commit d7f63935f435f0bf948ade9bea0d4668445ad28f Author: ModelHub XC Date: Wed Jun 24 11:33:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-2-7b-chat-hf-30-sparsity-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c469c97 --- /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 +Llama-2-7b-chat-hf-30-sparsity.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf-30-sparsity.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf-30-sparsity.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf-30-sparsity.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf-30-sparsity.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf-30-sparsity.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf-30-sparsity.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf-30-sparsity.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf-30-sparsity.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf-30-sparsity.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf-30-sparsity.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf-30-sparsity.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7b-chat-hf-30-sparsity.IQ4_XS.gguf b/Llama-2-7b-chat-hf-30-sparsity.IQ4_XS.gguf new file mode 100644 index 0000000..1e9abde --- /dev/null +++ b/Llama-2-7b-chat-hf-30-sparsity.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c3f2826e401b7e0b2c498cb97cced26e1a754b37ce9dd9972b66a886a989e6b +size 3647517472 diff --git a/Llama-2-7b-chat-hf-30-sparsity.Q2_K.gguf b/Llama-2-7b-chat-hf-30-sparsity.Q2_K.gguf new file mode 100644 index 0000000..7d4abb5 --- /dev/null +++ b/Llama-2-7b-chat-hf-30-sparsity.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9769a9842166392e6b2a6de0ae0408ee3b86da57e662f8124184033d7c31c2d1 +size 2532864800 diff --git a/Llama-2-7b-chat-hf-30-sparsity.Q3_K_L.gguf b/Llama-2-7b-chat-hf-30-sparsity.Q3_K_L.gguf new file mode 100644 index 0000000..a912180 --- /dev/null +++ b/Llama-2-7b-chat-hf-30-sparsity.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4c651dd60129ddb41c29f7d50b5f1e4ab9a9bb8cecef092f9b05d72dd151b5e +size 3597112096 diff --git a/Llama-2-7b-chat-hf-30-sparsity.Q3_K_M.gguf b/Llama-2-7b-chat-hf-30-sparsity.Q3_K_M.gguf new file mode 100644 index 0000000..8bede14 --- /dev/null +++ b/Llama-2-7b-chat-hf-30-sparsity.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6d4277e9d225e2f400658a517911bc6ed4f749045bbd2f753439643bba073b9 +size 3298005792 diff --git a/Llama-2-7b-chat-hf-30-sparsity.Q3_K_S.gguf b/Llama-2-7b-chat-hf-30-sparsity.Q3_K_S.gguf new file mode 100644 index 0000000..b180738 --- /dev/null +++ b/Llama-2-7b-chat-hf-30-sparsity.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d89b35ccbe2e2d171774bad95318b5c76b2d7cd5dca380ced7f094a0c63d9a71 +size 2948305696 diff --git a/Llama-2-7b-chat-hf-30-sparsity.Q4_K_M.gguf b/Llama-2-7b-chat-hf-30-sparsity.Q4_K_M.gguf new file mode 100644 index 0000000..9c39067 --- /dev/null +++ b/Llama-2-7b-chat-hf-30-sparsity.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3b34cfc3c06e18bb306e9a053b9ca9e50332c596a630452d8d3e4acd7e95bc5 +size 4081005344 diff --git a/Llama-2-7b-chat-hf-30-sparsity.Q4_K_S.gguf b/Llama-2-7b-chat-hf-30-sparsity.Q4_K_S.gguf new file mode 100644 index 0000000..4b5b2a6 --- /dev/null +++ b/Llama-2-7b-chat-hf-30-sparsity.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c243cc9ee94059af530f20de89983632a900e4687dcd7db0696a91c982f39b88 +size 3856741152 diff --git a/Llama-2-7b-chat-hf-30-sparsity.Q5_K_M.gguf b/Llama-2-7b-chat-hf-30-sparsity.Q5_K_M.gguf new file mode 100644 index 0000000..2c63f38 --- /dev/null +++ b/Llama-2-7b-chat-hf-30-sparsity.