commit 607646c875afb9ae8588de1773a232f08db86a81 Author: ModelHub XC Date: Mon Aug 10 00:55:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama2-7b-sft-ultrachat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..79a4dd8 --- /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 +llama2-7b-sft-ultrachat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..194f1b0 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: AmberYifan/llama2-7b-sft-ultrachat +language: +- en +library_name: transformers +model_name: llama2-7b-sft-ultrachat +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/llama2-7b-sft-ultrachat + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama2-7b-sft-ultrachat-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/llama2-7b-sft-ultrachat-GGUF/resolve/main/llama2-7b-sft-ultrachat.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-GGUF/resolve/main/llama2-7b-sft-ultrachat.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-GGUF/resolve/main/llama2-7b-sft-ultrachat.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-GGUF/resolve/main/llama2-7b-sft-ultrachat.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-GGUF/resolve/main/llama2-7b-sft-ultrachat.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-GGUF/resolve/main/llama2-7b-sft-ultrachat.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-GGUF/resolve/main/llama2-7b-sft-ultrachat.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-GGUF/resolve/main/llama2-7b-sft-ultrachat.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-GGUF/resolve/main/llama2-7b-sft-ultrachat.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-GGUF/resolve/main/llama2-7b-sft-ultrachat.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-GGUF/resolve/main/llama2-7b-sft-ultrachat.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-GGUF/resolve/main/llama2-7b-sft-ultrachat.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/llama2-7b-sft-ultrachat.IQ4_XS.gguf b/llama2-7b-sft-ultrachat.IQ4_XS.gguf new file mode 100644 index 0000000..58efd87 --- /dev/null +++ b/llama2-7b-sft-ultrachat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eb4598f5d217abe296b981d11fab75f8d21d8d2a60c70fde86992852f3563db +size 3647518208 diff --git a/llama2-7b-sft-ultrachat.Q2_K.gguf b/llama2-7b-sft-ultrachat.Q2_K.gguf new file mode 100644 index 0000000..88f09f6 --- /dev/null +++ b/llama2-7b-sft-ultrachat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a343533fd89756d526a0e7dc3a83d3d309d2770bd2b0df074f89539a2341a86 +size 2532865536 diff --git a/llama2-7b-sft-ultrachat.Q3_K_L.gguf b/llama2-7b-sft-ultrachat.Q3_K_L.gguf new file mode 100644 index 0000000..585d47c --- /dev/null +++ b/llama2-7b-sft-ultrachat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:076235999ef3899ebe38047fcfc87191c2e2647af1e4e50288d64524b024dbd2 +size 3597112832 diff --git a/llama2-7b-sft-ultrachat.Q3_K_M.gguf b/llama2-7b-sft-ultrachat.Q3_K_M.gguf new file mode 100644 index 0000000..9634a76 --- /dev/null +++ b/llama2-7b-sft-ultrachat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09c0b596445630238488adf8ab63e3e01427c654947bdbf08efe6af6af5b966c +size 3298006528 diff --git a/llama2-7b-sft-ultrachat.Q3_K_S.gguf b/llama2-7b-sft-ultrachat.Q3_K_S.gguf new file mode 100644 index 0000000..81c6676 --- /dev/null +++ b/llama2-7b-sft-ultrachat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2b9ae88d1d402a6c4541587d9cc3f7e72987540b98b31be2643505100e415e9 +size 2948306432 diff --git a/llama2-7b-sft-ultrachat.Q4_K_M.gguf b/llama2-7b-sft-ultrachat.Q4_K_M.gguf new file mode 100644 index 0000000..d2c2257 --- /dev/null +++ b/llama2-7b-sft-ultrachat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f380131d7e364e93d9164e4d4b8293662347d45b4ac54bb77caabbfce1ddfec5 +size 4081006080 diff --git a/llama2-7b-sft-ultrachat.Q4_K_S.gguf b/llama2-7b-sft-ultrachat.Q4_K_S.gguf new file mode 100644 index 0000000..df9e655 --- /dev/null +++ b/llama2-7b-sft-ultrachat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f4b003a4ed3a6c8d3cc487d2c37cb01736cdd031485072c7c758e24e504e18a +size 3856741888 diff --git a/llama2-7b-sft-ultrachat.Q5_K_M.gguf b/llama2-7b-sft-ultrachat.Q5_K_M.gguf new file mode 100644 index 0000000..3a00441 --- /dev/null +++ b/llama2-7b-sft-ultrachat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62c3075dcb18588a366c5a169aa302382364cd20d5c0835a1eaa30454df0a9f7 +size 4783158784 diff --git a/llama2-7b-sft-ultrachat.Q5_K_S.gguf b/llama2-7b-sft-ultrachat.Q5_K_S.gguf new file mode 100644 index 0000000..e604c68 --- /dev/null +++ b/llama2-7b-sft-ultrachat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:422f94e76eaebf00cb25281afb4d9654b8730516d98d1df2a79c6c5fed906b0a +size 4651693568 diff --git a/llama2-7b-sft-ultrachat.Q6_K.gguf b/llama2-7b-sft-ultrachat.Q6_K.gguf new file mode 100644 index 0000000..59054d5 --- /dev/null +++ b/llama2-7b-sft-ultrachat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b07e7db51029664f12135532f5c2be4c3bc414122413753e555d4fb3a7476c91 +size 5529196032 diff --git a/llama2-7b-sft-ultrachat.Q8_0.gguf b/llama2-7b-sft-ultrachat.Q8_0.gguf new file mode 100644 index 0000000..c279f4d --- /dev/null +++ b/llama2-7b-sft-ultrachat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51bc8db0ee26c713590b08c04c45eba48cc04a592ceeca0a8e7216ee5715d367 +size 7161091584 diff --git a/llama2-7b-sft-ultrachat.f16.gguf b/llama2-7b-sft-ultrachat.f16.gguf new file mode 100644 index 0000000..6e60bfc --- /dev/null +++ b/llama2-7b-sft-ultrachat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:640abb95d34ce467a86a448e8f42e35ed13cd8488f75029a925224d7b27263ff +size 13478106624