commit 6d901b6e5d748e6d11aafd58ae2e43da017c6f5b Author: ModelHub XC Date: Tue Oct 6 20:43:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLAMA3.1-8b-Counsel-v1.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f7ae227 --- /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-v1.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLAMA3.1-8b-Counsel-v1.1.IQ4_XS.gguf b/LLAMA3.1-8b-Counsel-v1.1.IQ4_XS.gguf new file mode 100644 index 0000000..5d95caf --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d1abae0e6cd2c0af7ad76a0a4a21d7cac14a29f7784b47b8ddea519fc7eabed +size 4484364576 diff --git a/LLAMA3.1-8b-Counsel-v1.1.Q2_K.gguf b/LLAMA3.1-8b-Counsel-v1.1.Q2_K.gguf new file mode 100644 index 0000000..f750aa9 --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59d946188e4809c4e4bc9c550ac3d98367b9f924e5ed970156ac82739301e393 +size 3179133216 diff --git a/LLAMA3.1-8b-Counsel-v1.1.Q3_K_L.gguf b/LLAMA3.1-8b-Counsel-v1.1.Q3_K_L.gguf new file mode 100644 index 0000000..c899ede --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e0ae1b46547a042312a35d46d7fd163e22f3ab291c9e941c55c55d5acd3bd2d +size 4321958176 diff --git a/LLAMA3.1-8b-Counsel-v1.1.Q3_K_M.gguf b/LLAMA3.1-8b-Counsel-v1.1.Q3_K_M.gguf new file mode 100644 index 0000000..431a4da --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1a05e97f7c5d213e9c2d906c3c8a140dacb548827ec86735589c812fa340b89 +size 4018919712 diff --git a/LLAMA3.1-8b-Counsel-v1.1.Q3_K_S.gguf b/LLAMA3.1-8b-Counsel-v1.1.Q3_K_S.gguf new file mode 100644 index 0000000..0d0b5d3 --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d576ba1553b65136cf903a3ea93cc6c40fed9060e0e5bda34d7464d5834a700 +size 3664501024 diff --git a/LLAMA3.1-8b-Counsel-v1.1.Q4_K_M.gguf b/LLAMA3.1-8b-Counsel-v1.1.Q4_K_M.gguf new file mode 100644 index 0000000..2f7bda5 --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cac1b4df60b1101aa3b27248fee51634df6aa920bbe0a63b51593c87ab4cc8b9 +size 4920736032 diff --git a/LLAMA3.1-8b-Counsel-v1.1.Q4_K_S.gguf b/LLAMA3.1-8b-Counsel-v1.1.Q4_K_S.gguf new file mode 100644 index 0000000..387aa4c --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:683fbf7761c2595fed23c0ef1dac60e8444b38b295edbfe65980308c01f22668 +size 4692670752 diff --git a/LLAMA3.1-8b-Counsel-v1.1.Q5_K_M.gguf b/LLAMA3.1-8b-Counsel-v1.1.Q5_K_M.gguf new file mode 100644 index 0000000..d1574ca --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b70c48e55b0fe2eff6d80dcfe2af33c30ee9f0d2fcfba638b8d8c8b7b5363547 +size 5732989216 diff --git a/LLAMA3.1-8b-Counsel-v1.1.Q5_K_S.gguf b/LLAMA3.1-8b-Counsel-v1.1.Q5_K_S.gguf new file mode 100644 index 0000000..37dedb8 --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a2573b69629eed410aa7bfe202bd2eaa53ec04db1b83e19310915c98e280891 +size 5599295776 diff --git a/LLAMA3.1-8b-Counsel-v1.1.Q6_K.gguf b/LLAMA3.1-8b-Counsel-v1.1.Q6_K.gguf new file mode 100644 index 0000000..46b3dd7 --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f298414af6d20139284703f200925abb849f9038fef2e5337d2627e74226185c +size 6596008224 diff --git a/LLAMA3.1-8b-Counsel-v1.1.Q8_0.gguf b/LLAMA3.1-8b-Counsel-v1.1.Q8_0.gguf new file mode 100644 index 0000000..5be1465 --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85360f2dc413f4f042e5a98b735aeef7728e9cc92cba321526e17f9038c618b4 +size 8540772640 diff --git a/LLAMA3.1-8b-Counsel-v1.1.f16.gguf b/LLAMA3.1-8b-Counsel-v1.1.f16.gguf new file mode 100644 index 0000000..48ab327 --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6166483947fa8ce51e4a7fe795ea41328524c7f03e220476329929becbc77bac +size 16068892960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..17761e8 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: Mekuu/LLAMA3.1-8b-Counsel-v1.1 +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-v1.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LLAMA3.1-8b-Counsel-v1.1-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-v1.1-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.1-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.1-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.1-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.1-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.1-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.1-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.1-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.1-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.1-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.1-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.1-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.1.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. + +