commit afa76fcbaeb829e3075dc3ce1bec4768a7db0fd9 Author: ModelHub XC Date: Wed Aug 5 01:29:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mini-Lama-8B-Base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9d62a77 --- /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 +Mini-Lama-8B-Base.f16.gguf filter=lfs diff=lfs merge=lfs -text +Mini-Lama-8B-Base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mini-Lama-8B-Base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mini-Lama-8B-Base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mini-Lama-8B-Base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mini-Lama-8B-Base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mini-Lama-8B-Base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mini-Lama-8B-Base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mini-Lama-8B-Base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mini-Lama-8B-Base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mini-Lama-8B-Base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mini-Lama-8B-Base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mini-Lama-8B-Base.IQ4_XS.gguf b/Mini-Lama-8B-Base.IQ4_XS.gguf new file mode 100644 index 0000000..27757c3 --- /dev/null +++ b/Mini-Lama-8B-Base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c990ea2c44b58725c088f1ee6cb17537fbb8461e5a7eea9eac440750eb8212a +size 4733463104 diff --git a/Mini-Lama-8B-Base.Q2_K.gguf b/Mini-Lama-8B-Base.Q2_K.gguf new file mode 100644 index 0000000..b47525a --- /dev/null +++ b/Mini-Lama-8B-Base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a358906cd816671f827855aa0d0bb480399b623cbd73aa804fa52b354b470115 +size 3353221696 diff --git a/Mini-Lama-8B-Base.Q3_K_L.gguf b/Mini-Lama-8B-Base.Q3_K_L.gguf new file mode 100644 index 0000000..e2b73b8 --- /dev/null +++ b/Mini-Lama-8B-Base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ff1fabfd8a3e7f98f7ff463488f63daa847aa110c0bbe1347e61a352f6fff7e +size 4565336640 diff --git a/Mini-Lama-8B-Base.Q3_K_M.gguf b/Mini-Lama-8B-Base.Q3_K_M.gguf new file mode 100644 index 0000000..efa4539 --- /dev/null +++ b/Mini-Lama-8B-Base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72444b0a1ca96b1b5a7c64e46564e3425100f14076a2cb3dc378d94881fb85f1 +size 4242375232 diff --git a/Mini-Lama-8B-Base.Q3_K_S.gguf b/Mini-Lama-8B-Base.Q3_K_S.gguf new file mode 100644 index 0000000..d6d5723 --- /dev/null +++ b/Mini-Lama-8B-Base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4546844a61cabc61b9ca7f5113da85987ca19d356fb9352620a4221db8b0540 +size 3866788416 diff --git a/Mini-Lama-8B-Base.Q4_K_M.gguf b/Mini-Lama-8B-Base.Q4_K_M.gguf new file mode 100644 index 0000000..b6cbf85 --- /dev/null +++ b/Mini-Lama-8B-Base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72c4b7bbccf689d37fd8f33aba81fc00e05bf1f9af5c136d7e68d90301ba0fa1 +size 5198744128 diff --git a/Mini-Lama-8B-Base.Q4_K_S.gguf b/Mini-Lama-8B-Base.Q4_K_S.gguf new file mode 100644 index 0000000..64d482d --- /dev/null +++ b/Mini-Lama-8B-Base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476e5077e6c0bfc60e16a1cd71e60a30afae53dc0f37ba4f3c12daef0bf0b1a8 +size 4954458688 diff --git a/Mini-Lama-8B-Base.Q5_K_M.gguf b/Mini-Lama-8B-Base.Q5_K_M.gguf new file mode 100644 index 0000000..c6e3309 --- /dev/null +++ b/Mini-Lama-8B-Base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7834e4f086133bc0da5cce81571890e952c72b22b8c9fc34aa85e3483a910105 +size 6059133504 diff --git a/Mini-Lama-8B-Base.Q5_K_S.gguf b/Mini-Lama-8B-Base.Q5_K_S.gguf new file mode 100644 index 0000000..4a53358 --- /dev/null +++ b/Mini-Lama-8B-Base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87180231e6ca8d6dc3baabd7d1d4affe7cd04886df19826b48f0ef3f5b20f8ac +size 5917084224 diff --git a/Mini-Lama-8B-Base.Q6_K.gguf b/Mini-Lama-8B-Base.Q6_K.gguf new file mode 100644 index 0000000..2ba97a3 --- /dev/null +++ b/Mini-Lama-8B-Base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33688af7050109025f30765c766bb52f3fb919be05d1f8a8963c8e1beeabae08 +size 6973297216 diff --git a/Mini-Lama-8B-Base.Q8_0.gguf b/Mini-Lama-8B-Base.Q8_0.gguf new file mode 100644 index 0000000..ab88a76 --- /dev/null +++ b/Mini-Lama-8B-Base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e98bfa289794732d6692def042b4244dee1b2daeb0c6b77e0ca802e72e6ff6fd +size 9029419584 diff --git a/Mini-Lama-8B-Base.f16.gguf b/Mini-Lama-8B-Base.f16.gguf new file mode 100644 index 0000000..015b2bc --- /dev/null +++ b/Mini-Lama-8B-Base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4c67c6334d29719fd3bc2065150fff02798a22814e48acb841defe0347f89e9 +size 16988602944 diff --git a/README.md b/README.md new file mode 100644 index 0000000..277d714 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Nabbers1999/Mini-Llama-8B-Base-0124 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- ministral-3 +- text-generation +- base +- llamafied +- novision +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Nabbers1999/Mini-Llama-8B-Base-0124 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mini-Lama-8B-Base-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Mini-Lama-8B-Base-i1-GGUF +## 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/Mini-Lama-8B-Base-GGUF/resolve/main/Mini-Lama-8B-Base.Q2_K.gguf) | Q2_K | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Mini-Lama-8B-Base-GGUF/resolve/main/Mini-Lama-8B-Base.Q3_K_S.gguf) | Q3_K_S | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mini-Lama-8B-Base-GGUF/resolve/main/Mini-Lama-8B-Base.Q3_K_M.gguf) | Q3_K_M | 4.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mini-Lama-8B-Base-GGUF/resolve/main/Mini-Lama-8B-Base.Q3_K_L.gguf) | Q3_K_L | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Mini-Lama-8B-Base-GGUF/resolve/main/Mini-Lama-8B-Base.IQ4_XS.gguf) | IQ4_XS | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mini-Lama-8B-Base-GGUF/resolve/main/Mini-Lama-8B-Base.Q4_K_S.gguf) | Q4_K_S | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mini-Lama-8B-Base-GGUF/resolve/main/Mini-Lama-8B-Base.Q4_K_M.gguf) | Q4_K_M | 5.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mini-Lama-8B-Base-GGUF/resolve/main/Mini-Lama-8B-Base.Q5_K_S.gguf) | Q5_K_S | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mini-Lama-8B-Base-GGUF/resolve/main/Mini-Lama-8B-Base.Q5_K_M.gguf) | Q5_K_M | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mini-Lama-8B-Base-GGUF/resolve/main/Mini-Lama-8B-Base.Q6_K.gguf) | Q6_K | 7.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mini-Lama-8B-Base-GGUF/resolve/main/Mini-Lama-8B-Base.Q8_0.gguf) | Q8_0 | 9.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mini-Lama-8B-Base-GGUF/resolve/main/Mini-Lama-8B-Base.f16.gguf) | f16 | 17.1 | 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. + +