commit e0af12409bb7b877efbc2fe60f204fe28097c111 Author: ModelHub XC Date: Fri Jul 3 18:08:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ArxivLlama3.1_6144-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f94dcc3 --- /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 +ArxivLlama3.1_6144.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama3.1_6144.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama3.1_6144.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama3.1_6144.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama3.1_6144.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama3.1_6144.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama3.1_6144.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama3.1_6144.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama3.1_6144.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama3.1_6144.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ArxivLlama3.1_6144.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ArxivLlama3.1_6144.IQ4_XS.gguf b/ArxivLlama3.1_6144.IQ4_XS.gguf new file mode 100644 index 0000000..3f89934 --- /dev/null +++ b/ArxivLlama3.1_6144.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35185ae01e04df86499b204d784ab38dfb375b2e245bd7d8e2c6831e6290313b +size 4484364224 diff --git a/ArxivLlama3.1_6144.Q2_K.gguf b/ArxivLlama3.1_6144.Q2_K.gguf new file mode 100644 index 0000000..1e6c0ae --- /dev/null +++ b/ArxivLlama3.1_6144.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69b02ba6112c0204cb6d8308a7470ac606218eae39a5f5633fe0fcafb8ab5f5e +size 3179132864 diff --git a/ArxivLlama3.1_6144.Q3_K_L.gguf b/ArxivLlama3.1_6144.Q3_K_L.gguf new file mode 100644 index 0000000..c66ed94 --- /dev/null +++ b/ArxivLlama3.1_6144.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d331332b55a9ba79d69778771136b9a71ffa6c8ce1bf5fc51cc4090b2e17092 +size 4321957824 diff --git a/ArxivLlama3.1_6144.Q3_K_M.gguf b/ArxivLlama3.1_6144.Q3_K_M.gguf new file mode 100644 index 0000000..2e285e0 --- /dev/null +++ b/ArxivLlama3.1_6144.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b28f5434b63da480f3a258855d10f5690ad626a22b7345850390ee77920acdbb +size 4018919360 diff --git a/ArxivLlama3.1_6144.Q3_K_S.gguf b/ArxivLlama3.1_6144.Q3_K_S.gguf new file mode 100644 index 0000000..8be9c8d --- /dev/null +++ b/ArxivLlama3.1_6144.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00bbde14239894f7e5ef71dc7c3f3cce4ce5fbd7f4106e1d94bbaf73f97c219e +size 3664500672 diff --git a/ArxivLlama3.1_6144.Q4_K_M.gguf b/ArxivLlama3.1_6144.Q4_K_M.gguf new file mode 100644 index 0000000..da55ede --- /dev/null +++ b/ArxivLlama3.1_6144.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:679f592244e913ed556cd652a42e9ccc823077321768f44ee4025245b1285ad0 +size 4920735680 diff --git a/ArxivLlama3.1_6144.Q4_K_S.gguf b/ArxivLlama3.1_6144.Q4_K_S.gguf new file mode 100644 index 0000000..78ccffd --- /dev/null +++ b/ArxivLlama3.1_6144.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c98fd9872f26d5d08708f6b3fdedb63df85483c8958d95ca1088df90bf658bb4 +size 4692670400 diff --git a/ArxivLlama3.1_6144.Q5_K_M.gguf b/ArxivLlama3.1_6144.Q5_K_M.gguf new file mode 100644 index 0000000..83751c9 --- /dev/null +++ b/ArxivLlama3.1_6144.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4b039d270eea8305285f3326bf86faf5f298552dfd4b24f9f031c42e677124d +size 5732988864 diff --git a/ArxivLlama3.1_6144.Q5_K_S.gguf b/ArxivLlama3.1_6144.Q5_K_S.gguf new file mode 100644 index 0000000..0633585 --- /dev/null +++ b/ArxivLlama3.1_6144.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b16e574cf64be7e6482bda76c743092489ce29a275ba3b9d5d405355e4fd54 +size 5599295424 diff --git a/ArxivLlama3.1_6144.Q6_K.gguf b/ArxivLlama3.1_6144.Q6_K.gguf new file mode 100644 index 0000000..457d884 --- /dev/null +++ b/ArxivLlama3.1_6144.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2397ae6cb28c87ca55cdefabd1ff3e86aa8cb72172d97958545d1a7780d8f4ad +size 6596007872 diff --git a/ArxivLlama3.1_6144.Q8_0.gguf b/ArxivLlama3.1_6144.Q8_0.gguf new file mode 100644 index 0000000..0166d7c --- /dev/null +++ b/ArxivLlama3.1_6144.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc1774ea9bf9ae7b4ab3d0b203da083d7d69404c05b74afa830f82ea5941fac3 +size 8540772288 diff --git a/ArxivLlama3.1_6144.f16.gguf b/ArxivLlama3.1_6144.f16.gguf new file mode 100644 index 0000000..b6e8718 --- /dev/null +++ b/ArxivLlama3.1_6144.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6937f409fcb34e9dfae75a144c163e573a029ac7159ca0589796a12f2ce77498 +size 16068892608 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d70deda --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: xinyifang/ArxivLlama3.1_6144 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/xinyifang/ArxivLlama3.1_6144 + + +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/ArxivLlama3.1_6144-GGUF/resolve/main/ArxivLlama3.1_6144.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama3.1_6144-GGUF/resolve/main/ArxivLlama3.1_6144.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama3.1_6144-GGUF/resolve/main/ArxivLlama3.1_6144.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama3.1_6144-GGUF/resolve/main/ArxivLlama3.1_6144.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama3.1_6144-GGUF/resolve/main/ArxivLlama3.1_6144.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama3.1_6144-GGUF/resolve/main/ArxivLlama3.1_6144.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama3.1_6144-GGUF/resolve/main/ArxivLlama3.1_6144.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama3.1_6144-GGUF/resolve/main/ArxivLlama3.1_6144.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama3.1_6144-GGUF/resolve/main/ArxivLlama3.1_6144.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama3.1_6144-GGUF/resolve/main/ArxivLlama3.1_6144.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama3.1_6144-GGUF/resolve/main/ArxivLlama3.1_6144.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ArxivLlama3.1_6144-GGUF/resolve/main/ArxivLlama3.1_6144.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. + +