commit d1f6c41a02dc2e73d0df6efd95cdd8110914e8cc Author: ModelHub XC Date: Sat Jun 20 21:55:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ArxivLlama_dsllama-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f9190f2 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +ArxivLlama_dsllama.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama_dsllama.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama_dsllama.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama_dsllama.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama_dsllama.f16.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama_dsllama.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama_dsllama.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama_dsllama.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama_dsllama.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama_dsllama.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama_dsllama.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ArxivLlama_dsllama.IQ4_XS.gguf b/ArxivLlama_dsllama.IQ4_XS.gguf new file mode 100644 index 0000000..e52152a --- /dev/null +++ b/ArxivLlama_dsllama.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50111fd3bb31a1ad6af62678cb6434b64dbdaa1f3fc515525b59abaeaec23d4a +size 4484364576 diff --git a/ArxivLlama_dsllama.Q2_K.gguf b/ArxivLlama_dsllama.Q2_K.gguf new file mode 100644 index 0000000..1e4a865 --- /dev/null +++ b/ArxivLlama_dsllama.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fca67acd1bbb2023b92057b22d8b4325b5b5f8d77b269a2d9fe6b055dd0cf650 +size 3179133216 diff --git a/ArxivLlama_dsllama.Q3_K_L.gguf b/ArxivLlama_dsllama.Q3_K_L.gguf new file mode 100644 index 0000000..829a800 --- /dev/null +++ b/ArxivLlama_dsllama.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9fa9450bf282344df0ee3bb78b8e5006e9d5857d95e9c02601212420f5928d5 +size 4321958176 diff --git a/ArxivLlama_dsllama.Q3_K_M.gguf b/ArxivLlama_dsllama.Q3_K_M.gguf new file mode 100644 index 0000000..e48e08f --- /dev/null +++ b/ArxivLlama_dsllama.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a79724b02acbf041b5adde297c08d45c076b38381d6c5251b597eb6ae2c677a +size 4018919712 diff --git a/ArxivLlama_dsllama.Q3_K_S.gguf b/ArxivLlama_dsllama.Q3_K_S.gguf new file mode 100644 index 0000000..15a8cc4 --- /dev/null +++ b/ArxivLlama_dsllama.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e90b67d37ea3cfa59259fc9dc31fda990e8542421d239307bfef09bf1ea7c8ec +size 3664501024 diff --git a/ArxivLlama_dsllama.Q4_K_M.gguf b/ArxivLlama_dsllama.Q4_K_M.gguf new file mode 100644 index 0000000..b339a9e --- /dev/null +++ b/ArxivLlama_dsllama.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08316a26f6adbcbbe3ba4c8956a5895880b3856411445c3a639a1b442d61f6c1 +size 4920736032 diff --git a/ArxivLlama_dsllama.Q4_K_S.gguf b/ArxivLlama_dsllama.Q4_K_S.gguf new file mode 100644 index 0000000..4c84a99 --- /dev/null +++ b/ArxivLlama_dsllama.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7a2dbfe9b6a69d25caadd59bad926e0afa39a1ddbbf1e93987fe3ee365abb78 +size 4692670752 diff --git a/ArxivLlama_dsllama.Q5_K_M.gguf b/ArxivLlama_dsllama.Q5_K_M.gguf new file mode 100644 index 0000000..17aa5f2 --- /dev/null +++ b/ArxivLlama_dsllama.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29c7ca14e29746146475b08fd2706626820c3c09aa2acec93c404ed8bec03ca9 +size 5732989216 diff --git a/ArxivLlama_dsllama.Q5_K_S.gguf b/ArxivLlama_dsllama.Q5_K_S.gguf new file mode 100644 index 0000000..e203497 --- /dev/null +++ b/ArxivLlama_dsllama.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ffde64e7f183072d52a81df0981ef3ac55a44fd67793d4143d1a9d29a73c900 +size 5599295776 diff --git a/ArxivLlama_dsllama.Q6_K.gguf b/ArxivLlama_dsllama.Q6_K.gguf new file mode 100644 index 0000000..c0e120d --- /dev/null +++ b/ArxivLlama_dsllama.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf7e8ed8ef98bb32b755853331cf12bc22c6f49945b473514ee2306627e32538 +size 6596008224 diff --git a/ArxivLlama_dsllama.Q8_0.gguf b/ArxivLlama_dsllama.Q8_0.gguf new file mode 100644 index 0000000..a7d29f5 --- /dev/null +++ b/ArxivLlama_dsllama.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57f35344ee03c172c27e19d9c2026508ecb39eb6ffe6271e9ba232ac9d055207 +size 8540772640 diff --git a/ArxivLlama_dsllama.f16.gguf b/ArxivLlama_dsllama.f16.gguf new file mode 100644 index 0000000..9430539 --- /dev/null +++ b/ArxivLlama_dsllama.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39f1707a13af0f12cfe08042f632611ee12fcd6077fbaf696522b8b5e01f4b29 +size 16068892960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b3ec7b7 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: xinyifang/ArxivLlama_dsllama +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/xinyifang/ArxivLlama_dsllama + + +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/ArxivLlama_dsllama-GGUF/resolve/main/ArxivLlama_dsllama.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama_dsllama-GGUF/resolve/main/ArxivLlama_dsllama.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama_dsllama-GGUF/resolve/main/ArxivLlama_dsllama.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama_dsllama-GGUF/resolve/main/ArxivLlama_dsllama.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama_dsllama-GGUF/resolve/main/ArxivLlama_dsllama.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama_dsllama-GGUF/resolve/main/ArxivLlama_dsllama.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama_dsllama-GGUF/resolve/main/ArxivLlama_dsllama.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama_dsllama-GGUF/resolve/main/ArxivLlama_dsllama.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama_dsllama-GGUF/resolve/main/ArxivLlama_dsllama.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama_dsllama-GGUF/resolve/main/ArxivLlama_dsllama.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama_dsllama-GGUF/resolve/main/ArxivLlama_dsllama.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama_dsllama-GGUF/resolve/main/ArxivLlama_dsllama.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. + +