commit b1d1ae78af7275a17ac7cce1f4a5c42c735aeb11 Author: ModelHub XC Date: Tue Aug 4 15:43:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Instruct-UltraDPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e719466 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-3-8B-Instruct-UltraDPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-UltraDPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Instruct-UltraDPO.IQ3_M.gguf b/Llama-3-8B-Instruct-UltraDPO.IQ3_M.gguf new file mode 100644 index 0000000..a945272 --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:962d79752fd969c076fa9f834abb5e4b38a6077609aac34a0cea8d479d7103c0 +size 3784823584 diff --git a/Llama-3-8B-Instruct-UltraDPO.IQ3_S.gguf b/Llama-3-8B-Instruct-UltraDPO.IQ3_S.gguf new file mode 100644 index 0000000..a7c8e26 --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:529528db59d2fa9a5045729ed81e331dbbab2c3cb575c89c43278262895122c9 +size 3682325280 diff --git a/Llama-3-8B-Instruct-UltraDPO.IQ3_XS.gguf b/Llama-3-8B-Instruct-UltraDPO.IQ3_XS.gguf new file mode 100644 index 0000000..525b956 --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e42996d6d89eeaa89134f93477644c977832a8aa627c1b6ab6339b98f6716fe +size 3518747424 diff --git a/Llama-3-8B-Instruct-UltraDPO.IQ4_XS.gguf b/Llama-3-8B-Instruct-UltraDPO.IQ4_XS.gguf new file mode 100644 index 0000000..6ad40b4 --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a59a5fd24102b2d4a3d2905692d768ab3e2cb3bce7ff29f19743352f4cc464c2 +size 4484363040 diff --git a/Llama-3-8B-Instruct-UltraDPO.Q2_K.gguf b/Llama-3-8B-Instruct-UltraDPO.Q2_K.gguf new file mode 100644 index 0000000..1af4070 --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:342f3ba1ea420c1d22594b51b0d37be61b6a90124f53a827f0db8214478e3641 +size 3179131680 diff --git a/Llama-3-8B-Instruct-UltraDPO.Q3_K_L.gguf b/Llama-3-8B-Instruct-UltraDPO.Q3_K_L.gguf new file mode 100644 index 0000000..4c53a0c --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1f5632eafc8e4f4e278dc6036e159fc3f96a17f3baba09f7e37cb053fb3d140 +size 4321956640 diff --git a/Llama-3-8B-Instruct-UltraDPO.Q3_K_M.gguf b/Llama-3-8B-Instruct-UltraDPO.Q3_K_M.gguf new file mode 100644 index 0000000..0a48fb3 --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a149775335941c587255bb020b5570cc2766a4305e447f307477c36e3132c20a +size 4018918176 diff --git a/Llama-3-8B-Instruct-UltraDPO.Q3_K_S.gguf b/Llama-3-8B-Instruct-UltraDPO.Q3_K_S.gguf new file mode 100644 index 0000000..d5382e5 --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8661e4d99905b38cd518d996591d0346ce6bd1e7343cca22a197d65df97de02a +size 3664499488 diff --git a/Llama-3-8B-Instruct-UltraDPO.Q4_K_M.gguf b/Llama-3-8B-Instruct-UltraDPO.Q4_K_M.gguf new file mode 100644 index 0000000..7069e27 --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d15eeda6c3d4c01d9e39f7e48077895b619eb59aac72317e8b2706aba3f9927 +size 4920734496 diff --git a/Llama-3-8B-Instruct-UltraDPO.Q4_K_S.gguf b/Llama-3-8B-Instruct-UltraDPO.Q4_K_S.gguf new file mode 100644 index 0000000..475d35b --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eabaf9b89a75268fbfcf60c53cd193b2555f51148bf5d26b4b064426c9ba799 +size 4692669216 diff --git a/Llama-3-8B-Instruct-UltraDPO.Q5_K_M.gguf b/Llama-3-8B-Instruct-UltraDPO.Q5_K_M.gguf new file mode 100644 index 0000000..b0fa0ab --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66cc42d06ba2f97e1dc731a4cd525de2598dfeee22e1c852b20f5584cf2748dc +size 5732987680 diff --git a/Llama-3-8B-Instruct-UltraDPO.Q5_K_S.gguf b/Llama-3-8B-Instruct-UltraDPO.Q5_K_S.gguf new file mode 100644 index 0000000..0ff6eab --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b4d24934ca4dd6a2fc923798535250a84988f19618fd97ae636a8453d249ed0 +size 5599294240 diff --git a/Llama-3-8B-Instruct-UltraDPO.Q6_K.gguf b/Llama-3-8B-Instruct-UltraDPO.Q6_K.gguf new file mode 100644 index 0000000..d238ecb --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96960379a3c2512a86c1ff196e473fc87a15803ea3660e4f6b200c709c9c05d5 +size 6596006688 diff --git a/Llama-3-8B-Instruct-UltraDPO.Q8_0.gguf b/Llama-3-8B-Instruct-UltraDPO.Q8_0.gguf new file mode 100644 index 0000000..5150699 --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ce0366d740ce4de8fe95ed56815cb08352407c28796767fe9cc267e5d65ccc9 +size 8540771104 diff --git a/Llama-3-8B-Instruct-UltraDPO.f16.gguf b/Llama-3-8B-Instruct-UltraDPO.f16.gguf new file mode 100644 index 0000000..fe22de3 --- /dev/null +++ b/Llama-3-8B-Instruct-UltraDPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07a6b2942ca85462ad36f3dca9e4712a22ad2f2e205d276197051dd5fe07d672 +size 16068891424 diff --git a/README.md b/README.md new file mode 100644 index 0000000..743f993 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Magpie-Align/Llama-3-8B-Instruct-UltraDPO +datasets: +- HuggingFaceH4/ultrafeedback_binarized +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- alignment-handbook +- trl +- dpo +- generated_from_trainer +- trl +- dpo +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/Magpie-Align/Llama-3-8B-Instruct-UltraDPO + + +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-3-8B-Instruct-UltraDPO-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-UltraDPO-GGUF/resolve/main/Llama-3-8B-Instruct-UltraDPO.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. + +