commit 6f7fde9033aea562f1fa28c1edfef840fcbf0be6 Author: ModelHub XC Date: Thu Jun 18 07:26:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama2-13b-hyperbolic-cluster-pruned-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a8ad7ae --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +llama2-13b-hyperbolic-cluster-pruned.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-hyperbolic-cluster-pruned.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-hyperbolic-cluster-pruned.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-hyperbolic-cluster-pruned.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-hyperbolic-cluster-pruned.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-hyperbolic-cluster-pruned.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-hyperbolic-cluster-pruned.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-hyperbolic-cluster-pruned.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-hyperbolic-cluster-pruned.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-hyperbolic-cluster-pruned.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-hyperbolic-cluster-pruned.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8f91f81 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: namannn/llama2-13b-hyperbolic-cluster-pruned +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- chemistry +- biology +- finance +- legal +- music +- art +- code +- climate +- medical +- quantized +--- +## About + + + + + + +static quants of https://huggingface.co/namannn/llama2-13b-hyperbolic-cluster-pruned + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama2-13b-hyperbolic-cluster-pruned-GGUF).*** + +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/llama2-13b-hyperbolic-cluster-pruned-GGUF/resolve/main/llama2-13b-hyperbolic-cluster-pruned.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-13b-hyperbolic-cluster-pruned-GGUF/resolve/main/llama2-13b-hyperbolic-cluster-pruned.Q3_K_S.gguf) | Q3_K_S | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-13b-hyperbolic-cluster-pruned-GGUF/resolve/main/llama2-13b-hyperbolic-cluster-pruned.Q3_K_M.gguf) | Q3_K_M | 5.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-13b-hyperbolic-cluster-pruned-GGUF/resolve/main/llama2-13b-hyperbolic-cluster-pruned.Q3_K_L.gguf) | Q3_K_L | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-13b-hyperbolic-cluster-pruned-GGUF/resolve/main/llama2-13b-hyperbolic-cluster-pruned.IQ4_XS.gguf) | IQ4_XS | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-13b-hyperbolic-cluster-pruned-GGUF/resolve/main/llama2-13b-hyperbolic-cluster-pruned.Q4_K_S.gguf) | Q4_K_S | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama2-13b-hyperbolic-cluster-pruned-GGUF/resolve/main/llama2-13b-hyperbolic-cluster-pruned.Q4_K_M.gguf) | Q4_K_M | 6.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama2-13b-hyperbolic-cluster-pruned-GGUF/resolve/main/llama2-13b-hyperbolic-cluster-pruned.Q5_K_S.gguf) | Q5_K_S | 7.1 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-13b-hyperbolic-cluster-pruned-GGUF/resolve/main/llama2-13b-hyperbolic-cluster-pruned.Q5_K_M.gguf) | Q5_K_M | 7.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-13b-hyperbolic-cluster-pruned-GGUF/resolve/main/llama2-13b-hyperbolic-cluster-pruned.Q6_K.gguf) | Q6_K | 8.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-13b-hyperbolic-cluster-pruned-GGUF/resolve/main/llama2-13b-hyperbolic-cluster-pruned.Q8_0.gguf) | Q8_0 | 10.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-13b-hyperbolic-cluster-pruned-GGUF/resolve/main/llama2-13b-hyperbolic-cluster-pruned.f16.gguf) | f16 | 20.4 | 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/llama2-13b-hyperbolic-cluster-pruned.IQ4_XS.gguf b/llama2-13b-hyperbolic-cluster-pruned.IQ4_XS.gguf new file mode 100644 index 0000000..7900f82 --- /dev/null +++ b/llama2-13b-hyperbolic-cluster-pruned.