commit 8f19e36c432fdd2c3c66bfc61206f14188f85f32 Author: ModelHub XC Date: Fri May 8 10:58:08 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c74ba27 --- /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-dpo-full-wo-kqa_silver_wogold-ep3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..892e025 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: Minbyul/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3 +datasets: +- HuggingFaceH4/ultrafeedback_binarized +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- alignment-handbook +- trl +- dpo +- generated_from_trainer +- trl +- dpo +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/Minbyul/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3 + + +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-dpo-full-wo-kqa_silver_wogold-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.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-dpo-full-wo-kqa_silver_wogold-ep3.IQ4_XS.gguf b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.IQ4_XS.gguf new file mode 100644 index 0000000..df32027 --- /dev/null +++ b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87619eca88224eba1c38ed29416dacf177ea6c6b5b9c61e9bd0d473c6cdfe9bb +size 3647518016 diff --git a/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q2_K.gguf b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q2_K.gguf new file mode 100644 index 0000000..77805a1 --- /dev/null +++ b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37261daefac11eebba8bc37ed87903299e66fd7a2c34ff0941c658b20ed4b3e9 +size 2532865344 diff --git a/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q3_K_L.gguf b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q3_K_L.gguf new file mode 100644 index 0000000..dc61d2a --- /dev/null +++ b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:731e194a09c2bb70f51259317f472fdfc71c36281da786208fcb926fc4d09ee4 +size 3597112640 diff --git a/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q3_K_M.gguf b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q3_K_M.gguf new file mode 100644 index 0000000..d7f2765 --- /dev/null +++ b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa5009411fa5950dc7598b76c7cada23b9ea73df9431a5f2583f457855b57ba6 +size 3298006336 diff --git a/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q3_K_S.gguf b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q3_K_S.gguf new file mode 100644 index 0000000..5862333 --- /dev/null +++ b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1869acf4fcaa47a659d113b50dc72522dbf8ddf37a55adb2a2c3b11260fd5c9 +size 2948306240 diff --git a/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q4_K_M.gguf b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q4_K_M.gguf new file mode 100644 index 0000000..1783ce8 --- /dev/null +++ b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf3afb5694456e5b6aac89a96adc9dc8fbdb9be72ed30fd61aa4d630d6a9b31 +size 4081005888 diff --git a/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q4_K_S.gguf b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q4_K_S.gguf new file mode 100644 index 0000000..b00dbdd --- /dev/null +++ b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18d0aeba4eafaa94753de91ef8f7cba8b9c84f4b30b6a12b4ae5a5612e007187 +size 3856741696 diff --git a/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q5_K_M.gguf b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q5_K_M.gguf new file mode 100644 index 0000000..4491932 --- /dev/null +++ b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e0cf65d08081b79ae0cc28b19059f10031294e0574286210479f2ee665eaf01 +size 4783158592 diff --git a/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q5_K_S.gguf b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q5_K_S.gguf new file mode 100644 index 0000000..9c97a61 --- /dev/null +++ b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4f6ec0f8648e928c89302b710c874ccd72104addd8189b5f6cc20c075d4ff84 +size 4651693376 diff --git a/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q6_K.gguf b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q6_K.gguf new file mode 100644 index 0000000..dff3bd3 --- /dev/null +++ b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dc58d27f49704c0c5e6346261f99510d92de7eb884d6aad01dc1bd9fac2a644 +size 5529195840 diff --git a/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q8_0.gguf b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q8_0.gguf new file mode 100644 index 0000000..629601c --- /dev/null +++ b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d78a465702456693dbf2a42ab4dace08fcb68d15db5c10056557b565030c5f1c +size 7161091392 diff --git a/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.f16.gguf b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.f16.gguf new file mode 100644 index 0000000..dee2281 --- /dev/null +++ b/llama2-7b-dpo-full-wo-kqa_silver_wogold-ep3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0cc303273797daddb8a6e3ff39adad7374a31561d68c18f24c6c663dd626fef +size 13478106432