commit a56b16a2d848deaa1b63fed28baa0d97d1dd060e Author: ModelHub XC Date: Wed Sep 23 17:16:26 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-2-7b-sft-DPO-2k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..25860c7 --- /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-sft-DPO-2k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-DPO-2k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-DPO-2k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-DPO-2k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-DPO-2k.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-DPO-2k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-DPO-2k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-DPO-2k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-DPO-2k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-DPO-2k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-DPO-2k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-DPO-2k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7b-sft-DPO-2k.IQ4_XS.gguf b/Llama-2-7b-sft-DPO-2k.IQ4_XS.gguf new file mode 100644 index 0000000..6e3a019 --- /dev/null +++ b/Llama-2-7b-sft-DPO-2k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9894872d17735010b31b4954fb704736b05d723073e16094c7d7b84da6a2f800 +size 3647518272 diff --git a/Llama-2-7b-sft-DPO-2k.Q2_K.gguf b/Llama-2-7b-sft-DPO-2k.Q2_K.gguf new file mode 100644 index 0000000..008640c --- /dev/null +++ b/Llama-2-7b-sft-DPO-2k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8d11fbd798035d82e3d5ea46dfba45c7f0fd6bbf4747258765d9cf2063e678e +size 2532865600 diff --git a/Llama-2-7b-sft-DPO-2k.Q3_K_L.gguf b/Llama-2-7b-sft-DPO-2k.Q3_K_L.gguf new file mode 100644 index 0000000..afaf4e3 --- /dev/null +++ b/Llama-2-7b-sft-DPO-2k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aea899e14c52a9c6267386989a2f1c0f188b5b366f66da0801f3b818d1eab71 +size 3597112896 diff --git a/Llama-2-7b-sft-DPO-2k.Q3_K_M.gguf b/Llama-2-7b-sft-DPO-2k.Q3_K_M.gguf new file mode 100644 index 0000000..faed099 --- /dev/null +++ b/Llama-2-7b-sft-DPO-2k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01e22aa9a2ee7044ce45cf76bd054e8132cb9cbb5a1881fa9f88d7801bd66dde +size 3298006592 diff --git a/Llama-2-7b-sft-DPO-2k.Q3_K_S.gguf b/Llama-2-7b-sft-DPO-2k.Q3_K_S.gguf new file mode 100644 index 0000000..e1dedee --- /dev/null +++ b/Llama-2-7b-sft-DPO-2k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64e5b909598e8031830a5540b437854504fd810cf398935eb4b24c724ef2492e +size 2948306496 diff --git a/Llama-2-7b-sft-DPO-2k.Q4_K_M.gguf b/Llama-2-7b-sft-DPO-2k.Q4_K_M.gguf new file mode 100644 index 0000000..5b6ea74 --- /dev/null +++ b/Llama-2-7b-sft-DPO-2k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdbd884a955c3f62ffed2f05df697f4e608d13f490d67898e6aed817d9909aad +size 4081006144 diff --git a/Llama-2-7b-sft-DPO-2k.Q4_K_S.gguf b/Llama-2-7b-sft-DPO-2k.Q4_K_S.gguf new file mode 100644 index 0000000..d12d780 --- /dev/null +++ b/Llama-2-7b-sft-DPO-2k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69382ae37c82750e5fe66ab4e4cfb20abbd0dbd0e6c8264aa5e7d5606a881cba +size 3856741952 diff --git a/Llama-2-7b-sft-DPO-2k.Q5_K_M.gguf b/Llama-2-7b-sft-DPO-2k.Q5_K_M.gguf new file mode 100644 index 0000000..614759b --- /dev/null +++ b/Llama-2-7b-sft-DPO-2k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cc9961cd94c9ef92062cf525cf7320915647757524eab3143ff6a4e2182c3f5 +size 4783158848 diff --git a/Llama-2-7b-sft-DPO-2k.Q5_K_S.gguf b/Llama-2-7b-sft-DPO-2k.Q5_K_S.gguf new file mode 100644 index 0000000..f0e8496 --- /dev/null +++ b/Llama-2-7b-sft-DPO-2k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd024b0b92f7e55959771e32096d5e6efc2d30fdf5b44dc429d0831ded45436b +size 4651693632 diff --git a/Llama-2-7b-sft-DPO-2k.Q6_K.gguf b/Llama-2-7b-sft-DPO-2k.Q6_K.gguf new file mode 100644 index 0000000..305a4db --- /dev/null +++ b/Llama-2-7b-sft-DPO-2k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb48c8fd18b66eb8b2a65191b589c57e6396a37ea4da88e802b167ea2098846a +size 5529196096 diff --git a/Llama-2-7b-sft-DPO-2k.Q8_0.gguf b/Llama-2-7b-sft-DPO-2k.Q8_0.gguf new file mode 100644 index 0000000..ca609ca --- /dev/null +++ b/Llama-2-7b-sft-DPO-2k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a130dc4a8be98f3f32f6010462bc159fe9d99071233a14e8abdf4b90c06d22f +size 7161091648 diff --git a/Llama-2-7b-sft-DPO-2k.f16.gguf b/Llama-2-7b-sft-DPO-2k.f16.gguf new file mode 100644 index 0000000..9663ed6 --- /dev/null +++ b/Llama-2-7b-sft-DPO-2k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a33ad5611d233ce20871a7833c73401d51e335062a4d4b90eb37f8f573846435 +size 13478106688 diff --git a/README.md b/README.md new file mode 100644 index 0000000..56352e6 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: AmberYifan/Llama-2-7b-sft-DPO-2k +language: +- en +library_name: transformers +model_name: Llama-2-7b-sft-DPO-2k +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Llama-2-7b-sft-DPO-2k + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-2-7b-sft-DPO-2k-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/Llama-2-7b-sft-DPO-2k-GGUF/resolve/main/Llama-2-7b-sft-DPO-2k.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-DPO-2k-GGUF/resolve/main/Llama-2-7b-sft-DPO-2k.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-DPO-2k-GGUF/resolve/main/Llama-2-7b-sft-DPO-2k.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-DPO-2k-GGUF/resolve/main/Llama-2-7b-sft-DPO-2k.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-DPO-2k-GGUF/resolve/main/Llama-2-7b-sft-DPO-2k.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-DPO-2k-GGUF/resolve/main/Llama-2-7b-sft-DPO-2k.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-DPO-2k-GGUF/resolve/main/Llama-2-7b-sft-DPO-2k.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-DPO-2k-GGUF/resolve/main/Llama-2-7b-sft-DPO-2k.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-DPO-2k-GGUF/resolve/main/Llama-2-7b-sft-DPO-2k.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-DPO-2k-GGUF/resolve/main/Llama-2-7b-sft-DPO-2k.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-DPO-2k-GGUF/resolve/main/Llama-2-7b-sft-DPO-2k.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-DPO-2k-GGUF/resolve/main/Llama-2-7b-sft-DPO-2k.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. + +