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e5d9bbf973caa2cff0f337aba36f15c00514ea01c632bed57556b375d77d5a4 +size 5480442560 diff --git a/llama2-13b-hyperbolic-cluster-pruned.Q2_K.gguf b/llama2-13b-hyperbolic-cluster-pruned.Q2_K.gguf new file mode 100644 index 0000000..a34f486 --- /dev/null +++ b/llama2-13b-hyperbolic-cluster-pruned.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff0f30bd264f11fec130561395a12e5fc5cf05bc49f71c7d23ea9a0232a9111c +size 3804564160 diff --git a/llama2-13b-hyperbolic-cluster-pruned.Q3_K_L.gguf b/llama2-13b-hyperbolic-cluster-pruned.Q3_K_L.gguf new file mode 100644 index 0000000..538535a --- /dev/null +++ b/llama2-13b-hyperbolic-cluster-pruned.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c346328c9855ee8641f9fb979701ce2ed15f3903a5252450c8f64e0ec7075a3f +size 5416657600 diff --git a/llama2-13b-hyperbolic-cluster-pruned.Q3_K_M.gguf b/llama2-13b-hyperbolic-cluster-pruned.Q3_K_M.gguf new file mode 100644 index 0000000..975ca14 --- /dev/null +++ b/llama2-13b-hyperbolic-cluster-pruned.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58b4695c97865e1c7fb7ba683ef1f27244b207aa3e0d417ec01b5638008cb656 +size 4954628800 diff --git a/llama2-13b-hyperbolic-cluster-pruned.Q3_K_S.gguf b/llama2-13b-hyperbolic-cluster-pruned.Q3_K_S.gguf new file mode 100644 index 0000000..e5a2675 --- /dev/null +++ b/llama2-13b-hyperbolic-cluster-pruned.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42270d22c612b5da7dc4eafb459f06fd3ed7f2adf3903295b076c452039f1859 +size 4431958720 diff --git a/llama2-13b-hyperbolic-cluster-pruned.Q4_K_M.gguf b/llama2-13b-hyperbolic-cluster-pruned.Q4_K_M.gguf new file mode 100644 index 0000000..98e25b4 --- /dev/null +++ b/llama2-13b-hyperbolic-cluster-pruned.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ccb29971e025279d43e58c01c3471386ed4bda5bba533cde7750bf37bad1144 +size 6134758080 diff --git a/llama2-13b-hyperbolic-cluster-pruned.Q4_K_S.gguf b/llama2-13b-hyperbolic-cluster-pruned.Q4_K_S.gguf new file mode 100644 index 0000000..56b2a64 --- /dev/null +++ b/llama2-13b-hyperbolic-cluster-pruned.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ed289bc6a8c7f6cbf701eb72a8f8274b932881b1c84e35ab645215c714587ba +size 5799316160 diff --git a/llama2-13b-hyperbolic-cluster-pruned.Q5_K_M.gguf b/llama2-13b-hyperbolic-cluster-pruned.Q5_K_M.gguf new file mode 100644 index 0000000..2159138 --- /dev/null +++ b/llama2-13b-hyperbolic-cluster-pruned.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ee7c82b62f63f9435715ffe6613e7468fa0f48875779ff4ee8e8c3c94a20c7b +size 7202503360 diff --git a/llama2-13b-hyperbolic-cluster-pruned.Q5_K_S.gguf b/llama2-13b-hyperbolic-cluster-pruned.Q5_K_S.gguf new file mode 100644 index 0000000..8b6a471 --- /dev/null +++ b/llama2-13b-hyperbolic-cluster-pruned.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ee85c0816a38437d7c6d9f0264839258cfd4165b14fae3aaa01cb14fdcfc5c7 +size 7009274560 diff --git a/llama2-13b-hyperbolic-cluster-pruned.Q6_K.gguf b/llama2-13b-hyperbolic-cluster-pruned.Q6_K.gguf new file mode 100644 index 0000000..996b745 --- /dev/null +++ b/llama2-13b-hyperbolic-cluster-pruned.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95d933f4b90ef000befa7a62834514e9833557b79b08485bdf4fd4bda0dedc62 +size 8336982720 diff --git a/llama2-13b-hyperbolic-cluster-pruned.Q8_0.gguf b/llama2-13b-hyperbolic-cluster-pruned.Q8_0.gguf new file mode 100644 index 0000000..7d55eb7 --- /dev/null +++ b/llama2-13b-hyperbolic-cluster-pruned.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ffe052fdcb602c23d1a7ddeb3c168a68243d3571b114cb39a898a1a8f1db12f +size 10797777600 diff --git a/llama2-13b-hyperbolic-cluster-pruned.f16.gguf b/llama2-13b-hyperbolic-cluster-pruned.f16.gguf new file mode 100644 index 0000000..4c77cb9 --- /dev/null +++ b/llama2-13b-hyperbolic-cluster-pruned.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cead92ecbba8dc55f23eefd04aec048deec013a7c0a3c0e1b0de6dccaa37e715 +size 20323435200