commit e67be3e9e298c78d02f30a6cda17b535d1d936e2 Author: ModelHub XC Date: Wed Aug 19 16:21:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama2_Femicide-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..833768e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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_Femicide.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama2_Femicide.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama2_Femicide.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama2_Femicide.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama2_Femicide.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama2_Femicide.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama2_Femicide.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama2_Femicide.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama2_Femicide.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama2_Femicide.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama2_Femicide.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama2_Femicide.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama2_Femicide.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama2_Femicide.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama2_Femicide.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama2_Femicide.IQ3_M.gguf b/Llama2_Femicide.IQ3_M.gguf new file mode 100644 index 0000000..64632bc --- /dev/null +++ b/Llama2_Femicide.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f393af537815c9e908da049867bf390accb39fce98fda93471221b2df362dbf6 +size 3114865856 diff --git a/Llama2_Femicide.IQ3_S.gguf b/Llama2_Femicide.IQ3_S.gguf new file mode 100644 index 0000000..d458ffa --- /dev/null +++ b/Llama2_Femicide.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b09025a14cdafbc334f404dafb336152c245c33b6516f201a46806ddca0696bf +size 2948306112 diff --git a/Llama2_Femicide.IQ3_XS.gguf b/Llama2_Femicide.IQ3_XS.gguf new file mode 100644 index 0000000..8e511e0 --- /dev/null +++ b/Llama2_Femicide.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cdf6c07fceed49491b817ec08c4c8479ab2554a2ed22a41c4d75a520f957110 +size 2796524736 diff --git a/Llama2_Femicide.IQ4_XS.gguf b/Llama2_Femicide.IQ4_XS.gguf new file mode 100644 index 0000000..af84f26 --- /dev/null +++ b/Llama2_Femicide.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eefbe882f13537242f251a2c90d3f72ddf02461ec92c90390a6b98613d694884 +size 3647517888 diff --git a/Llama2_Femicide.Q2_K.gguf b/Llama2_Femicide.Q2_K.gguf new file mode 100644 index 0000000..da17b1b --- /dev/null +++ b/Llama2_Femicide.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc10fdf9958e276a18023eb79c517fad693410eb4703ce08b35d32d8ae1b1380 +size 2532865216 diff --git a/Llama2_Femicide.Q3_K_L.gguf b/Llama2_Femicide.Q3_K_L.gguf new file mode 100644 index 0000000..4c548e6 --- /dev/null +++ b/Llama2_Femicide.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb2a00b7da95c822e073487ccdab1689d9b8ad0a992d4e6e38fed609d2ad75c0 +size 3597112512 diff --git a/Llama2_Femicide.Q3_K_M.gguf b/Llama2_Femicide.Q3_K_M.gguf new file mode 100644 index 0000000..3f2d104 --- /dev/null +++ b/Llama2_Femicide.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ea73974b07c30f13f314fabe84e6782993bdbc002b03abae8c71637bec366a5 +size 3298006208 diff --git a/Llama2_Femicide.Q3_K_S.gguf b/Llama2_Femicide.Q3_K_S.gguf new file mode 100644 index 0000000..f9ecc41 --- /dev/null +++ b/Llama2_Femicide.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc8724075fc1d829b1b555117edd5ad558cb7c63cbb9c1bb2d1c090bfff16dd0 +size 2948306112 diff --git a/Llama2_Femicide.Q4_K_M.gguf b/Llama2_Femicide.Q4_K_M.gguf new file mode 100644 index 0000000..8616559 --- /dev/null +++ b/Llama2_Femicide.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a16e3283c5b165cb8554992547db0330263386bf33933b215e26b8497e25b09 +size 4081005760 diff --git a/Llama2_Femicide.Q4_K_S.gguf b/Llama2_Femicide.Q4_K_S.gguf new file mode 100644 index 0000000..aaf18ba --- /dev/null +++ b/Llama2_Femicide.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a641882ced0bdb790cd8c92ba59e6c6c3c7cd608f969e0e73941cebf7f866b6 +size 3856741568 diff --git a/Llama2_Femicide.Q5_K_M.gguf b/Llama2_Femicide.Q5_K_M.gguf new file mode 100644 index 0000000..f668d1a --- /dev/null +++ b/Llama2_Femicide.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f9fa1bdcb30105d89965d582f56c354bebff771311816c1628764c3fee32df2 +size 4783158464 diff --git a/Llama2_Femicide.Q5_K_S.gguf b/Llama2_Femicide.Q5_K_S.gguf new file mode 100644 index 0000000..bb68fd2 --- /dev/null +++ b/Llama2_Femicide.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3db744922142c0f3d13b5d007516cdb5193e99681e1e3f5ea87fb8c3327a981d +size 4651693248 diff --git a/Llama2_Femicide.Q6_K.gguf b/Llama2_Femicide.Q6_K.gguf new file mode 100644 index 0000000..8e1eab9 --- /dev/null +++ b/Llama2_Femicide.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:652d4ca4be3e4851b4ea6c41d87e4ee6a06b6193408a17acb7e7d9d3d345a173 +size 5529195712 diff --git a/Llama2_Femicide.Q8_0.gguf b/Llama2_Femicide.Q8_0.gguf new file mode 100644 index 0000000..4e9166d --- /dev/null +++ b/Llama2_Femicide.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4165fb9f15704506624a0b959fb8a9aa9666d779a0bc29bd9df7a502beb6ddac +size 7161091264 diff --git a/Llama2_Femicide.f16.gguf b/Llama2_Femicide.f16.gguf new file mode 100644 index 0000000..49a09f1 --- /dev/null +++ b/Llama2_Femicide.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d802ba3a36ff5d8585dee06aeb75bd112057d890a8f494d71a062bdc1ea15489 +size 13478106304 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2082e2e --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: gizemgg/Llama2_Femicide +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/gizemgg/Llama2_Femicide + + +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_Femicide-GGUF/resolve/main/Llama2_Femicide.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2_Femicide-GGUF/resolve/main/Llama2_Femicide.IQ3_XS.gguf) | IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2_Femicide-GGUF/resolve/main/Llama2_Femicide.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama2_Femicide-GGUF/resolve/main/Llama2_Femicide.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2_Femicide-GGUF/resolve/main/Llama2_Femicide.IQ3_M.gguf) | IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2_Femicide-GGUF/resolve/main/Llama2_Femicide.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama2_Femicide-GGUF/resolve/main/Llama2_Femicide.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2_Femicide-GGUF/resolve/main/Llama2_Femicide.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2_Femicide-GGUF/resolve/main/Llama2_Femicide.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama2_Femicide-GGUF/resolve/main/Llama2_Femicide.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama2_Femicide-GGUF/resolve/main/Llama2_Femicide.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2_Femicide-GGUF/resolve/main/Llama2_Femicide.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2_Femicide-GGUF/resolve/main/Llama2_Femicide.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama2_Femicide-GGUF/resolve/main/Llama2_Femicide.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama2_Femicide-GGUF/resolve/main/Llama2_Femicide.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. + +