commit 5a78c1928fd98c8cb41d9205d8384c64992c8d80 Author: ModelHub XC Date: Sun Jun 14 01:32:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/RoLlama3-8b-Instruct-DPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..67814fa --- /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 +RoLlama3-8b-Instruct-DPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3-8b-Instruct-DPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3-8b-Instruct-DPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3-8b-Instruct-DPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3-8b-Instruct-DPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3-8b-Instruct-DPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3-8b-Instruct-DPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3-8b-Instruct-DPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3-8b-Instruct-DPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3-8b-Instruct-DPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3-8b-Instruct-DPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3-8b-Instruct-DPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f195280 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: OpenLLM-Ro/RoLlama3-8b-Instruct-DPO +datasets: +- OpenLLM-Ro/ro_dpo_helpsteer +- OpenLLM-Ro/ro_dpo_ultrafeedback +- OpenLLM-Ro/ro_dpo_magpie +- OpenLLM-Ro/ro_dpo_argilla_magpie +- OpenLLM-Ro/ro_dpo_helpsteer2 +language: +- ro +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-Instruct-DPO + + +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/RoLlama3-8b-Instruct-DPO-GGUF/resolve/main/RoLlama3-8b-Instruct-DPO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3-8b-Instruct-DPO-GGUF/resolve/main/RoLlama3-8b-Instruct-DPO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3-8b-Instruct-DPO-GGUF/resolve/main/RoLlama3-8b-Instruct-DPO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3-8b-Instruct-DPO-GGUF/resolve/main/RoLlama3-8b-Instruct-DPO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3-8b-Instruct-DPO-GGUF/resolve/main/RoLlama3-8b-Instruct-DPO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3-8b-Instruct-DPO-GGUF/resolve/main/RoLlama3-8b-Instruct-DPO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3-8b-Instruct-DPO-GGUF/resolve/main/RoLlama3-8b-Instruct-DPO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3-8b-Instruct-DPO-GGUF/resolve/main/RoLlama3-8b-Instruct-DPO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3-8b-Instruct-DPO-GGUF/resolve/main/RoLlama3-8b-Instruct-DPO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3-8b-Instruct-DPO-GGUF/resolve/main/RoLlama3-8b-Instruct-DPO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3-8b-Instruct-DPO-GGUF/resolve/main/RoLlama3-8b-Instruct-DPO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3-8b-Instruct-DPO-GGUF/resolve/main/RoLlama3-8b-Instruct-DPO.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. + + diff --git a/RoLlama3-8b-Instruct-DPO.IQ4_XS.gguf b/RoLlama3-8b-Instruct-DPO.IQ4_XS.gguf new file mode 100644 index 0000000..90a71a2 --- /dev/null +++ b/RoLlama3-8b-Instruct-DPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8bc381cf1168b9decdc90d41a1982e19c21aed0daa42120cad2cae7187f360e +size 4484364288 diff --git a/RoLlama3-8b-Instruct-DPO.Q2_K.gguf b/RoLlama3-8b-Instruct-DPO.Q2_K.gguf new file mode 100644 index 0000000..ec8448a --- /dev/null +++ b/RoLlama3-8b-Instruct-DPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb44f2d4503316d75fba0c4fde73715b4020be36a365bcd4e7f084bbcc6b2c29 +size 3179132928 diff --git a/RoLlama3-8b-Instruct-DPO.Q3_K_L.gguf b/RoLlama3-8b-Instruct-DPO.Q3_K_L.gguf new file mode 100644 index 0000000..5627ea4 --- /dev/null +++ b/RoLlama3-8b-Instruct-DPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0703bef74a5f6c99b1dc86022782a287d03263a296733eb4bcfcfeaecf3098e3 +size 4321957888 diff --git a/RoLlama3-8b-Instruct-DPO.Q3_K_M.gguf b/RoLlama3-8b-Instruct-DPO.Q3_K_M.gguf new file mode 100644 index 0000000..9543456 --- /dev/null +++ b/RoLlama3-8b-Instruct-DPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80d2afff51b6c2af0e03445f7a35b947f04b63c1a99f59efa3efd72ca568b14e +size 4018919424 diff --git a/RoLlama3-8b-Instruct-DPO.Q3_K_S.gguf b/RoLlama3-8b-Instruct-DPO.Q3_K_S.gguf new file mode 100644 index 0000000..2008df3 --- /dev/null +++ b/RoLlama3-8b-Instruct-DPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa46183114c5214c20ae5a4f4a5755cb3267ce2e1ebbc3d202a5b072cb57990a +size 3664500736 diff --git a/RoLlama3-8b-Instruct-DPO.Q4_K_M.gguf b/RoLlama3-8b-Instruct-DPO.Q4_K_M.gguf new file mode 100644 index 0000000..781f731 --- /dev/null +++ b/RoLlama3-8b-Instruct-DPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef382744590eaae3fcd03ab9eeca722b71ec572553eae6a2fd0a0dfc8d4cb2b6 +size 4920735744 diff --git a/RoLlama3-8b-Instruct-DPO.Q4_K_S.gguf b/RoLlama3-8b-Instruct-DPO.Q4_K_S.gguf new file mode 100644 index 0000000..e395ddf --- /dev/null +++ b/RoLlama3-8b-Instruct-DPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39d454564b5474c0a26f74d0d60b1781897a973811e51846c3d6957cf4354adf +size 4692670464 diff --git a/RoLlama3-8b-Instruct-DPO.Q5_K_M.gguf b/RoLlama3-8b-Instruct-DPO.Q5_K_M.gguf new file mode 100644 index 0000000..43cda38 --- /dev/null +++ b/RoLlama3-8b-Instruct-DPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57a0b101d9c4e2f52cb7fdf6cc85d788114d0edb164d0ce3652d0389fc9a8b9f +size 5732988928 diff --git a/RoLlama3-8b-Instruct-DPO.Q5_K_S.gguf b/RoLlama3-8b-Instruct-DPO.Q5_K_S.gguf new file mode 100644 index 0000000..c0a8c13 --- /dev/null +++ b/RoLlama3-8b-Instruct-DPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6863dbca802eb4fe83a406cd033f34bf3fa0b0cdbb10c44bfbe3273218b1223 +size 5599295488 diff --git a/RoLlama3-8b-Instruct-DPO.Q6_K.gguf b/RoLlama3-8b-Instruct-DPO.Q6_K.gguf new file mode 100644 index 0000000..da3a7d7 --- /dev/null +++ b/RoLlama3-8b-Instruct-DPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78c495fc82b9cdab08cb2e450867e17dab0cd9b738f15cb73bba55e4c6805660 +size 6596007936 diff --git a/RoLlama3-8b-Instruct-DPO.Q8_0.gguf b/RoLlama3-8b-Instruct-DPO.Q8_0.gguf new file mode 100644 index 0000000..3fa49d1 --- /dev/null +++ b/RoLlama3-8b-Instruct-DPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7448ce191fb962b1ada787c48ec6e348c0c92dcbd6494d23f41f83f553426e7e +size 8540772352 diff --git a/RoLlama3-8b-Instruct-DPO.f16.gguf b/RoLlama3-8b-Instruct-DPO.f16.gguf new file mode 100644 index 0000000..9ee6c39 --- /dev/null +++ b/RoLlama3-8b-Instruct-DPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfc5e0a7e45510a65fdeef1224fe518ca120ab76015edda0308803119fba2218 +size 16068892672