commit 550733d870261876d4e1e121fbe917ea7300bb16 Author: ModelHub XC Date: Mon Jul 6 10:43:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama2-7b-sft-ultrachat-hhrlhf-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7f315de --- /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-hhrlhf.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat-hhrlhf.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat-hhrlhf.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat-hhrlhf.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat-hhrlhf.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat-hhrlhf.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat-hhrlhf.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat-hhrlhf.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat-hhrlhf.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat-hhrlhf.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat-hhrlhf.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-sft-ultrachat-hhrlhf.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..86fef03 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: AmberYifan/llama2-7b-sft-ultrachat-hhrlhf +language: +- en +library_name: transformers +model_name: llama2-7b-sft-ultrachat-hhrlhf +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/llama2-7b-sft-ultrachat-hhrlhf + + +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-hhrlhf-GGUF/resolve/main/llama2-7b-sft-ultrachat-hhrlhf.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-hhrlhf-GGUF/resolve/main/llama2-7b-sft-ultrachat-hhrlhf.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-hhrlhf-GGUF/resolve/main/llama2-7b-sft-ultrachat-hhrlhf.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-hhrlhf-GGUF/resolve/main/llama2-7b-sft-ultrachat-hhrlhf.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-hhrlhf-GGUF/resolve/main/llama2-7b-sft-ultrachat-hhrlhf.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-hhrlhf-GGUF/resolve/main/llama2-7b-sft-ultrachat-hhrlhf.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-hhrlhf-GGUF/resolve/main/llama2-7b-sft-ultrachat-hhrlhf.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-hhrlhf-GGUF/resolve/main/llama2-7b-sft-ultrachat-hhrlhf.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-hhrlhf-GGUF/resolve/main/llama2-7b-sft-ultrachat-hhrlhf.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-hhrlhf-GGUF/resolve/main/llama2-7b-sft-ultrachat-hhrlhf.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-hhrlhf-GGUF/resolve/main/llama2-7b-sft-ultrachat-hhrlhf.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-sft-ultrachat-hhrlhf-GGUF/resolve/main/llama2-7b-sft-ultrachat-hhrlhf.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/llama2-7b-sft-ultrachat-hhrlhf.IQ4_XS.gguf b/llama2-7b-sft-ultrachat-hhrlhf.IQ4_XS.gguf new file mode 100644 index 0000000..ab09e19 --- /dev/null +++ b/llama2-7b-sft-ultrachat-hhrlhf.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f6a470723ba86c4ace5f4863b1339cec61c124056d4420fe7ca7f3c047e0711 +size 3647518272 diff --git a/llama2-7b-sft-ultrachat-hhrlhf.Q2_K.gguf b/llama2-7b-sft-ultrachat-hhrlhf.Q2_K.gguf new file mode 100644 index 0000000..338ec84 --- /dev/null +++ b/llama2-7b-sft-ultrachat-hhrlhf.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2aa9796378a46365c0df1f2e54a72a558391722c0f4894663b666260d84b1ba +size 2532865600 diff --git a/llama2-7b-sft-ultrachat-hhrlhf.Q3_K_L.gguf b/llama2-7b-sft-ultrachat-hhrlhf.Q3_K_L.gguf new file mode 100644 index 0000000..d8adbd7 --- /dev/null +++ b/llama2-7b-sft-ultrachat-hhrlhf.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:222f2eb1ac89c922a2db57e27d75020bfe8d388481dc92549cbecb1914a5f439 +size 3597112896 diff --git a/llama2-7b-sft-ultrachat-hhrlhf.Q3_K_M.gguf b/llama2-7b-sft-ultrachat-hhrlhf.Q3_K_M.gguf new file mode 100644 index 0000000..f8e3a07 --- /dev/null +++ b/llama2-7b-sft-ultrachat-hhrlhf.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:125f1024f5ca8558c94fbdc78f4dcb7e6b938c1b00eff33dd58edca5884a0408 +size 3298006592 diff --git a/llama2-7b-sft-ultrachat-hhrlhf.Q3_K_S.gguf b/llama2-7b-sft-ultrachat-hhrlhf.Q3_K_S.gguf new file mode 100644 index 0000000..41a13d8 --- /dev/null +++ b/llama2-7b-sft-ultrachat-hhrlhf.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1626adc9bf01181e557553665697c117c0b3d76dc3e79f3072d3551a74cefa79 +size 2948306496 diff --git a/llama2-7b-sft-ultrachat-hhrlhf.Q4_K_M.gguf b/llama2-7b-sft-ultrachat-hhrlhf.Q4_K_M.gguf new file mode 100644 index 0000000..de793e8 --- /dev/null +++ b/llama2-7b-sft-ultrachat-hhrlhf.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5fc3aa8b5a9a748f470f124dfd9f17bfaf77b83e4c5c6b73da32eba2469b40b +size 4081006144 diff --git a/llama2-7b-sft-ultrachat-hhrlhf.Q4_K_S.gguf b/llama2-7b-sft-ultrachat-hhrlhf.Q4_K_S.gguf new file mode 100644 index 0000000..178bcde --- /dev/null +++ b/llama2-7b-sft-ultrachat-hhrlhf.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f56fb493553d9a3320f0afd75a008e966bcb6d168a25297f19b6bd73e5c733ee +size 3856741952 diff --git a/llama2-7b-sft-ultrachat-hhrlhf.Q5_K_M.gguf b/llama2-7b-sft-ultrachat-hhrlhf.Q5_K_M.gguf new file mode 100644 index 0000000..52552c3 --- /dev/null +++ b/llama2-7b-sft-ultrachat-hhrlhf.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9e08f7a3f71fd5f750767483713b59f3f1fe9a0107be50cfb99452f26db106e +size 4783158848 diff --git a/llama2-7b-sft-ultrachat-hhrlhf.Q5_K_S.gguf b/llama2-7b-sft-ultrachat-hhrlhf.Q5_K_S.gguf new file mode 100644 index 0000000..6f561d1 --- /dev/null +++ b/llama2-7b-sft-ultrachat-hhrlhf.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:557e46e651a11332f2e48f680973ebebf52123c6bc666798e3c0b50a82898126 +size 4651693632 diff --git a/llama2-7b-sft-ultrachat-hhrlhf.Q6_K.gguf b/llama2-7b-sft-ultrachat-hhrlhf.Q6_K.gguf new file mode 100644 index 0000000..1b730a4 --- /dev/null +++ b/llama2-7b-sft-ultrachat-hhrlhf.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:062e9cbe3794f6bb2167a92123654f95cab68bbcaeb62f010bc184c2c5d7233c +size 5529196096 diff --git a/llama2-7b-sft-ultrachat-hhrlhf.Q8_0.gguf b/llama2-7b-sft-ultrachat-hhrlhf.Q8_0.gguf new file mode 100644 index 0000000..9dd7a53 --- /dev/null +++ b/llama2-7b-sft-ultrachat-hhrlhf.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b83b837e347fca639d58c6e54ab0f924f029c5feb37014e68e94580bd645e0c4 +size 7161091648 diff --git a/llama2-7b-sft-ultrachat-hhrlhf.f16.gguf b/llama2-7b-sft-ultrachat-hhrlhf.f16.gguf new file mode 100644 index 0000000..697cbf3 --- /dev/null +++ b/llama2-7b-sft-ultrachat-hhrlhf.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d441b6e64258e671b82ab5f3a99c32311d411a36833d5fa6e5b0d2b4c0868e69 +size 13478106688