commit ed39a89d0976ac2de9f7c6c7633c8f668ac97fcc Author: ModelHub XC Date: Tue Oct 20 11:42:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3_1-8b-Boost-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53ff367 --- /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 +llama-3_1-8b-Boost.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3_1-8b-Boost.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3_1-8b-Boost.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3_1-8b-Boost.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3_1-8b-Boost.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3_1-8b-Boost.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3_1-8b-Boost.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3_1-8b-Boost.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3_1-8b-Boost.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3_1-8b-Boost.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3_1-8b-Boost.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3_1-8b-Boost.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3a4c22d --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: golemsystems/llama-3_1-8b-Boost +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/golemsystems/llama-3_1-8b-Boost + + +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/llama-3_1-8b-Boost-GGUF/resolve/main/llama-3_1-8b-Boost.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3_1-8b-Boost-GGUF/resolve/main/llama-3_1-8b-Boost.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3_1-8b-Boost-GGUF/resolve/main/llama-3_1-8b-Boost.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3_1-8b-Boost-GGUF/resolve/main/llama-3_1-8b-Boost.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3_1-8b-Boost-GGUF/resolve/main/llama-3_1-8b-Boost.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3_1-8b-Boost-GGUF/resolve/main/llama-3_1-8b-Boost.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3_1-8b-Boost-GGUF/resolve/main/llama-3_1-8b-Boost.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3_1-8b-Boost-GGUF/resolve/main/llama-3_1-8b-Boost.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3_1-8b-Boost-GGUF/resolve/main/llama-3_1-8b-Boost.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3_1-8b-Boost-GGUF/resolve/main/llama-3_1-8b-Boost.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3_1-8b-Boost-GGUF/resolve/main/llama-3_1-8b-Boost.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3_1-8b-Boost-GGUF/resolve/main/llama-3_1-8b-Boost.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. + + diff --git a/llama-3_1-8b-Boost.IQ4_XS.gguf b/llama-3_1-8b-Boost.IQ4_XS.gguf new file mode 100644 index 0000000..a75f296 --- /dev/null +++ b/llama-3_1-8b-Boost.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebd086c45d1809d7d808ff29354ff0b37f0a93edd27079250cc4e533bdf8cc29 +size 4484363616 diff --git a/llama-3_1-8b-Boost.Q2_K.gguf b/llama-3_1-8b-Boost.Q2_K.gguf new file mode 100644 index 0000000..c667902 --- /dev/null +++ b/llama-3_1-8b-Boost.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea99aa550863bbf34af59b5cfe125d7a5105ee4be3217b47575183d1d85c2430 +size 3179132256 diff --git a/llama-3_1-8b-Boost.Q3_K_L.gguf b/llama-3_1-8b-Boost.Q3_K_L.gguf new file mode 100644 index 0000000..dd6487b --- /dev/null +++ b/llama-3_1-8b-Boost.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b7e11fdc5c6626e7603026888c4fa91caf3138171d9a8480f096943f37d548b +size 4321957216 diff --git a/llama-3_1-8b-Boost.Q3_K_M.gguf b/llama-3_1-8b-Boost.Q3_K_M.gguf new file mode 100644 index 0000000..d7921d9 --- /dev/null +++ b/llama-3_1-8b-Boost.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45939a8b14eb86a0c417d5b3390fd63f1f16bb78d1e054918df963351d6faf7a +size 4018918752 diff --git a/llama-3_1-8b-Boost.Q3_K_S.gguf b/llama-3_1-8b-Boost.Q3_K_S.gguf new file mode 100644 index 0000000..fda2b3a --- /dev/null +++ b/llama-3_1-8b-Boost.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c73e0b6f5d746502b9487a795e5a86196d57f70852f5f96eda8fcb33c565602a +size 3664500064 diff --git a/llama-3_1-8b-Boost.Q4_K_M.gguf b/llama-3_1-8b-Boost.Q4_K_M.gguf new file mode 100644 index 0000000..0f8577f --- /dev/null +++ b/llama-3_1-8b-Boost.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18111d4513811ad09925da4358e32d5df16c883951c04a58a943b4cfd2150189 +size 4920735072 diff --git a/llama-3_1-8b-Boost.Q4_K_S.gguf b/llama-3_1-8b-Boost.Q4_K_S.gguf new file mode 100644 index 0000000..5aeffc7 --- /dev/null +++ b/llama-3_1-8b-Boost.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9f61efa2a598e6415fe4a4d3a35f981533efcd5643ccd659ff0591325248215 +size 4692669792 diff --git a/llama-3_1-8b-Boost.Q5_K_M.gguf b/llama-3_1-8b-Boost.Q5_K_M.gguf new file mode 100644 index 0000000..0edbc47 --- /dev/null +++ b/llama-3_1-8b-Boost.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8ab450ed6ebd6bef685ead22a824205a1595f97296b114adbb5eebeacd4ea6b +size 5732988256 diff --git a/llama-3_1-8b-Boost.Q5_K_S.gguf b/llama-3_1-8b-Boost.Q5_K_S.gguf new file mode 100644 index 0000000..5c754c3 --- /dev/null +++ b/llama-3_1-8b-Boost.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38059b9ce43128ee6dcdf227fdc0362454443920de44644e51873ceaf17d5304 +size 5599294816 diff --git a/llama-3_1-8b-Boost.Q6_K.gguf b/llama-3_1-8b-Boost.Q6_K.gguf new file mode 100644 index 0000000..11976ec --- /dev/null +++ b/llama-3_1-8b-Boost.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2af7ca231bfb9c2abea34662ab7446071427eeb08267e42e850a62dcdb1605ff +size 6596007264 diff --git a/llama-3_1-8b-Boost.Q8_0.gguf b/llama-3_1-8b-Boost.Q8_0.gguf new file mode 100644 index 0000000..5491c0c --- /dev/null +++ b/llama-3_1-8b-Boost.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:254ff2c3d3e079818fd2bf21a0801962f0812184b249ea4257bdb4f7ed5e9b5c +size 8540771680 diff --git a/llama-3_1-8b-Boost.f16.gguf b/llama-3_1-8b-Boost.f16.gguf new file mode 100644 index 0000000..8899513 --- /dev/null +++ b/llama-3_1-8b-Boost.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89f5adb6a166c7b64a68f30fec5809d7e8b86956f7fdbb04d611fe5db06988d7 +size 16068892000