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a22b9e66c02ef71983cac53ca7ec77c649bd3d1550942768e3d628cf9ecb1624 +size 4783158048 diff --git a/Llama-2-7b-chat-hf-30-sparsity.Q5_K_S.gguf b/Llama-2-7b-chat-hf-30-sparsity.Q5_K_S.gguf new file mode 100644 index 0000000..8f67def --- /dev/null +++ b/Llama-2-7b-chat-hf-30-sparsity.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:620ca1ee80c71cbc77a793fc47afc69d588896c4637f92fc2012a10a01b36a58 +size 4651692832 diff --git a/Llama-2-7b-chat-hf-30-sparsity.Q6_K.gguf b/Llama-2-7b-chat-hf-30-sparsity.Q6_K.gguf new file mode 100644 index 0000000..cacbb02 --- /dev/null +++ b/Llama-2-7b-chat-hf-30-sparsity.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6b006e19b194f4a0baaef8b93354a7ecd14db5d467c1dca49c4f592d94567c3 +size 5529195296 diff --git a/Llama-2-7b-chat-hf-30-sparsity.Q8_0.gguf b/Llama-2-7b-chat-hf-30-sparsity.Q8_0.gguf new file mode 100644 index 0000000..4bda4c7 --- /dev/null +++ b/Llama-2-7b-chat-hf-30-sparsity.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0b085f3bf114916a40394dbdd3e2885d0a84c46eeb9692702ed566b12081bdf +size 7161090848 diff --git a/Llama-2-7b-chat-hf-30-sparsity.f16.gguf b/Llama-2-7b-chat-hf-30-sparsity.f16.gguf new file mode 100644 index 0000000..e9c1a38 --- /dev/null +++ b/Llama-2-7b-chat-hf-30-sparsity.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:656b4b2c5a4910cf76979663d2e773fbca9b86eaebab45ff74a18b4895f53160 +size 13478105888 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cc74818 --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: wang7776/Llama-2-7b-chat-hf-30-sparsity +extra_gated_button_content: Submit +extra_gated_fields: + ? I agree to share my name, email address and username with Meta and confirm that + I have already been granted download access on the Meta website + : checkbox +extra_gated_heading: Access Llama 2 on Hugging Face +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- facebook +- meta +- pytorch +- llama +- llama-2 +--- +## About + + + + + + +static quants of https://huggingface.co/wang7776/Llama-2-7b-chat-hf-30-sparsity + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-2-7b-chat-hf-30-sparsity-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/Llama-2-7b-chat-hf-30-sparsity-GGUF/resolve/main/Llama-2-7b-chat-hf-30-sparsity.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf-30-sparsity-GGUF/resolve/main/Llama-2-7b-chat-hf-30-sparsity.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf-30-sparsity-GGUF/resolve/main/Llama-2-7b-chat-hf-30-sparsity.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf-30-sparsity-GGUF/resolve/main/Llama-2-7b-chat-hf-30-sparsity.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf-30-sparsity-GGUF/resolve/main/Llama-2-7b-chat-hf-30-sparsity.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf-30-sparsity-GGUF/resolve/main/Llama-2-7b-chat-hf-30-sparsity.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf-30-sparsity-GGUF/resolve/main/Llama-2-7b-chat-hf-30-sparsity.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf-30-sparsity-GGUF/resolve/main/Llama-2-7b-chat-hf-30-sparsity.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf-30-sparsity-GGUF/resolve/main/Llama-2-7b-chat-hf-30-sparsity.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf-30-sparsity-GGUF/resolve/main/Llama-2-7b-chat-hf-30-sparsity.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf-30-sparsity-GGUF/resolve/main/Llama-2-7b-chat-hf-30-sparsity.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf-30-sparsity-GGUF/resolve/main/Llama-2-7b-chat-hf-30-sparsity.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. + +