commit 9db4116e808e617575a6ad66e87d80b9b5048545 Author: ModelHub XC Date: Sun Jun 14 07:08:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/StruXGPT-v2-Llama2-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d51d44f --- /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 +StruXGPT-v2-Llama2-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +StruXGPT-v2-Llama2-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +StruXGPT-v2-Llama2-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +StruXGPT-v2-Llama2-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +StruXGPT-v2-Llama2-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +StruXGPT-v2-Llama2-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +StruXGPT-v2-Llama2-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +StruXGPT-v2-Llama2-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +StruXGPT-v2-Llama2-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +StruXGPT-v2-Llama2-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +StruXGPT-v2-Llama2-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +StruXGPT-v2-Llama2-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7691c66 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: StruXGPT/StruXGPT-v2-Llama2-7B +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/StruXGPT/StruXGPT-v2-Llama2-7B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/StruXGPT-v2-Llama2-7B-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/StruXGPT-v2-Llama2-7B-GGUF/resolve/main/StruXGPT-v2-Llama2-7B.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/StruXGPT-v2-Llama2-7B-GGUF/resolve/main/StruXGPT-v2-Llama2-7B.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/StruXGPT-v2-Llama2-7B-GGUF/resolve/main/StruXGPT-v2-Llama2-7B.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/StruXGPT-v2-Llama2-7B-GGUF/resolve/main/StruXGPT-v2-Llama2-7B.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/StruXGPT-v2-Llama2-7B-GGUF/resolve/main/StruXGPT-v2-Llama2-7B.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/StruXGPT-v2-Llama2-7B-GGUF/resolve/main/StruXGPT-v2-Llama2-7B.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/StruXGPT-v2-Llama2-7B-GGUF/resolve/main/StruXGPT-v2-Llama2-7B.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/StruXGPT-v2-Llama2-7B-GGUF/resolve/main/StruXGPT-v2-Llama2-7B.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/StruXGPT-v2-Llama2-7B-GGUF/resolve/main/StruXGPT-v2-Llama2-7B.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/StruXGPT-v2-Llama2-7B-GGUF/resolve/main/StruXGPT-v2-Llama2-7B.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/StruXGPT-v2-Llama2-7B-GGUF/resolve/main/StruXGPT-v2-Llama2-7B.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/StruXGPT-v2-Llama2-7B-GGUF/resolve/main/StruXGPT-v2-Llama2-7B.f16.gguf) | f16 | 13.6 | 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/StruXGPT-v2-Llama2-7B.IQ4_XS.gguf b/StruXGPT-v2-Llama2-7B.IQ4_XS.gguf new file mode 100644 index 0000000..88fe037 --- /dev/null +++ b/StruXGPT-v2-Llama2-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dced94cb9990003022ad3ed5eb4a9387e81a51e214aa0d5477ed0054eefd7a70 +size 3647517920 diff --git a/StruXGPT-v2-Llama2-7B.Q2_K.gguf b/StruXGPT-v2-Llama2-7B.Q2_K.gguf new file mode 100644 index 0000000..38569c6 --- /dev/null +++ b/StruXGPT-v2-Llama2-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d098863beb168f7d3543fc1f834c4234e3498ea6964e079de8454b8565247381 +size 2532865248 diff --git a/StruXGPT-v2-Llama2-7B.Q3_K_L.gguf b/StruXGPT-v2-Llama2-7B.Q3_K_L.gguf new file mode 100644 index 0000000..642d9e3 --- /dev/null +++ b/StruXGPT-v2-Llama2-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3545e20918b91e0f180a509efad62d792d9965457036c44c5ee23787be89777 +size 3597112544 diff --git a/StruXGPT-v2-Llama2-7B.Q3_K_M.gguf b/StruXGPT-v2-Llama2-7B.Q3_K_M.gguf new file mode 100644 index 0000000..641bfa0 --- /dev/null +++ b/StruXGPT-v2-Llama2-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f41fd12ada4a8900148fb5d5af4344952933f3589f5a8b9f1ac0a50025dab870 +size 3298006240 diff --git a/StruXGPT-v2-Llama2-7B.Q3_K_S.gguf b/StruXGPT-v2-Llama2-7B.Q3_K_S.gguf new file mode 100644 index 0000000..ff8f30b --- /dev/null +++ b/StruXGPT-v2-Llama2-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bec9d989c73665b7a057024be050ef7ab5c85b3d241e7a9169355792e602655 +size 2948306144 diff --git a/StruXGPT-v2-Llama2-7B.Q4_K_M.gguf b/StruXGPT-v2-Llama2-7B.Q4_K_M.gguf new file mode 100644 index 0000000..6249742 --- /dev/null +++ b/StruXGPT-v2-Llama2-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfa7f825bd21974c319d18a4452b328b3272ca8c73009fb4b74f82212ab16539 +size 4081005792 diff --git a/StruXGPT-v2-Llama2-7B.Q4_K_S.gguf b/StruXGPT-v2-Llama2-7B.Q4_K_S.gguf new file mode 100644 index 0000000..0fe9932 --- /dev/null +++ b/StruXGPT-v2-Llama2-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04e58a6815ee9f1ec80bc74f8e22e90eb2c73c5d19df768a227d08887a150c1d +size 3856741600 diff --git a/StruXGPT-v2-Llama2-7B.Q5_K_M.gguf b/StruXGPT-v2-Llama2-7B.Q5_K_M.gguf new file mode 100644 index 0000000..a5bb636 --- /dev/null +++ b/StruXGPT-v2-Llama2-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f10ae244b1d9126edb230e83905a6719b6815d5ce2388d06078f22fd9034cc4a +size 4783158496 diff --git a/StruXGPT-v2-Llama2-7B.Q5_K_S.gguf b/StruXGPT-v2-Llama2-7B.Q5_K_S.gguf new file mode 100644 index 0000000..cb2f91f --- /dev/null +++ b/StruXGPT-v2-Llama2-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e966016e4a766352297dd16de07d4425b00612c56a073c8830f3c305366010a3 +size 4651693280 diff --git a/StruXGPT-v2-Llama2-7B.Q6_K.gguf b/StruXGPT-v2-Llama2-7B.Q6_K.gguf new file mode 100644 index 0000000..b6a48b8 --- /dev/null +++ b/StruXGPT-v2-Llama2-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56c5d2359b69a7fa54db21ca5b6d9ec14c6a6d48d234b1d639fcd9f286102131 +size 5529195744 diff --git a/StruXGPT-v2-Llama2-7B.Q8_0.gguf b/StruXGPT-v2-Llama2-7B.Q8_0.gguf new file mode 100644 index 0000000..e9381ad --- /dev/null +++ b/StruXGPT-v2-Llama2-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87e6085813973f0885065b403a07948888d0d5eb1376f1a517b5246776ea15d6 +size 7161091296 diff --git a/StruXGPT-v2-Llama2-7B.f16.gguf b/StruXGPT-v2-Llama2-7B.f16.gguf new file mode 100644 index 0000000..cff1f2a --- /dev/null +++ b/StruXGPT-v2-Llama2-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3c80a69cd9cce44137edde3df90199ee4bd5db84e9c7b0e6fd11c81d16af2df +size 13478106336