commit fe0f5d840a89b3682ce7740d548143b3f8eeb7c3 Author: ModelHub XC Date: Fri Aug 7 03:13:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLAMA3.1-8b-Counsel-v1.3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fc81d7a --- /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-Counsel-v1.3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.3.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLAMA3.1-8b-Counsel-v1.3.IQ4_XS.gguf b/LLAMA3.1-8b-Counsel-v1.3.IQ4_XS.gguf new file mode 100644 index 0000000..f0d9dfe --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:644d2da34d9e3a28fb611c570eee7026a6404b510ab2fb4c1ac7b65efb7b440b +size 4484364576 diff --git a/LLAMA3.1-8b-Counsel-v1.3.Q2_K.gguf b/LLAMA3.1-8b-Counsel-v1.3.Q2_K.gguf new file mode 100644 index 0000000..4ac45fe --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:085101f2ce1908d8c8263240c6ca127fd3c6903cf82a58d8eb239a318f4f0ea3 +size 3179133216 diff --git a/LLAMA3.1-8b-Counsel-v1.3.Q3_K_L.gguf b/LLAMA3.1-8b-Counsel-v1.3.Q3_K_L.gguf new file mode 100644 index 0000000..098d115 --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf96234d04ad6f915680b08d57dd0add1496ccd617a9d0996bd471a09b85bc05 +size 4321958176 diff --git a/LLAMA3.1-8b-Counsel-v1.3.Q3_K_M.gguf b/LLAMA3.1-8b-Counsel-v1.3.Q3_K_M.gguf new file mode 100644 index 0000000..29d664f --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57cbd8b3d2984156f3ab0d592a80a77380f3e961ebfdb646ebe4392c8bcb373c +size 4018919712 diff --git a/LLAMA3.1-8b-Counsel-v1.3.Q3_K_S.gguf b/LLAMA3.1-8b-Counsel-v1.3.Q3_K_S.gguf new file mode 100644 index 0000000..1686435 --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6719a9f9b900184ebf16d4bc5dfb1b6a9643a26e814604661c30258ec9c04f79 +size 3664501024 diff --git a/LLAMA3.1-8b-Counsel-v1.3.Q4_K_M.gguf b/LLAMA3.1-8b-Counsel-v1.3.Q4_K_M.gguf new file mode 100644 index 0000000..2ce7589 --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5fa5006ba56ab2b2595d4dbd3935e7a471c109a0fbecc1af51c06e94ac2fc9a +size 4920736032 diff --git a/LLAMA3.1-8b-Counsel-v1.3.Q4_K_S.gguf b/LLAMA3.1-8b-Counsel-v1.3.Q4_K_S.gguf new file mode 100644 index 0000000..90d831a --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee0fae899eba30fec6550d6ddefe6b51193cdcd06b5bda68090642d508422a73 +size 4692670752 diff --git a/LLAMA3.1-8b-Counsel-v1.3.Q5_K_M.gguf b/LLAMA3.1-8b-Counsel-v1.3.Q5_K_M.gguf new file mode 100644 index 0000000..b39890f --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd19cdc32b20047b7c011b800693b0c12bba3ce15ee34be60091f97949c39dd0 +size 5732989216 diff --git a/LLAMA3.1-8b-Counsel-v1.3.Q5_K_S.gguf b/LLAMA3.1-8b-Counsel-v1.3.Q5_K_S.gguf new file mode 100644 index 0000000..d526971 --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31cbcf6fc4d95b2a877045a30a414d5349e8b326733495668c68ee2133958103 +size 5599295776 diff --git a/LLAMA3.1-8b-Counsel-v1.3.Q6_K.gguf b/LLAMA3.1-8b-Counsel-v1.3.Q6_K.gguf new file mode 100644 index 0000000..dd26560 --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c076a2dcf7a76fd8354ded2366a9ef219e76c02400cf9abdb3b6e833e16da95 +size 6596008224 diff --git a/LLAMA3.1-8b-Counsel-v1.3.Q8_0.gguf b/LLAMA3.1-8b-Counsel-v1.3.Q8_0.gguf new file mode 100644 index 0000000..01c261f --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4ba52f3196f6e3379ae1e91478d177a6506b7c69f4735b06efb42cf5961173e +size 8540772640 diff --git a/LLAMA3.1-8b-Counsel-v1.3.f16.gguf b/LLAMA3.1-8b-Counsel-v1.3.f16.gguf new file mode 100644 index 0000000..3786968 --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:348397611eb1b2352d43e6f73c7681d7c10828759f25c15e96804ff2948954a5 +size 16068892960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f04a2a2 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: Mekuu/LLAMA3.1-8b-Counsel-v1.3 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/Mekuu/LLAMA3.1-8b-Counsel-v1.3 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LLAMA3.1-8b-Counsel-v1.3-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/LLAMA3.1-8b-Counsel-v1.3-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.3.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.3-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.3.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.3-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.3.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.3-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.3.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.3-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.3.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.3-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.3.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.3-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.3.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.3-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.3.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.3-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.3.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.3-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.3.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.3-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.3.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.3-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.3.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. + +