commit 6ccecfa6cd1cef8060ac1eb498712a7332b160f1 Author: ModelHub XC Date: Mon Jul 6 03:30:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DS-Distilled-Hermes-Llama-3.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..87764c7 --- /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 +DS-Distilled-Hermes-Llama-3.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DS-Distilled-Hermes-Llama-3.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DS-Distilled-Hermes-Llama-3.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DS-Distilled-Hermes-Llama-3.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DS-Distilled-Hermes-Llama-3.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +DS-Distilled-Hermes-Llama-3.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DS-Distilled-Hermes-Llama-3.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DS-Distilled-Hermes-Llama-3.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DS-Distilled-Hermes-Llama-3.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DS-Distilled-Hermes-Llama-3.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DS-Distilled-Hermes-Llama-3.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DS-Distilled-Hermes-Llama-3.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DS-Distilled-Hermes-Llama-3.1.IQ4_XS.gguf b/DS-Distilled-Hermes-Llama-3.1.IQ4_XS.gguf new file mode 100644 index 0000000..d5e547c --- /dev/null +++ b/DS-Distilled-Hermes-Llama-3.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82d438a1e324ec6494f08bb7bd6e3704d2a9e7588534040ae5eee7351b3a8b62 +size 4484368736 diff --git a/DS-Distilled-Hermes-Llama-3.1.Q2_K.gguf b/DS-Distilled-Hermes-Llama-3.1.Q2_K.gguf new file mode 100644 index 0000000..17b90fc --- /dev/null +++ b/DS-Distilled-Hermes-Llama-3.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db150f8cf102ecfe67abee519f2bcf6249e52293a1bcd34b37f936d4f185817f +size 3179137376 diff --git a/DS-Distilled-Hermes-Llama-3.1.Q3_K_L.gguf b/DS-Distilled-Hermes-Llama-3.1.Q3_K_L.gguf new file mode 100644 index 0000000..fb5dbf0 --- /dev/null +++ b/DS-Distilled-Hermes-Llama-3.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0acd29c02830f4fc1aa37c09cf4f90d6f5b68c613b9d6f74a892f1d693cca592 +size 4321962336 diff --git a/DS-Distilled-Hermes-Llama-3.1.Q3_K_M.gguf b/DS-Distilled-Hermes-Llama-3.1.Q3_K_M.gguf new file mode 100644 index 0000000..6ff517d --- /dev/null +++ b/DS-Distilled-Hermes-Llama-3.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d3108837808ae35b9f006b752cabaf363e8f861c3dbc5ddab4d0edc9f19c6b9 +size 4018923872 diff --git a/DS-Distilled-Hermes-Llama-3.1.Q3_K_S.gguf b/DS-Distilled-Hermes-Llama-3.1.Q3_K_S.gguf new file mode 100644 index 0000000..e32ea80 --- /dev/null +++ b/DS-Distilled-Hermes-Llama-3.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88cf5436c39254b6ef896ec40efe47e46cf799c3d166836275c0dd9996e4bf72 +size 3664505184 diff --git a/DS-Distilled-Hermes-Llama-3.1.Q4_K_M.gguf b/DS-Distilled-Hermes-Llama-3.1.Q4_K_M.gguf new file mode 100644 index 0000000..00a6df4 --- /dev/null +++ b/DS-Distilled-Hermes-Llama-3.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:982d7422d72b7ffee808011a3d078a4cb8eb26f7fc765477dd45213ece8fe752 +size 4920740192 diff --git a/DS-Distilled-Hermes-Llama-3.1.Q4_K_S.gguf b/DS-Distilled-Hermes-Llama-3.1.Q4_K_S.gguf new file mode 100644 index 0000000..5c09da0 --- /dev/null +++ b/DS-Distilled-Hermes-Llama-3.