commit 84dfeb8b5e276da6bc995676ad57232479bd8ca1 Author: ModelHub XC Date: Sun Jul 19 07:33:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ADG-CoT-LLaMa3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2f599c0 --- /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 +ADG-CoT-LLaMa3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ADG-CoT-LLaMa3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +ADG-CoT-LLaMa3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ADG-CoT-LLaMa3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ADG-CoT-LLaMa3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ADG-CoT-LLaMa3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ADG-CoT-LLaMa3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ADG-CoT-LLaMa3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ADG-CoT-LLaMa3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ADG-CoT-LLaMa3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ADG-CoT-LLaMa3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ADG-CoT-LLaMa3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ADG-CoT-LLaMa3-8B.IQ4_XS.gguf b/ADG-CoT-LLaMa3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..103342e --- /dev/null +++ b/ADG-CoT-LLaMa3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49d67743ec73158b65b6e0012a68ec54c68bde0062673d85db1cb555a90a698d +size 4484363424 diff --git a/ADG-CoT-LLaMa3-8B.Q2_K.gguf b/ADG-CoT-LLaMa3-8B.Q2_K.gguf new file mode 100644 index 0000000..c3e64c3 --- /dev/null +++ b/ADG-CoT-LLaMa3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcb61e2e8ab877b1c742c4b3e4f529ac69c9f1311c642d59fac1135872c4b802 +size 3179132064 diff --git a/ADG-CoT-LLaMa3-8B.Q3_K_L.gguf b/ADG-CoT-LLaMa3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..7861ba0 --- /dev/null +++ b/ADG-CoT-LLaMa3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf9244aba348c9047a25af8af817b8add4d906db24728136f703a3edd105188c +size 4321957024 diff --git a/ADG-CoT-LLaMa3-8B.Q3_K_M.gguf b/ADG-CoT-LLaMa3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..b92a914 --- /dev/null +++ b/ADG-CoT-LLaMa3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91c3692687745b394ebb281643646987ce5e893089d61a3d92f99787f61b7f11 +size 4018918560 diff --git a/ADG-CoT-LLaMa3-8B.Q3_K_S.gguf b/ADG-CoT-LLaMa3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..eaecc2d --- /dev/null +++ b/ADG-CoT-LLaMa3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:757a4b6cf074ad6707b3479e8bd0bcf86ce0c5e1b2e9c56d0d559d629f855760 +size 3664499872 diff --git a/ADG-CoT-LLaMa3-8B.Q4_K_M.gguf b/ADG-CoT-LLaMa3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..a650a1a --- /dev/null +++ b/ADG-CoT-LLaMa3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4ea53d6ba2a725c8b624040935c2c6abd148ebf032da7c79157bfaf70ace7e7 +size 4920734880 diff --git a/ADG-CoT-LLaMa3-8B.Q4_K_S.gguf b/ADG-CoT-LLaMa3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..3252fdc --- /dev/null +++ b/ADG-CoT-LLaMa3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f525031babecd48fbf6ebf5d87dda8bffbc49905c279192aa65775d1968dce5 +size 4692669600 diff --git a/ADG-CoT-LLaMa3-8B.Q5_K_M.gguf b/ADG-CoT-LLaMa3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..402c177 --- /dev/null +++ b/ADG-CoT-LLaMa3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:873cbe3c9c38c5df12811ccd625ade7383b5b13621c7d4dc5244ba1732432116 +size 5732988064 diff --git a/ADG-CoT-LLaMa3-8B.Q5_K_S.gguf b/ADG-CoT-LLaMa3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..1553793 --- /dev/null +++ b/ADG-CoT-LLaMa3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:395e23b1d51b43bfe8de8d4fa261cc0a0f6c8fde3a6d690562582129ac18f092 +size 5599294624 diff --git a/ADG-CoT-LLaMa3-8B.Q6_K.gguf b/ADG-CoT-LLaMa3-8B.Q6_K.gguf new file mode 100644 index 0000000..ae22402 --- /dev/null +++ b/ADG-CoT-LLaMa3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e88417616224b351878f3273716c5ef0c4b78a6ff4e519190382f981796625d0 +size 6596007072 diff --git a/ADG-CoT-LLaMa3-8B.Q8_0.gguf b/ADG-CoT-LLaMa3-8B.Q8_0.gguf new file mode 100644 index 0000000..9eba058 --- /dev/null +++ b/ADG-CoT-LLaMa3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9ef78d8fe936c845013990a8234e66f9a534c81986cfb5a2ef58bb6362f2b6c +size 8540771488 diff --git a/ADG-CoT-LLaMa3-8B.f16.gguf b/ADG-CoT-LLaMa3-8B.f16.gguf new file mode 100644 index 0000000..74df593 --- /dev/null +++ b/ADG-CoT-LLaMa3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbb13b6c97b838fe984ade80966ac17daef8c7362cd592418edba01eebeec85f +size 16068891808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..da895ae --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: WisdomShell/ADG-CoT-LLaMa3-8B +language: +- zh +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- ADG +- SFT +--- +## About + + + + + + + + + +static quants of https://huggingface.co/WisdomShell/ADG-CoT-LLaMa3-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ADG-CoT-LLaMa3-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/ADG-CoT-LLaMa3-8B-i1-GGUF +## 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/ADG-CoT-LLaMa3-8B-GGUF/resolve/main/ADG-CoT-LLaMa3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ADG-CoT-LLaMa3-8B-GGUF/resolve/main/ADG-CoT-LLaMa3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ADG-CoT-LLaMa3-8B-GGUF/resolve/main/ADG-CoT-LLaMa3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ADG-CoT-LLaMa3-8B-GGUF/resolve/main/ADG-CoT-LLaMa3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ADG-CoT-LLaMa3-8B-GGUF/resolve/main/ADG-CoT-LLaMa3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/ADG-CoT-LLaMa3-8B-GGUF/resolve/main/ADG-CoT-LLaMa3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ADG-CoT-LLaMa3-8B-GGUF/resolve/main/ADG-CoT-LLaMa3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ADG-CoT-LLaMa3-8B-GGUF/resolve/main/ADG-CoT-LLaMa3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ADG-CoT-LLaMa3-8B-GGUF/resolve/main/ADG-CoT-LLaMa3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ADG-CoT-LLaMa3-8B-GGUF/resolve/main/ADG-CoT-LLaMa3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ADG-CoT-LLaMa3-8B-GGUF/resolve/main/ADG-CoT-LLaMa3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ADG-CoT-LLaMa3-8B-GGUF/resolve/main/ADG-CoT-LLaMa3-8B.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. + +