commit 4e28289f7cf668dd8375bad61a220fde994b6f86 Author: ModelHub XC Date: Sun Jun 14 03:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/dolphin-2.9-llama3-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a3c53cd --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +dolphin-2.9-llama3-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9-llama3-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..fdc79d9 --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: dphn/dolphin-2.9-llama3-8b +datasets: +- cognitivecomputations/Dolphin-2.9 +- teknium/OpenHermes-2.5 +- m-a-p/CodeFeedback-Filtered-Instruction +- cognitivecomputations/dolphin-coder +- cognitivecomputations/samantha-data +- HuggingFaceH4/ultrachat_200k +- microsoft/orca-math-word-problems-200k +- abacusai/SystemChat-1.1 +- Locutusque/function-calling-chatml +- internlm/Agent-FLAN +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- axolotl +--- +## About + + + + + + +static quants of https://huggingface.co/dphn/dolphin-2.9-llama3-8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#dolphin-2.9-llama3-8b-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-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/dolphin-2.9-llama3-8b-GGUF/resolve/main/dolphin-2.9-llama3-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-GGUF/resolve/main/dolphin-2.9-llama3-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-GGUF/resolve/main/dolphin-2.9-llama3-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-GGUF/resolve/main/dolphin-2.9-llama3-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-GGUF/resolve/main/dolphin-2.9-llama3-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-GGUF/resolve/main/dolphin-2.9-llama3-8b.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-GGUF/resolve/main/dolphin-2.9-llama3-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-GGUF/resolve/main/dolphin-2.9-llama3-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-GGUF/resolve/main/dolphin-2.9-llama3-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-GGUF/resolve/main/dolphin-2.9-llama3-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-GGUF/resolve/main/dolphin-2.9-llama3-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-GGUF/resolve/main/dolphin-2.9-llama3-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/dolphin-2.9-llama3-8b-GGUF/resolve/main/dolphin-2.9-llama3-8b.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/dolphin-2.9-llama3-8b.IQ4_XS.gguf b/dolphin-2.9-llama3-8b.IQ4_XS.gguf new file mode 100644 index 0000000..c8a325a --- /dev/null +++ b/dolphin-2.9-llama3-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b095b6f770ad8a8fbea497dd65f0bde358bba052fde248d89cda5574ef279d8f +size 4484376992 diff --git a/dolphin-2.9-llama3-8b.Q2_K.gguf b/dolphin-2.9-llama3-8b.Q2_K.gguf new file mode 100644 index 0000000..bf9b1c7 --- /dev/null +++ b/dolphin-2.9-llama3-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32557290d049a4d7bcd02b5987653252d9b727411e498881eb3e2be9fdbc5052 +size 3179143968 diff --git a/dolphin-2.9-llama3-8b.Q3_K_L.gguf b/dolphin-2.9-llama3-8b.Q3_K_L.gguf new file mode 100644 index 0000000..d2ece7e --- /dev/null +++ b/dolphin-2.9-llama3-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32aa50fce8195471b360baf5b4d5c1bd96698b1097c5453ccf2ea337540e8afd +size 4321969760 diff --git a/dolphin-2.9-llama3-8b.Q3_K_M.gguf b/dolphin-2.9-llama3-8b.Q3_K_M.gguf new file mode 100644 index 0000000..4927af8 --- /dev/null +++ b/dolphin-2.9-llama3-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2831615f45cff4376486876e8b0ebab6794b77609bcdddff69559b908b175e6 +size 4018931296 diff --git a/dolphin-2.9-llama3-8b.Q3_K_S.gguf b/dolphin-2.9-llama3-8b.Q3_K_S.gguf new file mode 100644 index 0000000..d700110 --- /dev/null +++ b/dolphin-2.9-llama3-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7ab272d5ac623655190e450b811936652e8c0d5bc30fb5583a587018e9e647a +size 3664512608 diff --git a/dolphin-2.9-llama3-8b.Q4_0_4_4.gguf b/dolphin-2.9-llama3-8b.Q4_0_4_4.gguf new file mode 100644 index 0000000..3f66deb --- /dev/null +++ b/dolphin-2.9-llama3-8b.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f03787b543d469bbc5c1d7d56b6cbb44190a38f0192bb9ab9c46b44fbbd6707 +size 4661226144 diff --git a/dolphin-2.9-llama3-8b.Q4_K_M.gguf b/dolphin-2.9-llama3-8b.Q4_K_M.gguf new file mode 100644 index 0000000..a3041af --- /dev/null +++ b/dolphin-2.9-llama3-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92945c5073130f4312c0632f4dbe67f1d63c3f953c3fa35a4eb0728fe0d00b9f +size 4920748704 diff --git a/dolphin-2.9-llama3-8b.Q4_K_S.gguf b/dolphin-2.9-llama3-8b.Q4_K_S.gguf new file mode 100644 index 0000000..8872ad6 --- /dev/null +++ b/dolphin-2.9-llama3-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1366614ef857d13333d1c3f28f69907be57216d4ff44f7958c4aed518bee75c1 +size 4692683424 diff --git a/dolphin-2.9-llama3-8b.Q5_K_M.gguf b/dolphin-2.9-llama3-8b.Q5_K_M.gguf new file mode 100644 index 0000000..f892cf0 --- /dev/null +++ b/dolphin-2.9-llama3-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ab3cc59f5de0f2b89d92c5a076d297b31fabca45896c10ba3100b0e734c85ee +size 5733002912 diff --git a/dolphin-2.9-llama3-8b.Q5_K_S.gguf b/dolphin-2.9-llama3-8b.Q5_K_S.gguf new file mode 100644 index 0000000..35c6676 --- /dev/null +++ b/dolphin-2.9-llama3-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2c10710842eeda9b02de4862c2633b426a54dde1882e2ca6f05ac0770b283bc +size 5599309472 diff --git a/dolphin-2.9-llama3-8b.Q6_K.gguf b/dolphin-2.9-llama3-8b.Q6_K.gguf new file mode 100644 index 0000000..b6d1064 --- /dev/null +++ b/dolphin-2.9-llama3-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:648831ec7161f4b0758b42b4fd45a8f3442da1ad39b8ce8e4e0e862c3b34f53d +size 6596023008 diff --git a/dolphin-2.9-llama3-8b.Q8_0.gguf b/dolphin-2.9-llama3-8b.Q8_0.gguf new file mode 100644 index 0000000..88a74cd --- /dev/null +++ b/dolphin-2.9-llama3-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f772ffc973c88c1cff439e0e3f6b256f9cfd5ca98d94640092fde17c72477c31 +size 8540791392 diff --git a/dolphin-2.9-llama3-8b.f16.gguf b/dolphin-2.9-llama3-8b.f16.gguf new file mode 100644 index 0000000..4c6dd34 --- /dev/null +++ b/dolphin-2.9-llama3-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cab812a621d2a3ac29a7a175c3ea73f3817fd16c75c4298f5b0e6beb37a0e2e +size 16068927072