new file mode 100644 index 0000000..1625e7a --- /dev/null +++ b/GWQ2b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88961d35b2431c86862ef4a688f9bb12ca08b4b901d1748b4eb71c9096a963c1 +size 1882544480 diff --git a/GWQ2b.Q6_K.gguf b/GWQ2b.Q6_K.gguf new file mode 100644 index 0000000..1dde1da --- /dev/null +++ b/GWQ2b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8b46aa4a98f732b0468fda77688447d373f38157eb217968756e2bdfc712910 +size 2151393632 diff --git a/GWQ2b.Q8_0.gguf b/GWQ2b.Q8_0.gguf new file mode 100644 index 0000000..9a89861 --- /dev/null +++ b/GWQ2b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1ae00c15f731c889e031194bc63e43fd4921a308e6509327d4524ee63757d06 +size 2784495968 diff --git a/GWQ2b.f16.gguf b/GWQ2b.f16.gguf new file mode 100644 index 0000000..6b35faa --- /dev/null +++ b/GWQ2b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49f0e35534f8a4e426f226cab8e9d2d463c24e1ba15ade6c8588af01b40351a5 +size 5235214688 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fa786c9 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: prithivMLmods/GWQ2b +language: +- en +library_name: transformers +license: gemma +quantized_by: mradermacher +tags: +- gemma +- 2b +- CoT +- text-generation-inference +- gwq2b +- gemma-with-question +- safetensors +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/GWQ2b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/GWQ2b-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/GWQ2b-GGUF/resolve/main/GWQ2b.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/GWQ2b-GGUF/resolve/main/GWQ2b.Q3_K_S.gguf) | Q3_K_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/GWQ2b-GGUF/resolve/main/GWQ2b.Q3_K_M.gguf) | Q3_K_M | 1.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GWQ2b-GGUF/resolve/main/GWQ2b.Q3_K_L.gguf) | Q3_K_L | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/GWQ2b-GGUF/resolve/main/GWQ2b.IQ4_XS.gguf) | IQ4_XS | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/GWQ2b-GGUF/resolve/main/GWQ2b.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GWQ2b-GGUF/resolve/main/GWQ2b.Q4_K_M.gguf) | Q4_K_M | 1.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GWQ2b-GGUF/resolve/main/GWQ2b.Q5_K_S.gguf) | Q5_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/GWQ2b-GGUF/resolve/main/GWQ2b.Q5_K_M.gguf) | Q5_K_M | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/GWQ2b-GGUF/resolve/main/GWQ2b.Q6_K.gguf) | Q6_K | 2.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GWQ2b-GGUF/resolve/main/GWQ2b.Q8_0.gguf) | Q8_0 | 2.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GWQ2b-GGUF/resolve/main/GWQ2b.f16.gguf) | f16 | 5.3 | 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. + +