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50492e4781b3333c1f082844752c905bc20b43420d70bdb52e4eb545582298b2 +size 4692674912 diff --git a/DS-Distilled-Hermes-Llama-3.1.Q5_K_M.gguf b/DS-Distilled-Hermes-Llama-3.1.Q5_K_M.gguf new file mode 100644 index 0000000..27cdc58 --- /dev/null +++ b/DS-Distilled-Hermes-Llama-3.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ee0e3db88ec5a621a4d33b1bcc76472d071ba27e4dd911dfbb243c12ff17909 +size 5732993376 diff --git a/DS-Distilled-Hermes-Llama-3.1.Q5_K_S.gguf b/DS-Distilled-Hermes-Llama-3.1.Q5_K_S.gguf new file mode 100644 index 0000000..e1166b8 --- /dev/null +++ b/DS-Distilled-Hermes-Llama-3.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bde8cf32e055a4415f405a354d123f2478562664d7ea4da85e486b779e53b1f5 +size 5599299936 diff --git a/DS-Distilled-Hermes-Llama-3.1.Q6_K.gguf b/DS-Distilled-Hermes-Llama-3.1.Q6_K.gguf new file mode 100644 index 0000000..00c9bb5 --- /dev/null +++ b/DS-Distilled-Hermes-Llama-3.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abbfd285af8d5ac048f69381ff39555861e086a4b6500877a7c55ed8a0392cdb +size 6596012384 diff --git a/DS-Distilled-Hermes-Llama-3.1.Q8_0.gguf b/DS-Distilled-Hermes-Llama-3.1.Q8_0.gguf new file mode 100644 index 0000000..26c687a --- /dev/null +++ b/DS-Distilled-Hermes-Llama-3.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2733eec2582e87dd4997fd2197d946c91c9348b11165125d31f8d4bd998b8f28 +size 8540776800 diff --git a/DS-Distilled-Hermes-Llama-3.1.f16.gguf b/DS-Distilled-Hermes-Llama-3.1.f16.gguf new file mode 100644 index 0000000..0e8346d --- /dev/null +++ b/DS-Distilled-Hermes-Llama-3.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb75512a6acc12a409b1d64f4b3862ef76167ed1976a477b04d7eea990eaaa5a +size 16068897120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ca5efdb --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Triangle104/DS-Distilled-Hermes-Llama-3.1 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Triangle104/DS-Distilled-Hermes-Llama-3.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/DS-Distilled-Hermes-Llama-3.1-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/DS-Distilled-Hermes-Llama-3.1-GGUF/resolve/main/DS-Distilled-Hermes-Llama-3.1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/DS-Distilled-Hermes-Llama-3.1-GGUF/resolve/main/DS-Distilled-Hermes-Llama-3.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/DS-Distilled-Hermes-Llama-3.1-GGUF/resolve/main/DS-Distilled-Hermes-Llama-3.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DS-Distilled-Hermes-Llama-3.1-GGUF/resolve/main/DS-Distilled-Hermes-Llama-3.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/DS-Distilled-Hermes-Llama-3.1-GGUF/resolve/main/DS-Distilled-Hermes-Llama-3.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/DS-Distilled-Hermes-Llama-3.1-GGUF/resolve/main/DS-Distilled-Hermes-Llama-3.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DS-Distilled-Hermes-Llama-3.1-GGUF/resolve/main/DS-Distilled-Hermes-Llama-3.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DS-Distilled-Hermes-Llama-3.1-GGUF/resolve/main/DS-Distilled-Hermes-Llama-3.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/DS-Distilled-Hermes-Llama-3.1-GGUF/resolve/main/DS-Distilled-Hermes-Llama-3.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/DS-Distilled-Hermes-Llama-3.1-GGUF/resolve/main/DS-Distilled-Hermes-Llama-3.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DS-Distilled-Hermes-Llama-3.1-GGUF/resolve/main/DS-Distilled-Hermes-Llama-3.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DS-Distilled-Hermes-Llama-3.1-GGUF/resolve/main/DS-Distilled-Hermes-Llama-3.1.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. + +