commit db4d83b59f5460c1639ede9b261ca0b5993710f8 Author: ModelHub XC Date: Sun Jun 14 05:02:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6c4cb9a --- /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-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..36c2213 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: allenai/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts +datasets: +- allenai/tulu-2.5-preference-data +- allenai/tulu-v2-sft-mixture +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/allenai/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts-i1-GGUF +## 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-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts-GGUF/resolve/main/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts-GGUF/resolve/main/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts-GGUF/resolve/main/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts-GGUF/resolve/main/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts-GGUF/resolve/main/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts-GGUF/resolve/main/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts-GGUF/resolve/main/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts-GGUF/resolve/main/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts-GGUF/resolve/main/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts-GGUF/resolve/main/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts-GGUF/resolve/main/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts-GGUF/resolve/main/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.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/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.IQ4_XS.gguf b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.IQ4_XS.gguf new file mode 100644 index 0000000..4f89902 --- /dev/null +++ b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3055f56ae2e749f6c1da043c0c08bc9130c2f8d9b5e91c01d56cbf12a27a906 +size 4484364032 diff --git a/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q2_K.gguf b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q2_K.gguf new file mode 100644 index 0000000..58d4c8e --- /dev/null +++ b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c23e1db76e6303c5139c1ea86214ac7f91afbba540435e802fd91375f9fa5b90 +size 3179132672 diff --git a/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q3_K_L.gguf b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q3_K_L.gguf new file mode 100644 index 0000000..25c5e45 --- /dev/null +++ b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb4448ddf364d6f801f4b7012062f51809eddf0bd8fbf53300f8f4b1dfed17fb +size 4321957632 diff --git a/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q3_K_M.gguf b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q3_K_M.gguf new file mode 100644 index 0000000..7c09897 --- /dev/null +++ b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acf23213e125b5d3ceb52f52a8fb8a3164168916613fcf11c54a970ea5fa49b0 +size 4018919168 diff --git a/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q3_K_S.gguf b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q3_K_S.gguf new file mode 100644 index 0000000..3533587 --- /dev/null +++ b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fcde817ce6c750cb9ffa57d5b270b9a3c41a0ebf5ce109e95be35e8977ffa49 +size 3664500480 diff --git a/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q4_K_M.gguf b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q4_K_M.gguf new file mode 100644 index 0000000..06f2af5 --- /dev/null +++ b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db383aa5aee2b9f9a3d2e6837687332504af79ba1d11b26b929739ff37c4dae4 +size 4920735488 diff --git a/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q4_K_S.gguf b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q4_K_S.gguf new file mode 100644 index 0000000..79f6f06 --- /dev/null +++ b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7cecf35cb262a125044e862daab41d5902e23ac1879beb9054221e80087c081 +size 4692670208 diff --git a/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q5_K_M.gguf b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q5_K_M.gguf new file mode 100644 index 0000000..ac8d45c --- /dev/null +++ b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa28294724d139cf4091d8626151cb17a380f45e0fabf8ca5976e201ec241e8b +size 5732988672 diff --git a/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q5_K_S.gguf b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q5_K_S.gguf new file mode 100644 index 0000000..8e83ac4 --- /dev/null +++ b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83e022ec893cca6257b3c6193bd2371eef25f9ffc4c29b9ba7a7327fea888750 +size 5599295232 diff --git a/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q6_K.gguf b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q6_K.gguf new file mode 100644 index 0000000..1ca9662 --- /dev/null +++ b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27fe7591fd7084cf3cb2eae13864cc719f1352644e88bcb47e82a4eb03a122c6 +size 6596007680 diff --git a/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q8_0.gguf b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q8_0.gguf new file mode 100644 index 0000000..fe86ae1 --- /dev/null +++ b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f13d1f6dbcb1bbd206dff79d4a69415182b1432b2d3b7dc217246ec97a7cadff +size 8540772096 diff --git a/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.f16.gguf b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.f16.gguf new file mode 100644 index 0000000..8e60cbe --- /dev/null +++ b/llama-3-tulu-v2.5-8b-uf-mean-70b-uf-rm-mixed-prompts.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69a92e9e0c8a714d29593f1e5804a75901d22189ef2ba389bbe08b9a6e438929 +size 16068892416