commit 6d2c2a0bb097fbe117ece73dbfd9abf3729a7c6f Author: ModelHub XC Date: Thu Jun 18 07:02:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d3c3432 --- /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-sft-wo-kqa_silver_wogold.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2e24652 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Minbyul/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold +datasets: +- HuggingFaceH4/ultrafeedback_binarized +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +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-sft-wo-kqa_silver_wogold + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama2-7b-dpo-full-sft-wo-kqa_silver_wogold-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/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold-GGUF/resolve/main/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold-GGUF/resolve/main/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold-GGUF/resolve/main/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold-GGUF/resolve/main/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold-GGUF/resolve/main/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold-GGUF/resolve/main/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold-GGUF/resolve/main/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold-GGUF/resolve/main/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold-GGUF/resolve/main/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold-GGUF/resolve/main/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold-GGUF/resolve/main/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold-GGUF/resolve/main/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.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. + + diff --git a/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.IQ4_XS.gguf b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.IQ4_XS.gguf new file mode 100644 index 0000000..67daa80 --- /dev/null +++ b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bf656ef0c6e72f8316934b5e8c0acd4d08b14f9425fc6dc3a7313c258e85081 +size 3647518080 diff --git a/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q2_K.gguf b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q2_K.gguf new file mode 100644 index 0000000..d541fcc --- /dev/null +++ b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb4ad07278f6fe5b36961b9b2772afaa437985c978f62851d3755e1bc6385c88 +size 2532865408 diff --git a/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q3_K_L.gguf b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q3_K_L.gguf new file mode 100644 index 0000000..278f51f --- /dev/null +++ b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3ad94c60f172bfe11b0b6846c8962dae21580f20d25a1bfa20090b9d9835d19 +size 3597112704 diff --git a/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q3_K_M.gguf b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q3_K_M.gguf new file mode 100644 index 0000000..78c81f9 --- /dev/null +++ b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2531f3bf31545a315d407adf196dc84172db9b68c7ebeecfc1058155cdd1987b +size 3298006400 diff --git a/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q3_K_S.gguf b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q3_K_S.gguf new file mode 100644 index 0000000..2cd115a --- /dev/null +++ b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f71c530f7bf405a03974bb6dbbbc995fb9d405dd20a570af8dbbf525c8da07a +size 2948306304 diff --git a/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q4_K_M.gguf b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q4_K_M.gguf new file mode 100644 index 0000000..f0847a5 --- /dev/null +++ b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3780769127ac2d4fe7ecf048558555153be62880f7120ba0ae88f554cbcd3f9 +size 4081005952 diff --git a/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q4_K_S.gguf b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q4_K_S.gguf new file mode 100644 index 0000000..838f715 --- /dev/null +++ b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:279c13ba9bf1147ca0cb6204b09bcb6c346f1b9ce8aa0d977ccd245d8819d866 +size 3856741760 diff --git a/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q5_K_M.gguf b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q5_K_M.gguf new file mode 100644 index 0000000..c637b76 --- /dev/null +++ b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d77e7eac18e354dc4b73c9f4d4df5a6f29e7c4ad29b42a8e2af6f51a8ce003bd +size 4783158656 diff --git a/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q5_K_S.gguf b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q5_K_S.gguf new file mode 100644 index 0000000..097093b --- /dev/null +++ b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eca077bbfdb821a360cc383df4fb5107c4bd8e2b860917a41fb0411077ac1088 +size 4651693440 diff --git a/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q6_K.gguf b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q6_K.gguf new file mode 100644 index 0000000..122ebfd --- /dev/null +++ b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41ba96c5390e49da08ae66442200944d659af9a91548871bcd17c504900da4d7 +size 5529195904 diff --git a/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q8_0.gguf b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q8_0.gguf new file mode 100644 index 0000000..2960f3c --- /dev/null +++ b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:965c15f0b24638a52bcf6020c338df9d5c7ab2186832eb8beb62bc88384aaf7c +size 7161091456 diff --git a/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.f16.gguf b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.f16.gguf new file mode 100644 index 0000000..aae484f --- /dev/null +++ b/llama2-7b-dpo-full-sft-wo-kqa_silver_wogold.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a8e2e327b422f5c9eb01456651141f29793f7c7ed51a5acc6d5beae9af42c91 +size 13478106496