commit 76f2633a02775f46b5560f6130f2f6814e055cbd Author: ModelHub XC Date: Tue Jun 2 19:18:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/guru-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1ca492b --- /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 +guru-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +guru-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +guru-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +guru-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +guru-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +guru-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +guru-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +guru-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +guru-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +guru-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +guru-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +guru-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..61dea2e --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: LLM360/guru-7B +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/LLM360/guru-7B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/guru-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/guru-7B-GGUF/resolve/main/guru-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/guru-7B-GGUF/resolve/main/guru-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/guru-7B-GGUF/resolve/main/guru-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/guru-7B-GGUF/resolve/main/guru-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/guru-7B-GGUF/resolve/main/guru-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/guru-7B-GGUF/resolve/main/guru-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/guru-7B-GGUF/resolve/main/guru-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/guru-7B-GGUF/resolve/main/guru-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/guru-7B-GGUF/resolve/main/guru-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/guru-7B-GGUF/resolve/main/guru-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/guru-7B-GGUF/resolve/main/guru-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/guru-7B-GGUF/resolve/main/guru-7B.f16.gguf) | f16 | 15.3 | 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. + + diff --git a/guru-7B.IQ4_XS.gguf b/guru-7B.IQ4_XS.gguf new file mode 100644 index 0000000..e213594 --- /dev/null +++ b/guru-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68314375a0e7a82c1f2d97f74c8a59fdb11470f2aa321c237a9f9fb920078edd +size 4250298944 diff --git a/guru-7B.Q2_K.gguf b/guru-7B.Q2_K.gguf new file mode 100644 index 0000000..ca12b35 --- /dev/null +++ b/guru-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eebf4ca5a684dc39be401354d8876741a366a5b0d5dc2e3f098bb5bfa5bbb64b +size 3015940672 diff --git a/guru-7B.Q3_K_L.gguf b/guru-7B.Q3_K_L.gguf new file mode 100644 index 0000000..bb572df --- /dev/null +++ b/guru-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7e05e5eed3bd71f2a7529097d2a9420125c073baa02be5f62f4ce3cc0091acd +size 4088459840 diff --git a/guru-7B.Q3_K_M.gguf b/guru-7B.Q3_K_M.gguf new file mode 100644 index 0000000..bf5bec9 --- /dev/null +++ b/guru-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0278478ebe694d87d522a5e4df3b0280d1d93cbcb96b49ddb0d8bdebf31b329 +size 3808391744 diff --git a/guru-7B.Q3_K_S.gguf b/guru-7B.Q3_K_S.gguf new file mode 100644 index 0000000..b8e9d0d --- /dev/null +++ b/guru-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d798a43112917a7e4dd4b75dab444558e2b88c1f347b4b698540cf08552ffca +size 3492368960 diff --git a/guru-7B.Q4_K_M.gguf b/guru-7B.Q4_K_M.gguf new file mode 100644 index 0000000..5e5e092 --- /dev/null +++ b/guru-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f286ce55759db971d6edb7583dcc6438859d838465434900200e330ca7636f0e +size 4683074112 diff --git a/guru-7B.Q4_K_S.gguf b/guru-7B.Q4_K_S.gguf new file mode 100644 index 0000000..151e9b3 --- /dev/null +++ b/guru-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4f6269d6ccb167bb555b180c10b47bf8025b2c4d2152610a805b9d0595455ea +size 4457769536 diff --git a/guru-7B.Q5_K_M.gguf b/guru-7B.Q5_K_M.gguf new file mode 100644 index 0000000..a151255 --- /dev/null +++ b/guru-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:319e622d6bef461a6621d1b343ddf301d9d12ed0b274fc2a5b1bf3e2a76c95db +size 5444831808 diff --git a/guru-7B.Q5_K_S.gguf b/guru-7B.Q5_K_S.gguf new file mode 100644 index 0000000..d510c97 --- /dev/null +++ b/guru-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24149b62c04a5cd03659fe866a502ecf533e088d4960634a91cce12ffb346ac8 +size 5315177024 diff --git a/guru-7B.Q6_K.gguf b/guru-7B.Q6_K.gguf new file mode 100644 index 0000000..083a9ce --- /dev/null +++ b/guru-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fbecb09cee8e64caaf43c3ee53810333945d3fc4622c427f83d173bfe8d1eca +size 6254199360 diff --git a/guru-7B.Q8_0.gguf b/guru-7B.Q8_0.gguf new file mode 100644 index 0000000..a5dd755 --- /dev/null +++ b/guru-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:532c4dde85e802fe53c05a52c4472803f24aa65a5d8e862cfa8e8672467183be +size 8098525760 diff --git a/guru-7B.f16.gguf b/guru-7B.f16.gguf new file mode 100644 index 0000000..49cd608 --- /dev/null +++ b/guru-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b628d8bf3afc77be1de02a57ff4098907a0d8d4bbdcba3090bf78b28e23b692 +size 15237853760