commit bf6e746edba72a88d0ac1041e0e9de1fc35c116a Author: ModelHub XC Date: Wed Jun 24 12:41:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLM-3.1-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..32adf7c --- /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 +LLM-3.1-8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLM-3.1-8B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLM-3.1-8B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLM-3.1-8B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLM-3.1-8B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLM-3.1-8B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLM-3.1-8B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLM-3.1-8B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLM-3.1-8B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLM-3.1-8B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLM-3.1-8B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLM-3.1-8B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLM-3.1-8B-Instruct.IQ4_XS.gguf b/LLM-3.1-8B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..19541d5 --- /dev/null +++ b/LLM-3.1-8B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7692ac2a06122f85c262075d01033a2f400d2942f7adc79835af0549a1fe88a +size 4484367616 diff --git a/LLM-3.1-8B-Instruct.Q2_K.gguf b/LLM-3.1-8B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..2dfe2e7 --- /dev/null +++ b/LLM-3.1-8B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c192de980ce486e667f1e9141be822e75e1fda42597e6d788108d2d48e3315d +size 3179136256 diff --git a/LLM-3.1-8B-Instruct.Q3_K_L.gguf b/LLM-3.1-8B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..8e33c17 --- /dev/null +++ b/LLM-3.1-8B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:863e5f3c8d4bc1861bbdfefb15b6329d425c53aafc87fab85bfac0ffb1a8d050 +size 4321961216 diff --git a/LLM-3.1-8B-Instruct.Q3_K_M.gguf b/LLM-3.1-8B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..adc5327 --- /dev/null +++ b/LLM-3.1-8B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b15b8b4fa040b2490c4472b10d3c011482d56894e7b254cb22d760170d59463c +size 4018922752 diff --git a/LLM-3.1-8B-Instruct.Q3_K_S.gguf b/LLM-3.1-8B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..7d0cdef --- /dev/null +++ b/LLM-3.1-8B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1880384b4d4ae02d16a3d3cddef0d4300c6c884a7022e7b07510a23af0eef8a +size 3664504064 diff --git a/LLM-3.1-8B-Instruct.Q4_K_M.gguf b/LLM-3.1-8B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..1fd4c26 --- /dev/null +++ b/LLM-3.1-8B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61cc465efa873c11a953effb2b9c60ce00d1adf974436f1d321b0428c463f485 +size 4920739072 diff --git a/LLM-3.1-8B-Instruct.Q4_K_S.gguf b/LLM-3.1-8B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..dc76719 --- /dev/null +++ b/LLM-3.1-8B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d531738dc824c088295ba46bb3f46996bb71438ced75d1267abc50e7b3ca521 +size 4692673792 diff --git a/LLM-3.1-8B-Instruct.Q5_K_M.gguf b/LLM-3.1-8B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..5c7ea26 --- /dev/null +++ b/LLM-3.1-8B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc7a8d6f9205d9956424ce2d9b374ac4de7f5fd17a01efeb3cbfb5c1b09437eb +size 5732992256 diff --git a/LLM-3.1-8B-Instruct.Q5_K_S.gguf b/LLM-3.1-8B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..e41ca90 --- /dev/null +++ b/LLM-3.1-8B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c342972b366e60a1fc064f99a1f16c1144bb34e911854d644158d6200e7e218 +size 5599298816 diff --git a/LLM-3.1-8B-Instruct.Q6_K.gguf b/LLM-3.1-8B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..5d1a124 --- /dev/null +++ b/LLM-3.1-8B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0db412862bc8d49468c91d00b26788862b036529fdf727c7c7e55cb0410d7f2f +size 6596011264 diff --git a/LLM-3.1-8B-Instruct.Q8_0.gguf b/LLM-3.1-8B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..ccdf255 --- /dev/null +++ b/LLM-3.1-8B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:504801f9f67fb3b8e09f1fabe42cdda23b8428a66de47364b9d542e03d01b2d5 +size 8540775680 diff --git a/LLM-3.1-8B-Instruct.f16.gguf b/LLM-3.1-8B-Instruct.f16.gguf new file mode 100644 index 0000000..aef32c8 --- /dev/null +++ b/LLM-3.1-8B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39076f67583937c63d86128ce2540b7dcb804c8501ff1f81ca516b954bf101fd +size 16068896000 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ae39367 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: tommylam/LLM-3.1-8B-Instruct +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/tommylam/LLM-3.1-8B-Instruct + + +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/LLM-3.1-8B-Instruct-GGUF/resolve/main/LLM-3.1-8B-Instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLM-3.1-8B-Instruct-GGUF/resolve/main/LLM-3.1-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLM-3.1-8B-Instruct-GGUF/resolve/main/LLM-3.1-8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLM-3.1-8B-Instruct-GGUF/resolve/main/LLM-3.1-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLM-3.1-8B-Instruct-GGUF/resolve/main/LLM-3.1-8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLM-3.1-8B-Instruct-GGUF/resolve/main/LLM-3.1-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLM-3.1-8B-Instruct-GGUF/resolve/main/LLM-3.1-8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLM-3.1-8B-Instruct-GGUF/resolve/main/LLM-3.1-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLM-3.1-8B-Instruct-GGUF/resolve/main/LLM-3.1-8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLM-3.1-8B-Instruct-GGUF/resolve/main/LLM-3.1-8B-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLM-3.1-8B-Instruct-GGUF/resolve/main/LLM-3.1-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLM-3.1-8B-Instruct-GGUF/resolve/main/LLM-3.1-8B-Instruct.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. + +