commit 9f6c5852308268e6b4cf4dbbe2660fc82f767391 Author: ModelHub XC Date: Sat May 23 20:04:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llammas-base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ed2071c --- /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 +Llammas-base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llammas-base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llammas-base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llammas-base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llammas-base.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llammas-base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llammas-base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llammas-base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llammas-base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llammas-base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llammas-base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llammas-base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llammas-base.IQ4_XS.gguf b/Llammas-base.IQ4_XS.gguf new file mode 100644 index 0000000..83baba9 --- /dev/null +++ b/Llammas-base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa76c6c0269225cc5c9b2bbc72c14a03e5afa849ae155572d7c3a08f57a118cb +size 3647517440 diff --git a/Llammas-base.Q2_K.gguf b/Llammas-base.Q2_K.gguf new file mode 100644 index 0000000..0678b65 --- /dev/null +++ b/Llammas-base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d640131da2a1afb3d2be178a6d7850fb24aa6b003175b2c1f1d4cb286ce347f2 +size 2532864768 diff --git a/Llammas-base.Q3_K_L.gguf b/Llammas-base.Q3_K_L.gguf new file mode 100644 index 0000000..d23c4e2 --- /dev/null +++ b/Llammas-base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f81fa91915a19cf577beb27bbd195d9e99854f3ddecf95e0fe04a094409b0646 +size 3597112064 diff --git a/Llammas-base.Q3_K_M.gguf b/Llammas-base.Q3_K_M.gguf new file mode 100644 index 0000000..8ae0466 --- /dev/null +++ b/Llammas-base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2baa8e141536008a955db7aa4529c25dfcdd4d14b7b5d7ac790439fde1fe8fcc +size 3298005760 diff --git a/Llammas-base.Q3_K_S.gguf b/Llammas-base.Q3_K_S.gguf new file mode 100644 index 0000000..c59a867 --- /dev/null +++ b/Llammas-base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95ed12e045436fbb3c436e7399fd39ca62efddef63fe19d1e4ecbd85f82844df +size 2948305664 diff --git a/Llammas-base.Q4_K_M.gguf b/Llammas-base.Q4_K_M.gguf new file mode 100644 index 0000000..9c17147 --- /dev/null +++ b/Llammas-base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74fb581ac60b05a96ca1d228a4bd15adc3faa21cd89a9f8d7b4e45a3ccc332cf +size 4081005312 diff --git a/Llammas-base.Q4_K_S.gguf b/Llammas-base.Q4_K_S.gguf new file mode 100644 index 0000000..65af2ad --- /dev/null +++ b/Llammas-base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ca39abfb0d06ccc8af4c684c6aa66bd74acd9caee2bc5ce27df0735647a181b +size 3856741120 diff --git a/Llammas-base.Q5_K_M.gguf b/Llammas-base.Q5_K_M.gguf new file mode 100644 index 0000000..371d509 --- /dev/null +++ b/Llammas-base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db78cc3acead100c1c5101638a497345f71773e5b57301bfdab8fc3f5a9f0319 +size 4783158016 diff --git a/Llammas-base.Q5_K_S.gguf b/Llammas-base.Q5_K_S.gguf new file mode 100644 index 0000000..97d1b47 --- /dev/null +++ b/Llammas-base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5611eee7bf56636a3b20e7316d6eda516fe1367b87a8d1ba0d7a856c13b48cf6 +size 4651692800 diff --git a/Llammas-base.Q6_K.gguf b/Llammas-base.Q6_K.gguf new file mode 100644 index 0000000..04d9b8a --- /dev/null +++ b/Llammas-base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b71936e5262836d62f12a33d869367f478a3552ef2a4d761086ec672623a495 +size 5529195264 diff --git a/Llammas-base.Q8_0.gguf b/Llammas-base.Q8_0.gguf new file mode 100644 index 0000000..ddd5e18 --- /dev/null +++ b/Llammas-base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6e4e631df690b3499aa252ae39d3f927220ee397b927a877d8fd3aed1683efd +size 7161090816 diff --git a/Llammas-base.f16.gguf b/Llammas-base.f16.gguf new file mode 100644 index 0000000..83bda7e --- /dev/null +++ b/Llammas-base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1927726b1d44aa9d0c467ce68109053b663964e1e11be9e1d4398a875aa8b7d8 +size 13478105856 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ba4d997 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: tartuNLP/Llammas-base +language: +- et +- en +library_name: transformers +license: llama2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/tartuNLP/Llammas-base + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llammas-base-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llammas-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/Llammas-base-GGUF/resolve/main/Llammas-base.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llammas-base-GGUF/resolve/main/Llammas-base.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llammas-base-GGUF/resolve/main/Llammas-base.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llammas-base-GGUF/resolve/main/Llammas-base.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llammas-base-GGUF/resolve/main/Llammas-base.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llammas-base-GGUF/resolve/main/Llammas-base.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llammas-base-GGUF/resolve/main/Llammas-base.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llammas-base-GGUF/resolve/main/Llammas-base.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llammas-base-GGUF/resolve/main/Llammas-base.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llammas-base-GGUF/resolve/main/Llammas-base.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llammas-base-GGUF/resolve/main/Llammas-base.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llammas-base-GGUF/resolve/main/Llammas-base.f16.gguf) | f16 | 13.6 | 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. + +