commit dd4409b360fa3ba225aa3b5dd7532a270f5ef251 Author: ModelHub XC Date: Thu Jul 30 21:35:24 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLaMA2-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a9ccca8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +LLaMA2-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA2-7B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLaMA2-7B.IQ4_XS.gguf b/LLaMA2-7B.IQ4_XS.gguf new file mode 100644 index 0000000..1f04cd0 --- /dev/null +++ b/LLaMA2-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45d028e69a6aa532d9f920af6ec48bcb76c17e4088fd26c9ac9fbc080cfba4c4 +size 3647517472 diff --git a/LLaMA2-7B.Q2_K.gguf b/LLaMA2-7B.Q2_K.gguf new file mode 100644 index 0000000..f701ee3 --- /dev/null +++ b/LLaMA2-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:020e4dc2ee20c85ea6012124420c4c9140bc7c4bcce7276558c1a4071a4daf84 +size 2532864800 diff --git a/LLaMA2-7B.Q3_K_L.gguf b/LLaMA2-7B.Q3_K_L.gguf new file mode 100644 index 0000000..68c4d2a --- /dev/null +++ b/LLaMA2-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2fbf3ddf5fe0b153745ae78c7199c55280809f609437872f70d4195aa31e1b3 +size 3597112096 diff --git a/LLaMA2-7B.Q3_K_M.gguf b/LLaMA2-7B.Q3_K_M.gguf new file mode 100644 index 0000000..84f6083 --- /dev/null +++ b/LLaMA2-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76e538de1483b17c284160ae132e893be57583c68b8b4f914b5f8ff8a01a7f6d +size 3298005792 diff --git a/LLaMA2-7B.Q3_K_S.gguf b/LLaMA2-7B.Q3_K_S.gguf new file mode 100644 index 0000000..4da2d51 --- /dev/null +++ b/LLaMA2-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5072e3ca1b7f63a270270bb0fc896f89992d1bf07e57ad5b4fa43b526e129be2 +size 2948305696 diff --git a/LLaMA2-7B.Q4_0_4_4.gguf b/LLaMA2-7B.Q4_0_4_4.gguf new file mode 100644 index 0000000..4eef73d --- /dev/null +++ b/LLaMA2-7B.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:219c8172687e5bfcf3d5c5bc433b60404cb714ab6d646873b431feeaa0798d80 +size 3825808160 diff --git a/LLaMA2-7B.Q4_K_M.gguf b/LLaMA2-7B.Q4_K_M.gguf new file mode 100644 index 0000000..bc267ac --- /dev/null +++ b/LLaMA2-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc5ea2d8d8f4d6f8d75a40cf572f53512287124cb354f4eb445a77c7fac3eae6 +size 4081005344 diff --git a/LLaMA2-7B.Q4_K_S.gguf b/LLaMA2-7B.Q4_K_S.gguf new file mode 100644 index 0000000..e562e00 --- /dev/null +++ b/LLaMA2-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c868d319351f2da6a97cbff54b31661cd169ff19677fc1cecaad3c6d7d4ab971 +size 3856741152 diff --git a/LLaMA2-7B.Q5_K_M.gguf b/LLaMA2-7B.Q5_K_M.gguf new file mode 100644 index 0000000..921f85c --- /dev/null +++ b/LLaMA2-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e259c2382b7e5b2ae56c4739149b8f6670b5f2639f941553e91c3ca33d1e187 +size 4783158048 diff --git a/LLaMA2-7B.Q5_K_S.gguf b/LLaMA2-7B.Q5_K_S.gguf new file mode 100644 index 0000000..2a982dc --- /dev/null +++ b/LLaMA2-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:567b46c45a958544ae719e8a3702a0621262c75a955d0fb6decb845d4b057466 +size 4651692832 diff --git a/LLaMA2-7B.Q6_K.gguf b/LLaMA2-7B.Q6_K.gguf new file mode 100644 index 0000000..9eec44b --- /dev/null +++ b/LLaMA2-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae312a9f6cbd709cfaf96490436f8bc172a3bf1e1ba3fe8dbca2c3e15856d00c +size 5529195296 diff --git a/LLaMA2-7B.Q8_0.gguf b/LLaMA2-7B.Q8_0.gguf new file mode 100644 index 0000000..f80dab1 --- /dev/null +++ b/LLaMA2-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fdc463719b297785c3fc69eab52f737320b442fcb81e76174669644b11fb4bf +size 7161090848 diff --git a/LLaMA2-7B.f16.gguf b/LLaMA2-7B.f16.gguf new file mode 100644 index 0000000..5b5eb16 --- /dev/null +++ b/LLaMA2-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc3d05a54051504f5b9d103fab1caf89257b4480048ee96a8324f55d3a501c67 +size 13478105888 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3a7dd84 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: GraphWiz/LLaMA2-7B +datasets: +- GraphWiz/GraphInstruct-RFT-72K +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- graph problem +--- +## About + + + + + + +static quants of https://huggingface.co/GraphWiz/LLaMA2-7B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/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/LLaMA2-7B-GGUF/resolve/main/LLaMA2-7B.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-GGUF/resolve/main/LLaMA2-7B.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-GGUF/resolve/main/LLaMA2-7B.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-GGUF/resolve/main/LLaMA2-7B.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-GGUF/resolve/main/LLaMA2-7B.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-GGUF/resolve/main/LLaMA2-7B.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-GGUF/resolve/main/LLaMA2-7B.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-GGUF/resolve/main/LLaMA2-7B.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-GGUF/resolve/main/LLaMA2-7B.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-GGUF/resolve/main/LLaMA2-7B.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-GGUF/resolve/main/LLaMA2-7B.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-GGUF/resolve/main/LLaMA2-7B.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA2-7B-GGUF/resolve/main/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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +