commit d380895be02691b5ca3a9c7ce683ec1be0f94a66 Author: ModelHub XC Date: Sun May 31 07:19:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LlaMa-DUSFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3851eab --- /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-DUSFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlaMa-DUSFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LlaMa-DUSFT.f16.gguf filter=lfs diff=lfs merge=lfs -text +LlaMa-DUSFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LlaMa-DUSFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlaMa-DUSFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LlaMa-DUSFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlaMa-DUSFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LlaMa-DUSFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlaMa-DUSFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlaMa-DUSFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlaMa-DUSFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LlaMa-DUSFT.IQ4_XS.gguf b/LlaMa-DUSFT.IQ4_XS.gguf new file mode 100644 index 0000000..642dc81 --- /dev/null +++ b/LlaMa-DUSFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b591a13320cc3dac81d0c8be4120309931bf7614e5910ff70ecabafdf7352ab +size 4514923808 diff --git a/LlaMa-DUSFT.Q2_K.gguf b/LlaMa-DUSFT.Q2_K.gguf new file mode 100644 index 0000000..3d47497 --- /dev/null +++ b/LlaMa-DUSFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4cc3f307b35576f38c9cac848030d3fc01d6f20fd7cfa6b4ca08344e9a53349 +size 3128263968 diff --git a/LlaMa-DUSFT.Q3_K_L.gguf b/LlaMa-DUSFT.Q3_K_L.gguf new file mode 100644 index 0000000..345e2ea --- /dev/null +++ b/LlaMa-DUSFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b245c36a42cbc0a22d949f6b3ad66be37e5cf8d69c678833634a01789eb7be0 +size 4455245088 diff --git a/LlaMa-DUSFT.Q3_K_M.gguf b/LlaMa-DUSFT.Q3_K_M.gguf new file mode 100644 index 0000000..851353c --- /dev/null +++ b/LlaMa-DUSFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23b685dc66745cedcbff592620e49d86c95f61e6bcb4da367c5bddbf2f452bd4 +size 4077495584 diff --git a/LlaMa-DUSFT.Q3_K_S.gguf b/LlaMa-DUSFT.Q3_K_S.gguf new file mode 100644 index 0000000..b9b54b8 --- /dev/null +++ b/LlaMa-DUSFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f46a6c1c098f1537ce537df8c75eb7d64248c76b1443f5dd68ceadb77079dcd6 +size 3644237088 diff --git a/LlaMa-DUSFT.Q4_K_M.gguf b/LlaMa-DUSFT.Q4_K_M.gguf new file mode 100644 index 0000000..934502e --- /dev/null +++ b/LlaMa-DUSFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd216e03c8b6db3d60955a432fa4cd4b6e8002c8ff5d842ed6ab439c7f1e45ac +size 5055759648 diff --git a/LlaMa-DUSFT.Q4_K_S.gguf b/LlaMa-DUSFT.Q4_K_S.gguf new file mode 100644 index 0000000..7aa890b --- /dev/null +++ b/LlaMa-DUSFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75121273f159b5b665d3aaf647337b59d262b6cfec733503a9bcce1cfac7735e +size 4773332256 diff --git a/LlaMa-DUSFT.Q5_K_M.gguf b/LlaMa-DUSFT.Q5_K_M.gguf new file mode 100644 index 0000000..799a8b8 --- /dev/null +++ b/LlaMa-DUSFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28f33d485f37306268b1ee6c62273e631cabd659f260b9f54d1a6e47fef5792b +size 5929354528 diff --git a/LlaMa-DUSFT.Q5_K_S.gguf b/LlaMa-DUSFT.Q5_K_S.gguf new file mode 100644 index 0000000..1754295 --- /dev/null +++ b/LlaMa-DUSFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a603818b3efbda0fe37616fb70cc30ae505abf1a5b5ccfc2dfbffc8acd46cf8 +size 5765023008 diff --git a/LlaMa-DUSFT.Q6_K.gguf b/LlaMa-DUSFT.Q6_K.gguf new file mode 100644 index 0000000..19e6f14 --- /dev/null +++ b/LlaMa-DUSFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd762c9f0d7c3103c26014305ae5bb3f7418bc07c36d7dfe7503857d3382051a +size 6857549088 diff --git a/LlaMa-DUSFT.Q8_0.gguf b/LlaMa-DUSFT.Q8_0.gguf new file mode 100644 index 0000000..38f3e81 --- /dev/null +++ b/LlaMa-DUSFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8841f7d06b9f5ac0481246f6f0c2beb12f4f6c8eec13add14b497947fc3ca3af +size 8881546528 diff --git a/LlaMa-DUSFT.f16.gguf b/LlaMa-DUSFT.f16.gguf new file mode 100644 index 0000000..ac4a956 --- /dev/null +++ b/LlaMa-DUSFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22ab6d7df4cf9a77d644dddd1e6ffb6653acc36350ef8cc8613b172f901cfd7e +size 16716375328 diff --git a/README.md b/README.md new file mode 100644 index 0000000..174f219 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: leftfooted/LlaMa-DUSFT +datasets: +- Open-Orca/OpenOrca +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/leftfooted/LlaMa-DUSFT + + +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/LlaMa-DUSFT-GGUF/resolve/main/LlaMa-DUSFT.Q2_K.gguf) | Q2_K | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/LlaMa-DUSFT-GGUF/resolve/main/LlaMa-DUSFT.Q3_K_S.gguf) | Q3_K_S | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LlaMa-DUSFT-GGUF/resolve/main/LlaMa-DUSFT.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LlaMa-DUSFT-GGUF/resolve/main/LlaMa-DUSFT.Q3_K_L.gguf) | Q3_K_L | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LlaMa-DUSFT-GGUF/resolve/main/LlaMa-DUSFT.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LlaMa-DUSFT-GGUF/resolve/main/LlaMa-DUSFT.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LlaMa-DUSFT-GGUF/resolve/main/LlaMa-DUSFT.Q4_K_M.gguf) | Q4_K_M | 5.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LlaMa-DUSFT-GGUF/resolve/main/LlaMa-DUSFT.Q5_K_S.gguf) | Q5_K_S | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/LlaMa-DUSFT-GGUF/resolve/main/LlaMa-DUSFT.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/LlaMa-DUSFT-GGUF/resolve/main/LlaMa-DUSFT.Q6_K.gguf) | Q6_K | 7.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LlaMa-DUSFT-GGUF/resolve/main/LlaMa-DUSFT.Q8_0.gguf) | Q8_0 | 9.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LlaMa-DUSFT-GGUF/resolve/main/LlaMa-DUSFT.f16.gguf) | f16 | 16.8 | 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. + +