commit 00ee19941c76f8e68b167f28632343819e156f61 Author: ModelHub XC Date: Sat Sep 26 07:37:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLAMA3.1-8b-Counsel-v1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..36d5cbe --- /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-v1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3.1-8b-Counsel-v1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLAMA3.1-8b-Counsel-v1.0.IQ4_XS.gguf b/LLAMA3.1-8b-Counsel-v1.0.IQ4_XS.gguf new file mode 100644 index 0000000..8f3ae0d --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9b7e455873626765b6869bf37317e97818bff19faf9c603ff3125bf9045e9f0 +size 4484368384 diff --git a/LLAMA3.1-8b-Counsel-v1.0.Q2_K.gguf b/LLAMA3.1-8b-Counsel-v1.0.Q2_K.gguf new file mode 100644 index 0000000..c318eb5 --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e354bb099409707ce906646ee2da0bacac31fbcc88a758206142834acd1087a4 +size 3179137024 diff --git a/LLAMA3.1-8b-Counsel-v1.0.Q3_K_L.gguf b/LLAMA3.1-8b-Counsel-v1.0.Q3_K_L.gguf new file mode 100644 index 0000000..7984be0 --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3727c2ca347686df00eb2878087e2a6798c7cc2e7796e8de4ac14fbe0d3cbb24 +size 4321961984 diff --git a/LLAMA3.1-8b-Counsel-v1.0.Q3_K_M.gguf b/LLAMA3.1-8b-Counsel-v1.0.Q3_K_M.gguf new file mode 100644 index 0000000..4f98a88 --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0347a44a40ae914733398ea2f8465c4af7c7779cbf446750613f4d4b71f1116 +size 4018923520 diff --git a/LLAMA3.1-8b-Counsel-v1.0.Q3_K_S.gguf b/LLAMA3.1-8b-Counsel-v1.0.Q3_K_S.gguf new file mode 100644 index 0000000..3f2626f --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0b8d00778da423429253704939d0ed59064da224d909d06737e3596cd182e01 +size 3664504832 diff --git a/LLAMA3.1-8b-Counsel-v1.0.Q4_K_M.gguf b/LLAMA3.1-8b-Counsel-v1.0.Q4_K_M.gguf new file mode 100644 index 0000000..ddec45d --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97089c35f08fc3c3ef44aab9e3263ad2c9bdffdee8144c8216639c6387f90a57 +size 4920739840 diff --git a/LLAMA3.1-8b-Counsel-v1.0.Q4_K_S.gguf b/LLAMA3.1-8b-Counsel-v1.0.Q4_K_S.gguf new file mode 100644 index 0000000..30d1a8f --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a06bd5658732f2b7f8592893e9d3ed0b3e5e7d429d2c50b5ef8a00764efa134a +size 4692674560 diff --git a/LLAMA3.1-8b-Counsel-v1.0.Q5_K_M.gguf b/LLAMA3.1-8b-Counsel-v1.0.Q5_K_M.gguf new file mode 100644 index 0000000..aa19df1 --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cc558d92c3e3976681d45942854134bc67fecb59334b528e6c5caa5e14ad1d7 +size 5732993024 diff --git a/LLAMA3.1-8b-Counsel-v1.0.Q5_K_S.gguf b/LLAMA3.1-8b-Counsel-v1.0.Q5_K_S.gguf new file mode 100644 index 0000000..87f831a --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6175c2b521c7906864f932e8aa30602dd78efb90b2199e99c5ca9d92fb9bea16 +size 5599299584 diff --git a/LLAMA3.1-8b-Counsel-v1.0.Q6_K.gguf b/LLAMA3.1-8b-Counsel-v1.0.Q6_K.gguf new file mode 100644 index 0000000..f49e818 --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b4bfbaee563403be2d292ceb8df5dcf532d9f4aedd0f6c40516ad80f952561d +size 6596012032 diff --git a/LLAMA3.1-8b-Counsel-v1.0.Q8_0.gguf b/LLAMA3.1-8b-Counsel-v1.0.Q8_0.gguf new file mode 100644 index 0000000..75d7b61 --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31b94004a49882435813a7e2ee91ad8d582062edc77476b771696808095fd654 +size 8540776448 diff --git a/LLAMA3.1-8b-Counsel-v1.0.f16.gguf b/LLAMA3.1-8b-Counsel-v1.0.f16.gguf new file mode 100644 index 0000000..0eb066d --- /dev/null +++ b/LLAMA3.1-8b-Counsel-v1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2db72984781d41fb6207ae061cdd51a8fc910d727577cffd64209f5868a700ee +size 16068896768 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b818389 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: Mekuu/LLAMA3.1-8b-Counsel-v1.0 +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-v1.0 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LLAMA3.1-8b-Counsel-v1.0-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-v1.0-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.0.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.0-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.0.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.0-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.0.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.0-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.0.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.0-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.0.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.0-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.0.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.0-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.0.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.0-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.0.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.0-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.0.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.0-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.0.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.0-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.0.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3.1-8b-Counsel-v1.0-GGUF/resolve/main/LLAMA3.1-8b-Counsel-v1.0.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. + +