commit 2837f35699717a508f992aac0eb6d3e8d989a254 Author: ModelHub XC Date: Mon Sep 28 18:30:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLaMA-3.1-8B-Instruct-KW-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d126dc1 --- /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-Instruct-KW-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Instruct-KW-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Instruct-KW-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Instruct-KW-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Instruct-KW-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Instruct-KW-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Instruct-KW-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Instruct-KW-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Instruct-KW-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Instruct-KW-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Instruct-KW-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Instruct-KW-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLaMA-3.1-8B-Instruct-KW-v2.IQ4_XS.gguf b/LLaMA-3.1-8B-Instruct-KW-v2.IQ4_XS.gguf new file mode 100644 index 0000000..d1c6889 --- /dev/null +++ b/LLaMA-3.1-8B-Instruct-KW-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbfbc088cccf6214551e81503928e908456c9bdf5df024b1f55bcbf47fdd2e2a +size 4484363200 diff --git a/LLaMA-3.1-8B-Instruct-KW-v2.Q2_K.gguf b/LLaMA-3.1-8B-Instruct-KW-v2.Q2_K.gguf new file mode 100644 index 0000000..4906063 --- /dev/null +++ b/LLaMA-3.1-8B-Instruct-KW-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8f560473fb095127babe909c85d6068546fa47251f89bf273daa1a85ba43aa6 +size 3179131840 diff --git a/LLaMA-3.1-8B-Instruct-KW-v2.Q3_K_L.gguf b/LLaMA-3.1-8B-Instruct-KW-v2.Q3_K_L.gguf new file mode 100644 index 0000000..6122a4c --- /dev/null +++ b/LLaMA-3.1-8B-Instruct-KW-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b5be2b7db7523c05b1cb7b21049f15e0178484c1c6adc3e22d07f7860936025 +size 4321956800 diff --git a/LLaMA-3.1-8B-Instruct-KW-v2.Q3_K_M.gguf b/LLaMA-3.1-8B-Instruct-KW-v2.Q3_K_M.gguf new file mode 100644 index 0000000..774f729 --- /dev/null +++ b/LLaMA-3.1-8B-Instruct-KW-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:588572193ee4421ab9e1356fd1ac49ea22df1b7d3ea454708765f739b5c056a3 +size 4018918336 diff --git a/LLaMA-3.1-8B-Instruct-KW-v2.Q3_K_S.gguf b/LLaMA-3.1-8B-Instruct-KW-v2.Q3_K_S.gguf new file mode 100644 index 0000000..5af2c04 --- /dev/null +++ b/LLaMA-3.1-8B-Instruct-KW-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13421dfe6cc0f0dbacf93fe15b84ef7bb9463532028daa87fb2a0529bb029f50 +size 3664499648 diff --git a/LLaMA-3.1-8B-Instruct-KW-v2.Q4_K_M.gguf b/LLaMA-3.1-8B-Instruct-KW-v2.Q4_K_M.gguf new file mode 100644 index 0000000..828091a --- /dev/null +++ b/LLaMA-3.1-8B-Instruct-KW-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70ca1918f0492d8148d6eaac31e46ac182294678383391707e5429d0944c3ddf +size 4920734656 diff --git a/LLaMA-3.1-8B-Instruct-KW-v2.Q4_K_S.gguf b/LLaMA-3.1-8B-Instruct-KW-v2.Q4_K_S.gguf new file mode 100644 index 0000000..57df8fa --- /dev/null +++ b/LLaMA-3.1-8B-Instruct-KW-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2629267a5e529f15dfa2fc22818df0cefe10c630a65a1f6d98cc66f5de26bfa3 +size 4692669376 diff --git a/LLaMA-3.1-8B-Instruct-KW-v2.Q5_K_M.gguf b/LLaMA-3.1-8B-Instruct-KW-v2.Q5_K_M.gguf new file mode 100644 index 0000000..1e451c1 --- /dev/null +++ b/LLaMA-3.1-8B-Instruct-KW-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9405138f3c6dcd0a67f9d255a6e84ed57000d28e0108268dbeed238b6ccf939 +size 5732987840 diff --git a/LLaMA-3.1-8B-Instruct-KW-v2.Q5_K_S.gguf b/LLaMA-3.1-8B-Instruct-KW-v2.Q5_K_S.gguf new file mode 100644 index 0000000..c14ad33 --- /dev/null +++ b/LLaMA-3.1-8B-Instruct-KW-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321cb2e24836e19da3dd9a7783c6fcd523bcb75b3ae4f0b263018f313fde3179 +size 5599294400 diff --git a/LLaMA-3.1-8B-Instruct-KW-v2.Q6_K.gguf b/LLaMA-3.1-8B-Instruct-KW-v2.Q6_K.gguf new file mode 100644 index 0000000..d961dbb --- /dev/null +++ b/LLaMA-3.1-8B-Instruct-KW-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5013a270261b798201bd3354556e45987f30216a3e3b72ef62bc45b4dd33d3c5 +size 6596006848 diff --git a/LLaMA-3.1-8B-Instruct-KW-v2.Q8_0.gguf b/LLaMA-3.1-8B-Instruct-KW-v2.Q8_0.gguf new file mode 100644 index 0000000..c0d24a5 --- /dev/null +++ b/LLaMA-3.1-8B-Instruct-KW-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df3f0a6f1020b1113c177ac3a8dc642ac98bfaa0c424d45d7750859ae1004795 +size 8540771264 diff --git a/LLaMA-3.1-8B-Instruct-KW-v2.f16.gguf b/LLaMA-3.1-8B-Instruct-KW-v2.f16.gguf new file mode 100644 index 0000000..03cb9f3 --- /dev/null +++ b/LLaMA-3.1-8B-Instruct-KW-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:758afccc159caec6b6222e05aba2d9762cdd280a8dc4d50612e1748a37d348bf +size 16068891584 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ed561ea --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: realaer/LLaMA-3.1-8B-Instruct-KW-v2 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +--- +## About + + + + + + +static quants of https://huggingface.co/realaer/LLaMA-3.1-8B-Instruct-KW-v2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LLaMA-3.1-8B-Instruct-KW-v2-GGUF).*** + +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-3.1-8B-Instruct-KW-v2-GGUF/resolve/main/LLaMA-3.1-8B-Instruct-KW-v2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Instruct-KW-v2-GGUF/resolve/main/LLaMA-3.1-8B-Instruct-KW-v2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Instruct-KW-v2-GGUF/resolve/main/LLaMA-3.1-8B-Instruct-KW-v2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Instruct-KW-v2-GGUF/resolve/main/LLaMA-3.1-8B-Instruct-KW-v2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Instruct-KW-v2-GGUF/resolve/main/LLaMA-3.1-8B-Instruct-KW-v2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Instruct-KW-v2-GGUF/resolve/main/LLaMA-3.1-8B-Instruct-KW-v2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Instruct-KW-v2-GGUF/resolve/main/LLaMA-3.1-8B-Instruct-KW-v2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Instruct-KW-v2-GGUF/resolve/main/LLaMA-3.1-8B-Instruct-KW-v2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Instruct-KW-v2-GGUF/resolve/main/LLaMA-3.1-8B-Instruct-KW-v2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Instruct-KW-v2-GGUF/resolve/main/LLaMA-3.1-8B-Instruct-KW-v2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Instruct-KW-v2-GGUF/resolve/main/LLaMA-3.1-8B-Instruct-KW-v2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Instruct-KW-v2-GGUF/resolve/main/LLaMA-3.1-8B-Instruct-KW-v2.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. + +