commit 5e906610568d780496a4ebe5ffba3090a01844da Author: ModelHub XC Date: Fri Jun 26 22:30:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLMBG-Llama-3.1-8B-BG-Reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4dc0181 --- /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 +LLMBG-Llama-3.1-8B-BG-Reasoning.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLMBG-Llama-3.1-8B-BG-Reasoning.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLMBG-Llama-3.1-8B-BG-Reasoning.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLMBG-Llama-3.1-8B-BG-Reasoning.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLMBG-Llama-3.1-8B-BG-Reasoning.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLMBG-Llama-3.1-8B-BG-Reasoning.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLMBG-Llama-3.1-8B-BG-Reasoning.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLMBG-Llama-3.1-8B-BG-Reasoning.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLMBG-Llama-3.1-8B-BG-Reasoning.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLMBG-Llama-3.1-8B-BG-Reasoning.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLMBG-Llama-3.1-8B-BG-Reasoning.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLMBG-Llama-3.1-8B-BG-Reasoning.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLMBG-Llama-3.1-8B-BG-Reasoning.IQ4_XS.gguf b/LLMBG-Llama-3.1-8B-BG-Reasoning.IQ4_XS.gguf new file mode 100644 index 0000000..e6b2a0a --- /dev/null +++ b/LLMBG-Llama-3.1-8B-BG-Reasoning.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42b402cfb93ea6b14021d9692bf8f11476737a6c7ab1d887ed4abfdfd12edace +size 4484368320 diff --git a/LLMBG-Llama-3.1-8B-BG-Reasoning.Q2_K.gguf b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q2_K.gguf new file mode 100644 index 0000000..4b3d145 --- /dev/null +++ b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5741829e440d3442513de5aa13523c09be53a7a61ef01af1c76396b8e6f0496a +size 3179136960 diff --git a/LLMBG-Llama-3.1-8B-BG-Reasoning.Q3_K_L.gguf b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q3_K_L.gguf new file mode 100644 index 0000000..ffa52e1 --- /dev/null +++ b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a0e267fb24b2ffbd2acdf08c437db680ffad35c8ec4d6b3a5df4cd88cacac94 +size 4321961920 diff --git a/LLMBG-Llama-3.1-8B-BG-Reasoning.Q3_K_M.gguf b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q3_K_M.gguf new file mode 100644 index 0000000..e0b9970 --- /dev/null +++ b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00ab621ea0bd2d97683ff3a5d703de510ad9a7787effd41298cc04c8fe1f65af +size 4018923456 diff --git a/LLMBG-Llama-3.1-8B-BG-Reasoning.Q3_K_S.gguf b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q3_K_S.gguf new file mode 100644 index 0000000..95c8c2e --- /dev/null +++ b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6dac3f5511a70db85170145c01ea26c4105d8fa2ac34614093d40ae73e4d9f6 +size 3664504768 diff --git a/LLMBG-Llama-3.1-8B-BG-Reasoning.Q4_K_M.gguf b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q4_K_M.gguf new file mode 100644 index 0000000..707f275 --- /dev/null +++ b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fd9bff00d349ef10fc048bbc6aa8a9fe358fc76d76bb32b3fe516c6cca78b3d +size 4920739776 diff --git a/LLMBG-Llama-3.1-8B-BG-Reasoning.Q4_K_S.gguf b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q4_K_S.gguf new file mode 100644 index 0000000..5762c22 --- /dev/null +++ b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9427bb2801794ee019f7bb2657ab2e42e41b907cf4c3271fbbdcdfc4723b1a8 +size 4692674496 diff --git a/LLMBG-Llama-3.1-8B-BG-Reasoning.Q5_K_M.gguf b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q5_K_M.gguf new file mode 100644 index 0000000..3f69e88 --- /dev/null +++ b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5c7a74d7f2886ebf807875c8f37b3073daf08d9af4a5c385ed407addd65a79a +size 5732992960 diff --git a/LLMBG-Llama-3.1-8B-BG-Reasoning.Q5_K_S.gguf b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q5_K_S.gguf new file mode 100644 index 0000000..040870d --- /dev/null +++ b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3d5a8db8fccd155eb2e3763171b7363a18555f53ee60da9b12cbe3b04ce5e7b +size 5599299520 diff --git a/LLMBG-Llama-3.1-8B-BG-Reasoning.Q6_K.gguf b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q6_K.gguf new file mode 100644 index 0000000..f852f56 --- /dev/null +++ b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0c4ff32475714276ae9ff63b376e9429f1a0fbf6b151deb785b4ea78a533250 +size 6596011968 diff --git a/LLMBG-Llama-3.1-8B-BG-Reasoning.Q8_0.gguf b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q8_0.gguf new file mode 100644 index 0000000..69fe4e7 --- /dev/null +++ b/LLMBG-Llama-3.1-8B-BG-Reasoning.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcac65d8aaffec4aa402101d4c1f9ba9e0fceecd7c204f785e0b595257b5f987 +size 8540776384 diff --git a/LLMBG-Llama-3.1-8B-BG-Reasoning.f16.gguf b/LLMBG-Llama-3.1-8B-BG-Reasoning.f16.gguf new file mode 100644 index 0000000..cc294a5 --- /dev/null +++ b/LLMBG-Llama-3.1-8B-BG-Reasoning.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:105ba482fc715a64f51b65a9c3745900534580d5165b497c78fcd9f3541340f5 +size 16068896704 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f1cfa2a --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: s-emanuilov/LLMBG-Llama-3.1-8B-BG-Reasoning-v0.1 +language: +- bg +library_name: transformers +license: cc-by-4.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/s-emanuilov/LLMBG-Llama-3.1-8B-BG-Reasoning-v0.1 + + +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/LLMBG-Llama-3.1-8B-BG-Reasoning-GGUF/resolve/main/LLMBG-Llama-3.1-8B-BG-Reasoning.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLMBG-Llama-3.1-8B-BG-Reasoning-GGUF/resolve/main/LLMBG-Llama-3.1-8B-BG-Reasoning.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLMBG-Llama-3.1-8B-BG-Reasoning-GGUF/resolve/main/LLMBG-Llama-3.1-8B-BG-Reasoning.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLMBG-Llama-3.1-8B-BG-Reasoning-GGUF/resolve/main/LLMBG-Llama-3.1-8B-BG-Reasoning.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLMBG-Llama-3.1-8B-BG-Reasoning-GGUF/resolve/main/LLMBG-Llama-3.1-8B-BG-Reasoning.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLMBG-Llama-3.1-8B-BG-Reasoning-GGUF/resolve/main/LLMBG-Llama-3.1-8B-BG-Reasoning.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLMBG-Llama-3.1-8B-BG-Reasoning-GGUF/resolve/main/LLMBG-Llama-3.1-8B-BG-Reasoning.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLMBG-Llama-3.1-8B-BG-Reasoning-GGUF/resolve/main/LLMBG-Llama-3.1-8B-BG-Reasoning.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLMBG-Llama-3.1-8B-BG-Reasoning-GGUF/resolve/main/LLMBG-Llama-3.1-8B-BG-Reasoning.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLMBG-Llama-3.1-8B-BG-Reasoning-GGUF/resolve/main/LLMBG-Llama-3.1-8B-BG-Reasoning.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLMBG-Llama-3.1-8B-BG-Reasoning-GGUF/resolve/main/LLMBG-Llama-3.1-8B-BG-Reasoning.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLMBG-Llama-3.1-8B-BG-Reasoning-GGUF/resolve/main/LLMBG-Llama-3.1-8B-BG-Reasoning.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. + +