commit 2dd0a2d2f4909f52a9d0b39ec5d62bcbefd6b3af Author: ModelHub XC Date: Thu Jul 16 15:14:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-2-7b-chat-sexed-version2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7c4edd0 --- /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-sexed-version2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-chat-sexed-version2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-chat-sexed-version2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-chat-sexed-version2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-chat-sexed-version2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-chat-sexed-version2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-chat-sexed-version2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-chat-sexed-version2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-chat-sexed-version2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-chat-sexed-version2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-chat-sexed-version2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-chat-sexed-version2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..52cafa5 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: ben-wycliff/llama-2-7b-chat-sexed-version2 +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/ben-wycliff/llama-2-7b-chat-sexed-version2 + + +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-sexed-version2-GGUF/resolve/main/llama-2-7b-chat-sexed-version2.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-chat-sexed-version2-GGUF/resolve/main/llama-2-7b-chat-sexed-version2.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-chat-sexed-version2-GGUF/resolve/main/llama-2-7b-chat-sexed-version2.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-chat-sexed-version2-GGUF/resolve/main/llama-2-7b-chat-sexed-version2.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-chat-sexed-version2-GGUF/resolve/main/llama-2-7b-chat-sexed-version2.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-chat-sexed-version2-GGUF/resolve/main/llama-2-7b-chat-sexed-version2.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-chat-sexed-version2-GGUF/resolve/main/llama-2-7b-chat-sexed-version2.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-chat-sexed-version2-GGUF/resolve/main/llama-2-7b-chat-sexed-version2.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-chat-sexed-version2-GGUF/resolve/main/llama-2-7b-chat-sexed-version2.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-chat-sexed-version2-GGUF/resolve/main/llama-2-7b-chat-sexed-version2.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-chat-sexed-version2-GGUF/resolve/main/llama-2-7b-chat-sexed-version2.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-chat-sexed-version2-GGUF/resolve/main/llama-2-7b-chat-sexed-version2.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. + + diff --git a/llama-2-7b-chat-sexed-version2.IQ4_XS.gguf b/llama-2-7b-chat-sexed-version2.IQ4_XS.gguf new file mode 100644 index 0000000..8742891 --- /dev/null +++ b/llama-2-7b-chat-sexed-version2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e39a4128766fedd3c9db33a43ee5e3ac4bda67e323c538ede97eadd6bbc2f792 +size 3647518048 diff --git a/llama-2-7b-chat-sexed-version2.Q2_K.gguf b/llama-2-7b-chat-sexed-version2.Q2_K.gguf new file mode 100644 index 0000000..a71a29a --- /dev/null +++ b/llama-2-7b-chat-sexed-version2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82305c6cc154b7d54f4870b6beb2d98fd490da50f0f53688e36040afec9139ff +size 2532865376 diff --git a/llama-2-7b-chat-sexed-version2.Q3_K_L.gguf b/llama-2-7b-chat-sexed-version2.Q3_K_L.gguf new file mode 100644 index 0000000..c65b4a3 --- /dev/null +++ b/llama-2-7b-chat-sexed-version2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c96e7bc94a5abd5032f64084f70672fc3bd840f9642bcba45e5ce1dfe77de38f +size 3597112672 diff --git a/llama-2-7b-chat-sexed-version2.Q3_K_M.gguf b/llama-2-7b-chat-sexed-version2.Q3_K_M.gguf new file mode 100644 index 0000000..384336f --- /dev/null +++ b/llama-2-7b-chat-sexed-version2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20a22c8bf7ab45cabbc4782cf9e907ae3fb170f59dc7536d8462725fbb77462c +size 3298006368 diff --git a/llama-2-7b-chat-sexed-version2.Q3_K_S.gguf b/llama-2-7b-chat-sexed-version2.Q3_K_S.gguf new file mode 100644 index 0000000..866b1c8 --- /dev/null +++ b/llama-2-7b-chat-sexed-version2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22f2591ef2304f50b25ed69c720c97a2bd6dab8c6bce15aae10ca46fc0a5efaa +size 2948306272 diff --git a/llama-2-7b-chat-sexed-version2.Q4_K_M.gguf b/llama-2-7b-chat-sexed-version2.Q4_K_M.gguf new file mode 100644 index 0000000..d673fa3 --- /dev/null +++ b/llama-2-7b-chat-sexed-version2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce65f0ebf831b922d99ba2fe1cb5371c107ab88e83a76c589402db0c370e8b20 +size 4081005920 diff --git a/llama-2-7b-chat-sexed-version2.Q4_K_S.gguf b/llama-2-7b-chat-sexed-version2.Q4_K_S.gguf new file mode 100644 index 0000000..c8a4c80 --- /dev/null +++ b/llama-2-7b-chat-sexed-version2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fab01a97626d9bf16cf4d6db4a49fbd4da1fa3e05ef57028dc5d6fde6c51a78a +size 3856741728 diff --git a/llama-2-7b-chat-sexed-version2.Q5_K_M.gguf b/llama-2-7b-chat-sexed-version2.Q5_K_M.gguf new file mode 100644 index 0000000..4c16328 --- /dev/null +++ b/llama-2-7b-chat-sexed-version2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd411e7601b9c2c1835eb9fcb46a9f2af6aaab7a42b335e9b8a11798093a7337 +size 4783158624 diff --git a/llama-2-7b-chat-sexed-version2.Q5_K_S.gguf b/llama-2-7b-chat-sexed-version2.Q5_K_S.gguf new file mode 100644 index 0000000..f2b9c86 --- /dev/null +++ b/llama-2-7b-chat-sexed-version2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef5ab16fc11eddd0775411c08dc6ca43f64ba0f52eba5f26874c6d85d377d266 +size 4651693408 diff --git a/llama-2-7b-chat-sexed-version2.Q6_K.gguf b/llama-2-7b-chat-sexed-version2.Q6_K.gguf new file mode 100644 index 0000000..2c7475b --- /dev/null +++ b/llama-2-7b-chat-sexed-version2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7858cb8c0f78f71d15f3a0be3ba33e057e80bf0fbb491ca5e4058d3182e20e9 +size 5529195872 diff --git a/llama-2-7b-chat-sexed-version2.Q8_0.gguf b/llama-2-7b-chat-sexed-version2.Q8_0.gguf new file mode 100644 index 0000000..250fa29 --- /dev/null +++ b/llama-2-7b-chat-sexed-version2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5696028eb08a7afda9ac916376a7a26418633d447bbd3ee32d0660cc24cce470 +size 7161091424 diff --git a/llama-2-7b-chat-sexed-version2.f16.gguf b/llama-2-7b-chat-sexed-version2.f16.gguf new file mode 100644 index 0000000..a1d3112 --- /dev/null +++ b/llama-2-7b-chat-sexed-version2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e36f4e2fb5e34863785c00e6c331bd62674372a739e4f6b1eae6ad2f666df109 +size 13478106464