commit d6a7c2693aca8da05b208c76211bedf82f617067 Author: ModelHub XC Date: Mon Jun 15 00:39:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Delphermes-1.7B-Thinking-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..da4070c --- /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 +Delphermes-1.7B-Thinking.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-1.7B-Thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-1.7B-Thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-1.7B-Thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-1.7B-Thinking.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-1.7B-Thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-1.7B-Thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-1.7B-Thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-1.7B-Thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-1.7B-Thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-1.7B-Thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-1.7B-Thinking.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Delphermes-1.7B-Thinking.IQ4_XS.gguf b/Delphermes-1.7B-Thinking.IQ4_XS.gguf new file mode 100644 index 0000000..58a53e9 --- /dev/null +++ b/Delphermes-1.7B-Thinking.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1884d8e55a29fa7913416d1694fc9d29f0143d893eea2924f0df95e7b8fa7a0 +size 1181587680 diff --git a/Delphermes-1.7B-Thinking.Q2_K.gguf b/Delphermes-1.7B-Thinking.Q2_K.gguf new file mode 100644 index 0000000..9c2a4d9 --- /dev/null +++ b/Delphermes-1.7B-Thinking.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaf75a4c601d022267ebce884dbe9ab65ec8c06c04e4ca6bd0185e8062f6e3b7 +size 879896800 diff --git a/Delphermes-1.7B-Thinking.Q3_K_L.gguf b/Delphermes-1.7B-Thinking.Q3_K_L.gguf new file mode 100644 index 0000000..16ac6c0 --- /dev/null +++ b/Delphermes-1.7B-Thinking.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22046d85e10e60e990969acc59a3a1ed6592089905905d3f8b09b773560bde50 +size 1137205472 diff --git a/Delphermes-1.7B-Thinking.Q3_K_M.gguf b/Delphermes-1.7B-Thinking.Q3_K_M.gguf new file mode 100644 index 0000000..a76a868 --- /dev/null +++ b/Delphermes-1.7B-Thinking.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d086e820068671c31f62422ac41329976f141cee1cdc123abde1b6277f120db5 +size 1073242336 diff --git a/Delphermes-1.7B-Thinking.Q3_K_S.gguf b/Delphermes-1.7B-Thinking.Q3_K_S.gguf new file mode 100644 index 0000000..2699519 --- /dev/null +++ b/Delphermes-1.7B-Thinking.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9b3b68ba1022f981051f6046323704d8530774c7bb6ea718eee770d2175e955 +size 1000956128 diff --git a/Delphermes-1.7B-Thinking.Q4_K_M.gguf b/Delphermes-1.7B-Thinking.Q4_K_M.gguf new file mode 100644 index 0000000..5b0164b --- /dev/null +++ b/Delphermes-1.7B-Thinking.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:206c45cf97a6c0238dcdcd6a6b3cc0ebacb48993d012c4bb1a3775bef6736a43 +size 1282439392 diff --git a/Delphermes-1.7B-Thinking.Q4_K_S.gguf b/Delphermes-1.7B-Thinking.Q4_K_S.gguf new file mode 100644 index 0000000..9600aa2 --- /dev/null +++ b/Delphermes-1.7B-Thinking.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22ebc6fa9521b3c6e0d3d8ab3110c27bb20955ca3f7a7b078aa2d478662856b2 +size 1235220704 diff --git a/Delphermes-1.7B-Thinking.Q5_K_M.gguf b/Delphermes-1.7B-Thinking.Q5_K_M.gguf new file mode 100644 index 0000000..207f1b7 --- /dev/null +++ b/Delphermes-1.7B-Thinking.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a773d16cffaaa62a56af138fc7db4c7dc4a8ebbcb6502f60bc5df74f4346bb01 +size 1471805664 diff --git a/Delphermes-1.7B-Thinking.Q5_K_S.gguf b/Delphermes-1.7B-Thinking.Q5_K_S.gguf new file mode 100644 index 0000000..8f69142 --- /dev/null +++ b/Delphermes-1.7B-Thinking.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:864abe0e06720e57e836b1cad89f18736bcbab12de8d6805f28a1cf8b8d4ef9c +size 1444509920 diff --git a/Delphermes-1.7B-Thinking.Q6_K.gguf b/Delphermes-1.7B-Thinking.Q6_K.gguf new file mode 100644 index 0000000..7b4cb3d --- /dev/null +++ b/Delphermes-1.7B-Thinking.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e9c61270f69bf98eee1dad53240508eba8c26d40a93a00a68d43b4992583205 +size 1673007328 diff --git a/Delphermes-1.7B-Thinking.Q8_0.gguf b/Delphermes-1.7B-Thinking.Q8_0.gguf new file mode 100644 index 0000000..f37a5df --- /dev/null +++ b/Delphermes-1.7B-Thinking.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:195ce3e500b3de7ffeece7749f95c7a80d588a1210c5350fc89b26f79fdd8888 +size 2165039328 diff --git a/Delphermes-1.7B-Thinking.f16.gguf b/Delphermes-1.7B-Thinking.f16.gguf new file mode 100644 index 0000000..66ebd88 --- /dev/null +++ b/Delphermes-1.7B-Thinking.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27f117e5dcbe5a7cf11de557bdd176fd7ff42fb78a5957ee18249c0bb2ce47b1 +size 4069679328 diff --git a/README.md b/README.md new file mode 100644 index 0000000..715cf5d --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: justinj92/Delphermes-1.7B-Thinking +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/justinj92/Delphermes-1.7B-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Delphermes-1.7B-Thinking-GGUF).*** + +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/Delphermes-1.7B-Thinking-GGUF/resolve/main/Delphermes-1.7B-Thinking.Q2_K.gguf) | Q2_K | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-1.7B-Thinking-GGUF/resolve/main/Delphermes-1.7B-Thinking.Q3_K_S.gguf) | Q3_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-1.7B-Thinking-GGUF/resolve/main/Delphermes-1.7B-Thinking.Q3_K_M.gguf) | Q3_K_M | 1.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-1.7B-Thinking-GGUF/resolve/main/Delphermes-1.7B-Thinking.Q3_K_L.gguf) | Q3_K_L | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-1.7B-Thinking-GGUF/resolve/main/Delphermes-1.7B-Thinking.IQ4_XS.gguf) | IQ4_XS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-1.7B-Thinking-GGUF/resolve/main/Delphermes-1.7B-Thinking.Q4_K_S.gguf) | Q4_K_S | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-1.7B-Thinking-GGUF/resolve/main/Delphermes-1.7B-Thinking.Q4_K_M.gguf) | Q4_K_M | 1.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-1.7B-Thinking-GGUF/resolve/main/Delphermes-1.7B-Thinking.Q5_K_S.gguf) | Q5_K_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-1.7B-Thinking-GGUF/resolve/main/Delphermes-1.7B-Thinking.Q5_K_M.gguf) | Q5_K_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-1.7B-Thinking-GGUF/resolve/main/Delphermes-1.7B-Thinking.Q6_K.gguf) | Q6_K | 1.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-1.7B-Thinking-GGUF/resolve/main/Delphermes-1.7B-Thinking.Q8_0.gguf) | Q8_0 | 2.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-1.7B-Thinking-GGUF/resolve/main/Delphermes-1.7B-Thinking.f16.gguf) | f16 | 4.2 | 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. + +