commit 9f3d8eea78cfb9fe705ff7b7038a84d68f8df879 Author: ModelHub XC Date: Tue May 26 13:21:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-sft-dpo-10k-IPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..123f2f7 --- /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-3.1-8B-sft-dpo-10k-IPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-IPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-IPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-IPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-IPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-IPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-IPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-IPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-IPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-IPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-IPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-sft-dpo-10k-IPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-sft-dpo-10k-IPO.IQ4_XS.gguf b/Llama-3.1-8B-sft-dpo-10k-IPO.IQ4_XS.gguf new file mode 100644 index 0000000..5482be4 --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-IPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0bc1e578e38c161933085321c5b96799cd8d001d3547346a46225f58684df29 +size 4484364128 diff --git a/Llama-3.1-8B-sft-dpo-10k-IPO.Q2_K.gguf b/Llama-3.1-8B-sft-dpo-10k-IPO.Q2_K.gguf new file mode 100644 index 0000000..fa5572d --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-IPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbfd043fd37ee61f561a5fc91ad25938e303c83dfd36ba98cc69821dd36bf602 +size 3179132768 diff --git a/Llama-3.1-8B-sft-dpo-10k-IPO.Q3_K_L.gguf b/Llama-3.1-8B-sft-dpo-10k-IPO.Q3_K_L.gguf new file mode 100644 index 0000000..90ba8f2 --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-IPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d93187550d9340c55bfb57b3047dc387db60b5ee68d61cc7e09ebef1bd42efed +size 4321957728 diff --git a/Llama-3.1-8B-sft-dpo-10k-IPO.Q3_K_M.gguf b/Llama-3.1-8B-sft-dpo-10k-IPO.Q3_K_M.gguf new file mode 100644 index 0000000..618a34a --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-IPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6704be845eeea462d7e50d58fc273dd2546e94a7994387883f404beac5bcc9b2 +size 4018919264 diff --git a/Llama-3.1-8B-sft-dpo-10k-IPO.Q3_K_S.gguf b/Llama-3.1-8B-sft-dpo-10k-IPO.Q3_K_S.gguf new file mode 100644 index 0000000..74fadfc --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-IPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b856dbdfc7a6c13c17daa8cb1a126f3138b259e3734dda99259b8fd33405b71 +size 3664500576 diff --git a/Llama-3.1-8B-sft-dpo-10k-IPO.Q4_K_M.gguf b/Llama-3.1-8B-sft-dpo-10k-IPO.Q4_K_M.gguf new file mode 100644 index 0000000..c2ab173 --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-IPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2d102ac2ad1d2149a0b5ea40d6c7f4edf7b766c2a8edc46f5490caaf87b9f0a +size 4920735584 diff --git a/Llama-3.1-8B-sft-dpo-10k-IPO.Q4_K_S.gguf b/Llama-3.1-8B-sft-dpo-10k-IPO.Q4_K_S.gguf new file mode 100644 index 0000000..36edbaa --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-IPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ace48743e9a635d15d621b76c2648bdcb1ab355d4a301e26b168bd07a20532b7 +size 4692670304 diff --git a/Llama-3.1-8B-sft-dpo-10k-IPO.Q5_K_M.gguf b/Llama-3.1-8B-sft-dpo-10k-IPO.Q5_K_M.gguf new file mode 100644 index 0000000..f726265 --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-IPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45b3bad5223ff8609e629db3ed5897cee00edbe0477bb2c8cd50f9193a99fbc1 +size 5732988768 diff --git a/Llama-3.1-8B-sft-dpo-10k-IPO.Q5_K_S.gguf b/Llama-3.1-8B-sft-dpo-10k-IPO.Q5_K_S.gguf new file mode 100644 index 0000000..6c5d471 --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-IPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e792892b68b4d6b2360cea9cdf9c323744564b3f9898dfb63af399c2482d3077 +size 5599295328 diff --git a/Llama-3.1-8B-sft-dpo-10k-IPO.Q6_K.gguf b/Llama-3.1-8B-sft-dpo-10k-IPO.Q6_K.gguf new file mode 100644 index 0000000..18b29b9 --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-IPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e65d162b75cbab653060e05a0e1faa0c9227a4d5a9935d2dfd38ba17fe948b61 +size 6596007776 diff --git a/Llama-3.1-8B-sft-dpo-10k-IPO.Q8_0.gguf b/Llama-3.1-8B-sft-dpo-10k-IPO.Q8_0.gguf new file mode 100644 index 0000000..26c12d9 --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-IPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0925a4629bab615b89aaac8023029103061a979d77813e173e5721f9f1d0db62 +size 8540772192 diff --git a/Llama-3.1-8B-sft-dpo-10k-IPO.f16.gguf b/Llama-3.1-8B-sft-dpo-10k-IPO.f16.gguf new file mode 100644 index 0000000..1f2ce8d --- /dev/null +++ b/Llama-3.1-8B-sft-dpo-10k-IPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d671a35add7c8e5451b49ad2e4ff7a2f86ee81ee74cc0dea654bea0c31d6f33b +size 16068892512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..45bfed3 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: AmberYifan/Llama-3.1-8B-sft-dpo-10k-IPO +language: +- en +library_name: transformers +model_name: Llama-3.1-8B-sft-dpo-10k-IPO +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + + + + +static quants of https://huggingface.co/AmberYifan/Llama-3.1-8B-sft-dpo-10k-IPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-8B-sft-dpo-10k-IPO-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-3.1-8B-sft-dpo-10k-IPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-IPO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-IPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-IPO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-IPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-IPO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-IPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-IPO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-IPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-IPO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-IPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-IPO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-IPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-IPO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-IPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-IPO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-IPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-IPO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-IPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-IPO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-IPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-IPO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-sft-dpo-10k-IPO-GGUF/resolve/main/Llama-3.1-8B-sft-dpo-10k-IPO.f16.gguf) | f16 | 16.2 | 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. + +