commit d26acbfd26a13a0508a0077c263e68e4ee3d8b1b Author: ModelHub XC Date: Sat Oct 17 03:46:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1-8B-Sonnet-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..21b6f33 --- /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 +Llama3.1-8B-Sonnet.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Sonnet.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Sonnet.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Sonnet.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Sonnet.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Sonnet.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Sonnet.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Sonnet.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Sonnet.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Sonnet.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Sonnet.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Sonnet.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1-8B-Sonnet.IQ4_XS.gguf b/Llama3.1-8B-Sonnet.IQ4_XS.gguf new file mode 100644 index 0000000..0b73d8d --- /dev/null +++ b/Llama3.1-8B-Sonnet.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e098346b67dc1071f83f442afe9c0a105f78b4672ac77b98a6434d29274a77e5 +size 4484365696 diff --git a/Llama3.1-8B-Sonnet.Q2_K.gguf b/Llama3.1-8B-Sonnet.Q2_K.gguf new file mode 100644 index 0000000..a8563c1 --- /dev/null +++ b/Llama3.1-8B-Sonnet.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aa7306abf79205efb908e9529f28929209c6c97100f68f8df0e45e3118bc8a0 +size 3179134336 diff --git a/Llama3.1-8B-Sonnet.Q3_K_L.gguf b/Llama3.1-8B-Sonnet.Q3_K_L.gguf new file mode 100644 index 0000000..8699124 --- /dev/null +++ b/Llama3.1-8B-Sonnet.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:070e2945afd0ad3ed273e3594e7eee8397a3c521c23caa3babf8a5cfd671de9a +size 4321959296 diff --git a/Llama3.1-8B-Sonnet.Q3_K_M.gguf b/Llama3.1-8B-Sonnet.Q3_K_M.gguf new file mode 100644 index 0000000..42da017 --- /dev/null +++ b/Llama3.1-8B-Sonnet.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8ff30cb11a46beeb5ee43767b711cf3aa940859b0d5b02e909952637c99794d +size 4018920832 diff --git a/Llama3.1-8B-Sonnet.Q3_K_S.gguf b/Llama3.1-8B-Sonnet.Q3_K_S.gguf new file mode 100644 index 0000000..15b0c05 --- /dev/null +++ b/Llama3.1-8B-Sonnet.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ab6560d9341da10e013c641414ada674834094644b8551d8cf33dd15923ea80 +size 3664502144 diff --git a/Llama3.1-8B-Sonnet.Q4_K_M.gguf b/Llama3.1-8B-Sonnet.Q4_K_M.gguf new file mode 100644 index 0000000..7332e25 --- /dev/null +++ b/Llama3.1-8B-Sonnet.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43c12d420fd6bd842e5c8f42fd9dbd97fb48d6bf79ebb353c901232142962522 +size 4920737152 diff --git a/Llama3.1-8B-Sonnet.Q4_K_S.gguf b/Llama3.1-8B-Sonnet.Q4_K_S.gguf new file mode 100644 index 0000000..992e4fb --- /dev/null +++ b/Llama3.1-8B-Sonnet.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5745a26a1a83cd61ec6b9c01af504c26f6ca030cea160aa2bac3db016d8a9384 +size 4692671872 diff --git a/Llama3.1-8B-Sonnet.Q5_K_M.gguf b/Llama3.1-8B-Sonnet.Q5_K_M.gguf new file mode 100644 index 0000000..74d30bd --- /dev/null +++ b/Llama3.1-8B-Sonnet.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bbd6d769933593c8152e75216b608582448ca7690b2c854f67984d085184428 +size 5732990336 diff --git a/Llama3.1-8B-Sonnet.Q5_K_S.gguf b/Llama3.1-8B-Sonnet.Q5_K_S.gguf new file mode 100644 index 0000000..04919c4 --- /dev/null +++ b/Llama3.1-8B-Sonnet.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:643ad64b7dee96b92c3e214925d2f2692c493b297c5f06fa3ec9db14170beab3 +size 5599296896 diff --git a/Llama3.1-8B-Sonnet.Q6_K.gguf b/Llama3.1-8B-Sonnet.Q6_K.gguf new file mode 100644 index 0000000..5126325 --- /dev/null +++ b/Llama3.1-8B-Sonnet.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0cdeb83ba32c7247ebc7dbd9e988e52dadf62b5a720a3575fbacc1b0ae5559e +size 6596009344 diff --git a/Llama3.1-8B-Sonnet.Q8_0.gguf b/Llama3.1-8B-Sonnet.Q8_0.gguf new file mode 100644 index 0000000..06f7068 --- /dev/null +++ b/Llama3.1-8B-Sonnet.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa93d6365cadb31b6be30ca46004ae7d5ced40ab3121208a53fbeb62277d3980 +size 8540773760 diff --git a/Llama3.1-8B-Sonnet.f16.gguf b/Llama3.1-8B-Sonnet.f16.gguf new file mode 100644 index 0000000..34330ad --- /dev/null +++ b/Llama3.1-8B-Sonnet.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57426866410b172e671869c3aa6c8bdb342f2615e8c81b777aa69f3d6275b79e +size 16068894080 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d37e05c --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: ayan4m1/Llama3.1-8B-Sonnet +datasets: +- mlfoundations-dev/oh-dcft-v3.1-claude-3-5-sonnet-20241022 +- Gryphe/Sonnet3.5-SlimOrcaDedupCleaned +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- llama3.1 +- sonnet +- claude +--- +## About + + + + + + +static quants of https://huggingface.co/ayan4m1/Llama3.1-8B-Sonnet + + +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/Llama3.1-8B-Sonnet-GGUF/resolve/main/Llama3.1-8B-Sonnet.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Sonnet-GGUF/resolve/main/Llama3.1-8B-Sonnet.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Sonnet-GGUF/resolve/main/Llama3.1-8B-Sonnet.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Sonnet-GGUF/resolve/main/Llama3.1-8B-Sonnet.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Sonnet-GGUF/resolve/main/Llama3.1-8B-Sonnet.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Sonnet-GGUF/resolve/main/Llama3.1-8B-Sonnet.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Sonnet-GGUF/resolve/main/Llama3.1-8B-Sonnet.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Sonnet-GGUF/resolve/main/Llama3.1-8B-Sonnet.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Sonnet-GGUF/resolve/main/Llama3.1-8B-Sonnet.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Sonnet-GGUF/resolve/main/Llama3.1-8B-Sonnet.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Sonnet-GGUF/resolve/main/Llama3.1-8B-Sonnet.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Sonnet-GGUF/resolve/main/Llama3.1-8B-Sonnet.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. + +