commit 38b923d8496300e7b35c024078b8accf7b3d03ee Author: ModelHub XC Date: Fri Jul 10 21:22:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLMTwin-Llama-3.1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8d4b737 --- /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 +LLMTwin-Llama-3.1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLMTwin-Llama-3.1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLMTwin-Llama-3.1-8B.IQ4_XS.gguf b/LLMTwin-Llama-3.1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..f9b32a3 --- /dev/null +++ b/LLMTwin-Llama-3.1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a99b22e5539eeec51f15e8fccdf32ebcedf687de8ebb7fdf60c70da259aa00c3 +size 4484363936 diff --git a/LLMTwin-Llama-3.1-8B.Q2_K.gguf b/LLMTwin-Llama-3.1-8B.Q2_K.gguf new file mode 100644 index 0000000..4307b6c --- /dev/null +++ b/LLMTwin-Llama-3.1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2943096b9df0af7f165de3782d2875ddfa9c4e3adb5a82ce0295714059bb8ba5 +size 3179132576 diff --git a/LLMTwin-Llama-3.1-8B.Q3_K_L.gguf b/LLMTwin-Llama-3.1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..489a0d2 --- /dev/null +++ b/LLMTwin-Llama-3.1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52a1e56d66cae43914155969ca49eb0fc20fb04e2ab1912a23e60bdb0e7de4e7 +size 4321957536 diff --git a/LLMTwin-Llama-3.1-8B.Q3_K_M.gguf b/LLMTwin-Llama-3.1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..0caaaf1 --- /dev/null +++ b/LLMTwin-Llama-3.1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e09ea2b3c52280468453105be5a7f052372ba2da7a0fe54e93e9fb9d0c17796 +size 4018919072 diff --git a/LLMTwin-Llama-3.1-8B.Q3_K_S.gguf b/LLMTwin-Llama-3.1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..8969c43 --- /dev/null +++ b/LLMTwin-Llama-3.1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1ccc3f87d9ada968194411e15915cdee42f947bf2b3de821f3f6e578282a2ce +size 3664500384 diff --git a/LLMTwin-Llama-3.1-8B.Q4_K_M.gguf b/LLMTwin-Llama-3.1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..9ec0469 --- /dev/null +++ b/LLMTwin-Llama-3.1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:209baeb9d7aee753227851b3e7dcb3d088796c0234586ea6db7d068dcc1b6ed3 +size 4920735392 diff --git a/LLMTwin-Llama-3.1-8B.Q4_K_S.gguf b/LLMTwin-Llama-3.1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..32493fa --- /dev/null +++ b/LLMTwin-Llama-3.1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04f5dc0212ac0ab8f835d83c91a93a0f5b3597e80b281dbc57bddfd97766e3b3 +size 4692670112 diff --git a/LLMTwin-Llama-3.1-8B.Q5_K_M.gguf b/LLMTwin-Llama-3.1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..6276945 --- /dev/null +++ b/LLMTwin-Llama-3.1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9560062e688bbe1bf460e096b937642e8ac5ae3d058634d157f587ed5966cf2 +size 5732988576 diff --git a/LLMTwin-Llama-3.1-8B.Q5_K_S.gguf b/LLMTwin-Llama-3.1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..4f3cb08 --- /dev/null +++ b/LLMTwin-Llama-3.1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4caa80c089bf2905f6066210595c0507fc53353ff100091fa29ddbb56760fff +size 5599295136 diff --git a/LLMTwin-Llama-3.1-8B.Q6_K.gguf b/LLMTwin-Llama-3.1-8B.Q6_K.gguf new file mode 100644 index 0000000..53b0971 --- /dev/null +++ b/LLMTwin-Llama-3.1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abaf33c375660c7c8381e8ccc12d79500053062bedd48025d93fcf21e52eb6e9 +size 6596007584 diff --git a/LLMTwin-Llama-3.1-8B.Q8_0.gguf b/LLMTwin-Llama-3.1-8B.Q8_0.gguf new file mode 100644 index 0000000..f0da962 --- /dev/null +++ b/LLMTwin-Llama-3.1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce9a02b4e412fc5f2f43dc27fe7d921cbf89edca7570f1587276c798ccc5964a +size 8540772000 diff --git a/LLMTwin-Llama-3.1-8B.f16.gguf b/LLMTwin-Llama-3.1-8B.f16.gguf new file mode 100644 index 0000000..8e8c845 --- /dev/null +++ b/LLMTwin-Llama-3.1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f78d463d60bd3068c8339042f4d63f459a361212e3bcce2004bdb1f891f2f38 +size 16068892320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..310fe5c --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: ArthurSrz/LLMTwin-Llama-3.1-8B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/ArthurSrz/LLMTwin-Llama-3.1-8B + + +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/LLMTwin-Llama-3.1-8B-GGUF/resolve/main/LLMTwin-Llama-3.1-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.1-8B-GGUF/resolve/main/LLMTwin-Llama-3.1-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.1-8B-GGUF/resolve/main/LLMTwin-Llama-3.1-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.1-8B-GGUF/resolve/main/LLMTwin-Llama-3.1-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.1-8B-GGUF/resolve/main/LLMTwin-Llama-3.1-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.1-8B-GGUF/resolve/main/LLMTwin-Llama-3.1-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.1-8B-GGUF/resolve/main/LLMTwin-Llama-3.1-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.1-8B-GGUF/resolve/main/LLMTwin-Llama-3.1-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.1-8B-GGUF/resolve/main/LLMTwin-Llama-3.1-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.1-8B-GGUF/resolve/main/LLMTwin-Llama-3.1-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.1-8B-GGUF/resolve/main/LLMTwin-Llama-3.1-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLMTwin-Llama-3.1-8B-GGUF/resolve/main/LLMTwin-Llama-3.1-8B.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. + +