commit 32f88c3ca6946ea8f859cd987c7fbe5fc7cb9f3c Author: ModelHub XC Date: Sat May 23 05:30:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-Danoia-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b62994c --- /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-3.1-8B-Danoia.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Danoia.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Danoia.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Danoia.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Danoia.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Danoia.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Danoia.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Danoia.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Danoia.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Danoia.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Danoia.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Danoia.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-Danoia.IQ4_XS.gguf b/Llama-3.1-8B-Danoia.IQ4_XS.gguf new file mode 100644 index 0000000..d2272eb --- /dev/null +++ b/Llama-3.1-8B-Danoia.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13e107fc3d637eaba9875bacba5e9c9054c7fbd4a00492ebd9b665c1fba936e3 +size 4484369184 diff --git a/Llama-3.1-8B-Danoia.Q2_K.gguf b/Llama-3.1-8B-Danoia.Q2_K.gguf new file mode 100644 index 0000000..38ad3ce --- /dev/null +++ b/Llama-3.1-8B-Danoia.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:703be40c0b01c48482487493f865afbd2b2dd209b55057949a3d4247f1c5517a +size 3179137824 diff --git a/Llama-3.1-8B-Danoia.Q3_K_L.gguf b/Llama-3.1-8B-Danoia.Q3_K_L.gguf new file mode 100644 index 0000000..39bcda4 --- /dev/null +++ b/Llama-3.1-8B-Danoia.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d0c7adb900c0b7710a6fb43429c9eab11806dd0a0d88b176b5a2f59bb2151ef +size 4321962784 diff --git a/Llama-3.1-8B-Danoia.Q3_K_M.gguf b/Llama-3.1-8B-Danoia.Q3_K_M.gguf new file mode 100644 index 0000000..0cdcceb --- /dev/null +++ b/Llama-3.1-8B-Danoia.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cd5c6ccb84dd888f659ed1d00030b7e46556538a8722a28e16be06accb7298f +size 4018924320 diff --git a/Llama-3.1-8B-Danoia.Q3_K_S.gguf b/Llama-3.1-8B-Danoia.Q3_K_S.gguf new file mode 100644 index 0000000..714a182 --- /dev/null +++ b/Llama-3.1-8B-Danoia.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4be0260c15d25eeb5ee8216a21c974f3e04f1312d3594bd96ed9f2aeda515af4 +size 3664505632 diff --git a/Llama-3.1-8B-Danoia.Q4_K_M.gguf b/Llama-3.1-8B-Danoia.Q4_K_M.gguf new file mode 100644 index 0000000..456bfde --- /dev/null +++ b/Llama-3.1-8B-Danoia.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccf6b7b8c0df8d80a80dc5a58db83f885760deea683d5b911a407b31b7f98cdc +size 4920740640 diff --git a/Llama-3.1-8B-Danoia.Q4_K_S.gguf b/Llama-3.1-8B-Danoia.Q4_K_S.gguf new file mode 100644 index 0000000..e04c667 --- /dev/null +++ b/Llama-3.1-8B-Danoia.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8f9445d4621a7c0c6504ecaa94d9e181563c0e2da9dc29a8108f5f57a8e36eb +size 4692675360 diff --git a/Llama-3.1-8B-Danoia.Q5_K_M.gguf b/Llama-3.1-8B-Danoia.Q5_K_M.gguf new file mode 100644 index 0000000..ef6ada1 --- /dev/null +++ b/Llama-3.1-8B-Danoia.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36799b5b8067f8647bd1a30b5b2df06ddb33480f8b27d5385db3e8afa77aa30f +size 5732993824 diff --git a/Llama-3.1-8B-Danoia.Q5_K_S.gguf b/Llama-3.1-8B-Danoia.Q5_K_S.gguf new file mode 100644 index 0000000..8348a1d --- /dev/null +++ b/Llama-3.1-8B-Danoia.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac688441fa4cabe0062de15992ad2107863b5601923ffd2f8ba5bce17968389e +size 5599300384 diff --git a/Llama-3.1-8B-Danoia.Q6_K.gguf b/Llama-3.1-8B-Danoia.Q6_K.gguf new file mode 100644 index 0000000..53dde6c --- /dev/null +++ b/Llama-3.1-8B-Danoia.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86fd87a28492b7de516a1ca4e9004f13cedb94946874d0c25df5e1daeb7863ef +size 6596012832 diff --git a/Llama-3.1-8B-Danoia.Q8_0.gguf b/Llama-3.1-8B-Danoia.Q8_0.gguf new file mode 100644 index 0000000..d402b1c --- /dev/null +++ b/Llama-3.1-8B-Danoia.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3404664dd22683d835bbad0adebe109244aa7cd68582a2f572e410e4afceb95 +size 8540777248 diff --git a/Llama-3.1-8B-Danoia.f16.gguf b/Llama-3.1-8B-Danoia.f16.gguf new file mode 100644 index 0000000..afd6ea8 --- /dev/null +++ b/Llama-3.1-8B-Danoia.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84b31e2cc5d4c816fc57051e2f0011b4956a3c488047fb0f5ab02a9e5cdf1cbf +size 16068897568 diff --git a/README.md b/README.md new file mode 100644 index 0000000..45b292c --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: trollek/Llama-3.1-8B-Danoia +datasets: +- trollek/Danoia-v03 +- trollek/Danoia-v02 +- N8Programs/CreativeGPT +- Gryphe/Opus-WritingPrompts +language: +- da +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- llama-factory +- unsloth +--- +## About + + + + + + +static quants of https://huggingface.co/trollek/Llama-3.1-8B-Danoia + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-Danoia-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-3.1-8B-Danoia-GGUF/resolve/main/Llama-3.1-8B-Danoia.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Danoia-GGUF/resolve/main/Llama-3.1-8B-Danoia.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Danoia-GGUF/resolve/main/Llama-3.1-8B-Danoia.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Danoia-GGUF/resolve/main/Llama-3.1-8B-Danoia.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Danoia-GGUF/resolve/main/Llama-3.1-8B-Danoia.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Danoia-GGUF/resolve/main/Llama-3.1-8B-Danoia.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Danoia-GGUF/resolve/main/Llama-3.1-8B-Danoia.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Danoia-GGUF/resolve/main/Llama-3.1-8B-Danoia.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Danoia-GGUF/resolve/main/Llama-3.1-8B-Danoia.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Danoia-GGUF/resolve/main/Llama-3.1-8B-Danoia.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Danoia-GGUF/resolve/main/Llama-3.1-8B-Danoia.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Danoia-GGUF/resolve/main/Llama-3.1-8B-Danoia.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. + +