commit d0687a85ec7f9920123b4dcef430ff3db3dfc015 Author: ModelHub XC Date: Fri Jul 3 01:30:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-2-7b-sft-hhrlhf-dpo-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0ecab2d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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-sft-hhrlhf-dpo.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-hhrlhf-dpo.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-hhrlhf-dpo.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-hhrlhf-dpo.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-hhrlhf-dpo.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-hhrlhf-dpo.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-hhrlhf-dpo.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-hhrlhf-dpo.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-hhrlhf-dpo.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-hhrlhf-dpo.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-hhrlhf-dpo.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7b-sft-hhrlhf-dpo.IQ4_XS.gguf b/Llama-2-7b-sft-hhrlhf-dpo.IQ4_XS.gguf new file mode 100644 index 0000000..89c23d2 --- /dev/null +++ b/Llama-2-7b-sft-hhrlhf-dpo.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c26cf2f0122b43313d9706e4fc23eac0efcd50bb868f9b95b8be48e3b6674387 +size 3647518272 diff --git a/Llama-2-7b-sft-hhrlhf-dpo.Q2_K.gguf b/Llama-2-7b-sft-hhrlhf-dpo.Q2_K.gguf new file mode 100644 index 0000000..39ec553 --- /dev/null +++ b/Llama-2-7b-sft-hhrlhf-dpo.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d1193c8a0e4d13b7cf0e61380907c18f43c133124124c10a14463dae830a788 +size 2532865600 diff --git a/Llama-2-7b-sft-hhrlhf-dpo.Q3_K_L.gguf b/Llama-2-7b-sft-hhrlhf-dpo.Q3_K_L.gguf new file mode 100644 index 0000000..95ed573 --- /dev/null +++ b/Llama-2-7b-sft-hhrlhf-dpo.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e757c72466e12c7f2a078c366720e6244299ac8e80c07fc08d1d1fe4ede612f +size 3597112896 diff --git a/Llama-2-7b-sft-hhrlhf-dpo.Q3_K_M.gguf b/Llama-2-7b-sft-hhrlhf-dpo.Q3_K_M.gguf new file mode 100644 index 0000000..dc11b58 --- /dev/null +++ b/Llama-2-7b-sft-hhrlhf-dpo.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21dcdda35bdd47ba0b3086c235c7bb5b356979c4213df228900e2f974805fad8 +size 3298006592 diff --git a/Llama-2-7b-sft-hhrlhf-dpo.Q3_K_S.gguf b/Llama-2-7b-sft-hhrlhf-dpo.Q3_K_S.gguf new file mode 100644 index 0000000..fdb6c46 --- /dev/null +++ b/Llama-2-7b-sft-hhrlhf-dpo.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95ad2c7fb9b68447313865b4385b99e25e7202e1532c0ccc39b61139a16127e9 +size 2948306496 diff --git a/Llama-2-7b-sft-hhrlhf-dpo.Q4_K_M.gguf b/Llama-2-7b-sft-hhrlhf-dpo.Q4_K_M.gguf new file mode 100644 index 0000000..ef64c73 --- /dev/null +++ b/Llama-2-7b-sft-hhrlhf-dpo.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d31a532a9da3daf0db005f0064e5cafeac435cc1154a79dc91a8746514b9e45 +size 4081006144 diff --git a/Llama-2-7b-sft-hhrlhf-dpo.Q4_K_S.gguf b/Llama-2-7b-sft-hhrlhf-dpo.Q4_K_S.gguf new file mode 100644 index 0000000..f6642db --- /dev/null +++ b/Llama-2-7b-sft-hhrlhf-dpo.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe80729fd799ef4c05154e9a39be37168fd4ff30ad87b9d3be80cc3af3a68602 +size 3856741952 diff --git a/Llama-2-7b-sft-hhrlhf-dpo.Q5_K_M.gguf b/Llama-2-7b-sft-hhrlhf-dpo.Q5_K_M.gguf new file mode 100644 index 0000000..b54d00a --- /dev/null +++ b/Llama-2-7b-sft-hhrlhf-dpo.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78d5256a4516d034608eb9e8082baae5e1465c0dd3d9e313ae3ec2fdd3d38190 +size 4783158848 diff --git a/Llama-2-7b-sft-hhrlhf-dpo.Q5_K_S.gguf b/Llama-2-7b-sft-hhrlhf-dpo.Q5_K_S.gguf new file mode 100644 index 0000000..c822ce5 --- /dev/null +++ b/Llama-2-7b-sft-hhrlhf-dpo.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58d95e4c76b121164e6599074ebd479f3d28b8542dbf5b55e49803e8e062091f +size 4651693632 diff --git a/Llama-2-7b-sft-hhrlhf-dpo.Q6_K.gguf b/Llama-2-7b-sft-hhrlhf-dpo.Q6_K.gguf new file mode 100644 index 0000000..5c06a19 --- /dev/null +++ b/Llama-2-7b-sft-hhrlhf-dpo.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64d6b6ae49fa1bf6f622d804edc4d70d202926d62c7b8dcdc98debdc3d469d90 +size 5529196096 diff --git a/Llama-2-7b-sft-hhrlhf-dpo.Q8_0.gguf b/Llama-2-7b-sft-hhrlhf-dpo.Q8_0.gguf new file mode 100644 index 0000000..0d426ed --- /dev/null +++ b/Llama-2-7b-sft-hhrlhf-dpo.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3b76816b8bee23361dd0d962e9b7bd4c87c6d8c37a9e1452f86fd9f4401ec44 +size 7161091648 diff --git a/Llama-2-7b-sft-hhrlhf-dpo.f16.gguf b/Llama-2-7b-sft-hhrlhf-dpo.f16.gguf new file mode 100644 index 0000000..5f0e5b0 --- /dev/null +++ b/Llama-2-7b-sft-hhrlhf-dpo.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb7d16e4eb3910a6f36333e118adc8bdc91c3c754319bff286099f0259803477 +size 13478106688 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ef2f095 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: AmberYifan/Llama-2-7b-sft-hhrlhf-dpo +language: +- en +library_name: transformers +model_name: Llama-2-7b-sft-hhrlhf-dpo +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Llama-2-7b-sft-hhrlhf-dpo + + +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-sft-hhrlhf-dpo-GGUF/resolve/main/Llama-2-7b-sft-hhrlhf-dpo.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-hhrlhf-dpo-GGUF/resolve/main/Llama-2-7b-sft-hhrlhf-dpo.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-hhrlhf-dpo-GGUF/resolve/main/Llama-2-7b-sft-hhrlhf-dpo.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-hhrlhf-dpo-GGUF/resolve/main/Llama-2-7b-sft-hhrlhf-dpo.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-hhrlhf-dpo-GGUF/resolve/main/Llama-2-7b-sft-hhrlhf-dpo.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-hhrlhf-dpo-GGUF/resolve/main/Llama-2-7b-sft-hhrlhf-dpo.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-hhrlhf-dpo-GGUF/resolve/main/Llama-2-7b-sft-hhrlhf-dpo.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-hhrlhf-dpo-GGUF/resolve/main/Llama-2-7b-sft-hhrlhf-dpo.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-hhrlhf-dpo-GGUF/resolve/main/Llama-2-7b-sft-hhrlhf-dpo.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-hhrlhf-dpo-GGUF/resolve/main/Llama-2-7b-sft-hhrlhf-dpo.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-hhrlhf-dpo-GGUF/resolve/main/Llama-2-7b-sft-hhrlhf-dpo.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-hhrlhf-dpo-GGUF/resolve/main/Llama-2-7b-sft-hhrlhf-dpo.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. + +