commit 85e37ba4b26ceb65a40edc1e6232369984bbfac2 Author: ModelHub XC Date: Thu Jun 18 06:14:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.1-tulu-2-dpo-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6b5ef9e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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-tulu-2-dpo-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-dpo-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-dpo-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-dpo-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-dpo-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-dpo-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-dpo-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-dpo-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-dpo-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-dpo-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-dpo-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ec56421 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: allenai/llama-3.1-tulu-2-dpo-8b +datasets: +- allenai/tulu-v2-sft-mixture +- argilla/ultrafeedback-binarized-preferences-cleaned +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/allenai/llama-3.1-tulu-2-dpo-8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3.1-tulu-2-dpo-8b-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-3.1-tulu-2-dpo-8b-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-3.1-tulu-2-dpo-8b-GGUF/resolve/main/llama-3.1-tulu-2-dpo-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-dpo-8b-GGUF/resolve/main/llama-3.1-tulu-2-dpo-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-dpo-8b-GGUF/resolve/main/llama-3.1-tulu-2-dpo-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-dpo-8b-GGUF/resolve/main/llama-3.1-tulu-2-dpo-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-dpo-8b-GGUF/resolve/main/llama-3.1-tulu-2-dpo-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-dpo-8b-GGUF/resolve/main/llama-3.1-tulu-2-dpo-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-dpo-8b-GGUF/resolve/main/llama-3.1-tulu-2-dpo-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-dpo-8b-GGUF/resolve/main/llama-3.1-tulu-2-dpo-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-dpo-8b-GGUF/resolve/main/llama-3.1-tulu-2-dpo-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-dpo-8b-GGUF/resolve/main/llama-3.1-tulu-2-dpo-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-dpo-8b-GGUF/resolve/main/llama-3.1-tulu-2-dpo-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-dpo-8b-GGUF/resolve/main/llama-3.1-tulu-2-dpo-8b.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-3.1-tulu-2-dpo-8b.IQ4_XS.gguf b/llama-3.1-tulu-2-dpo-8b.IQ4_XS.gguf new file mode 100644 index 0000000..18ead6b --- /dev/null +++ b/llama-3.1-tulu-2-dpo-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b60b9060363414cd7d59e219b7feb98e99f3268233605879bfdcb09718aaf81 +size 4484364224 diff --git a/llama-3.1-tulu-2-dpo-8b.Q2_K.gguf b/llama-3.1-tulu-2-dpo-8b.Q2_K.gguf new file mode 100644 index 0000000..18e626c --- /dev/null +++ b/llama-3.1-tulu-2-dpo-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fddb75228aa506788ea8cee2a5f5f15f37215703b3010d1f9c0a02f3bf1bb6a +size 3179132864 diff --git a/llama-3.1-tulu-2-dpo-8b.Q3_K_L.gguf b/llama-3.1-tulu-2-dpo-8b.Q3_K_L.gguf new file mode 100644 index 0000000..35e1bc8 --- /dev/null +++ b/llama-3.1-tulu-2-dpo-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b8301e062014ca2f1198c1daccbf6e4806339579f7f090049a1e43fbbe8ace7 +size 4321957824 diff --git a/llama-3.1-tulu-2-dpo-8b.Q3_K_M.gguf b/llama-3.1-tulu-2-dpo-8b.Q3_K_M.gguf new file mode 100644 index 0000000..dada7de --- /dev/null +++ b/llama-3.1-tulu-2-dpo-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2bd1c90c55bc7d5cd9cdac344bc10fa500ffa4ef5c2e02be5c79f1528a44499 +size 4018919360 diff --git a/llama-3.1-tulu-2-dpo-8b.Q3_K_S.gguf b/llama-3.1-tulu-2-dpo-8b.Q3_K_S.gguf new file mode 100644 index 0000000..e9454a5 --- /dev/null +++ b/llama-3.1-tulu-2-dpo-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc1987afd1b50688025b3898a4bb2209e5254cd7b4bcbc20d758eedcfd80e61c +size 3664500672 diff --git a/llama-3.1-tulu-2-dpo-8b.Q4_K_M.gguf b/llama-3.1-tulu-2-dpo-8b.Q4_K_M.gguf new file mode 100644 index 0000000..8b4ea8e --- /dev/null +++ b/llama-3.1-tulu-2-dpo-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f6f678698f7d08296091c25922462d6fc78e98492e84ec9000684e0b612fd92 +size 4920735680 diff --git a/llama-3.1-tulu-2-dpo-8b.Q4_K_S.gguf b/llama-3.1-tulu-2-dpo-8b.Q4_K_S.gguf new file mode 100644 index 0000000..28700cb --- /dev/null +++ b/llama-3.1-tulu-2-dpo-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96e5d4c28d9ba7ce030a219066f91551af7f37c3d88ef701abeaf444faf1518d +size 4692670400 diff --git a/llama-3.1-tulu-2-dpo-8b.Q5_K_M.gguf b/llama-3.1-tulu-2-dpo-8b.Q5_K_M.gguf new file mode 100644 index 0000000..84853cb --- /dev/null +++ b/llama-3.1-tulu-2-dpo-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba919513b6c00c81075216dc65474f21ae22f180dba56a6eb07855d9eedf524a +size 5732988864 diff --git a/llama-3.1-tulu-2-dpo-8b.Q5_K_S.gguf b/llama-3.1-tulu-2-dpo-8b.Q5_K_S.gguf new file mode 100644 index 0000000..20669b0 --- /dev/null +++ b/llama-3.1-tulu-2-dpo-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe145ea5af6a241a7c7550028d29e509ad91b1cc4d940ec80b9cde5d35f0c201 +size 5599295424 diff --git a/llama-3.1-tulu-2-dpo-8b.Q6_K.gguf b/llama-3.1-tulu-2-dpo-8b.Q6_K.gguf new file mode 100644 index 0000000..4346258 --- /dev/null +++ b/llama-3.1-tulu-2-dpo-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a70446913779d75703257c1225578e93963d45e258195b21cae961c9aa0adab +size 6596007872 diff --git a/llama-3.1-tulu-2-dpo-8b.Q8_0.gguf b/llama-3.1-tulu-2-dpo-8b.Q8_0.gguf new file mode 100644 index 0000000..8b973c0 --- /dev/null +++ b/llama-3.1-tulu-2-dpo-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abf8d84c479b2b1870627f4815c75e3c1b51a56e352f79ab94d4d6f148c47726 +size 8540772288 diff --git a/llama-3.1-tulu-2-dpo-8b.f16.gguf b/llama-3.1-tulu-2-dpo-8b.f16.gguf new file mode 100644 index 0000000..390c79b --- /dev/null +++ b/llama-3.1-tulu-2-dpo-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:508eade39e788a9fcc5e7669e8bde644ae34af74d3e2b5ab9b5029052b35e47b +size 16068892608