commit e2a6daa9fa9e78b8bd28fa22fd54e8f5d1ffdfca Author: ModelHub XC Date: Sun Oct 4 05:25:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-2-7b-sft-dpo-10k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f6210ee --- /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-10k.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-dpo-10k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-dpo-10k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-dpo-10k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-dpo-10k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-dpo-10k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-dpo-10k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-dpo-10k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-dpo-10k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-dpo-10k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-dpo-10k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sft-dpo-10k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7b-sft-dpo-10k.IQ4_XS.gguf b/Llama-2-7b-sft-dpo-10k.IQ4_XS.gguf new file mode 100644 index 0000000..216393d --- /dev/null +++ b/Llama-2-7b-sft-dpo-10k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9802a54120ddb0f67707db6db970dc1ff47e8c95194fbf04fb168c0fb08cdfa +size 3647518272 diff --git a/Llama-2-7b-sft-dpo-10k.Q2_K.gguf b/Llama-2-7b-sft-dpo-10k.Q2_K.gguf new file mode 100644 index 0000000..a85e3f0 --- /dev/null +++ b/Llama-2-7b-sft-dpo-10k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c0ed98b180f333bdc3838824af52951cfbcafe69bd79cef06937d88ecc1086e +size 2532865600 diff --git a/Llama-2-7b-sft-dpo-10k.Q3_K_L.gguf b/Llama-2-7b-sft-dpo-10k.Q3_K_L.gguf new file mode 100644 index 0000000..82cdca1 --- /dev/null +++ b/Llama-2-7b-sft-dpo-10k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50f78d6e8eb6446fdb57637a3f27ba6aa1393585139ccdbac8c9d73b44725d8f +size 3597112896 diff --git a/Llama-2-7b-sft-dpo-10k.Q3_K_M.gguf b/Llama-2-7b-sft-dpo-10k.Q3_K_M.gguf new file mode 100644 index 0000000..5cafc0a --- /dev/null +++ b/Llama-2-7b-sft-dpo-10k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1108e1c4607e7e24278e77192acb6a75fdc5d35e70b721fc06ebf67562295c +size 3298006592 diff --git a/Llama-2-7b-sft-dpo-10k.Q3_K_S.gguf b/Llama-2-7b-sft-dpo-10k.Q3_K_S.gguf new file mode 100644 index 0000000..0ac8afa --- /dev/null +++ b/Llama-2-7b-sft-dpo-10k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f50e427cfec4249fb51446d614ebefa635f8fa4115b9d6bbfb03a4b00e1a735 +size 2948306496 diff --git a/Llama-2-7b-sft-dpo-10k.Q4_K_M.gguf b/Llama-2-7b-sft-dpo-10k.Q4_K_M.gguf new file mode 100644 index 0000000..5b6a12c --- /dev/null +++ b/Llama-2-7b-sft-dpo-10k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8bfc60dda93bdfa05c75742becd264db6dc091c04d26aa41802a081ed0a0c69 +size 4081006144 diff --git a/Llama-2-7b-sft-dpo-10k.Q4_K_S.gguf b/Llama-2-7b-sft-dpo-10k.Q4_K_S.gguf new file mode 100644 index 0000000..dfaf6ef --- /dev/null +++ b/Llama-2-7b-sft-dpo-10k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:706be9ce665a60941aa60a3620c2d7848092b16aa17bc29208bb73d0a956d29c +size 3856741952 diff --git a/Llama-2-7b-sft-dpo-10k.Q5_K_M.gguf b/Llama-2-7b-sft-dpo-10k.Q5_K_M.gguf new file mode 100644 index 0000000..52a5078 --- /dev/null +++ b/Llama-2-7b-sft-dpo-10k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:962697a06caae6ae525ac38026b71c1988159b56c43ead363b3a37f638798a2b +size 4783158848 diff --git a/Llama-2-7b-sft-dpo-10k.Q5_K_S.gguf b/Llama-2-7b-sft-dpo-10k.Q5_K_S.gguf new file mode 100644 index 0000000..a1b436a --- /dev/null +++ b/Llama-2-7b-sft-dpo-10k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c038ea22b5e55e7d859482b31f2839788f4e02d56dbdb378a07d418e826d5ffb +size 4651693632 diff --git a/Llama-2-7b-sft-dpo-10k.Q6_K.gguf b/Llama-2-7b-sft-dpo-10k.Q6_K.gguf new file mode 100644 index 0000000..96d0172 --- /dev/null +++ b/Llama-2-7b-sft-dpo-10k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b7213c6638f048172590edb5db060e331629ddfc15d5b02e7850b68503df96a +size 5529196096 diff --git a/Llama-2-7b-sft-dpo-10k.Q8_0.gguf b/Llama-2-7b-sft-dpo-10k.Q8_0.gguf new file mode 100644 index 0000000..a8a1f87 --- /dev/null +++ b/Llama-2-7b-sft-dpo-10k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68ae7cfc29a78f8e6fcc8a828398f8e42f77113b1b90300c4e65901fa0e6c63a +size 7161091648 diff --git a/Llama-2-7b-sft-dpo-10k.f16.gguf b/Llama-2-7b-sft-dpo-10k.f16.gguf new file mode 100644 index 0000000..55335d6 --- /dev/null +++ b/Llama-2-7b-sft-dpo-10k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9067dcf3e87343c8771202e0e6af12127c6d88e540576b919c0a192a39b61fbd +size 13478106688 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d8f2df8 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: AmberYifan/Llama-2-7b-sft-dpo-10k +language: +- en +library_name: transformers +model_name: Llama-2-7b-sft-dpo-10k +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-10k + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-2-7b-sft-dpo-10k-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-10k-GGUF/resolve/main/Llama-2-7b-sft-dpo-10k.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-dpo-10k-GGUF/resolve/main/Llama-2-7b-sft-dpo-10k.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-dpo-10k-GGUF/resolve/main/Llama-2-7b-sft-dpo-10k.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-dpo-10k-GGUF/resolve/main/Llama-2-7b-sft-dpo-10k.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-dpo-10k-GGUF/resolve/main/Llama-2-7b-sft-dpo-10k.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-dpo-10k-GGUF/resolve/main/Llama-2-7b-sft-dpo-10k.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-dpo-10k-GGUF/resolve/main/Llama-2-7b-sft-dpo-10k.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-dpo-10k-GGUF/resolve/main/Llama-2-7b-sft-dpo-10k.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-dpo-10k-GGUF/resolve/main/Llama-2-7b-sft-dpo-10k.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-dpo-10k-GGUF/resolve/main/Llama-2-7b-sft-dpo-10k.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-dpo-10k-GGUF/resolve/main/Llama-2-7b-sft-dpo-10k.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sft-dpo-10k-GGUF/resolve/main/Llama-2-7b-sft-dpo-10k.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. + +