commit 1d82f627bba456497ecc4ca0e50777c34706a468 Author: ModelHub XC Date: Sat Jul 4 19:34:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MLlamav1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..879b420 --- /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 +MLlamav1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MLlamav1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MLlamav1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MLlamav1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MLlamav1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MLlamav1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MLlamav1.f16.gguf filter=lfs diff=lfs merge=lfs -text +MLlamav1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MLlamav1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MLlamav1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MLlamav1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MLlamav1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MLlamav1.IQ4_XS.gguf b/MLlamav1.IQ4_XS.gguf new file mode 100644 index 0000000..e0d9ee5 --- /dev/null +++ b/MLlamav1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:788330d2fde87236a5d597fe31cea3ecf17de0562ef2ea400a40d48121a38bce +size 5035481312 diff --git a/MLlamav1.Q2_K.gguf b/MLlamav1.Q2_K.gguf new file mode 100644 index 0000000..d22fd2e --- /dev/null +++ b/MLlamav1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:699d77361c22479ebdbf1d7ffe2c834beb750dd19d19d49d112e114b5181e65e +size 3778095328 diff --git a/MLlamav1.Q3_K_L.gguf b/MLlamav1.Q3_K_L.gguf new file mode 100644 index 0000000..b0f06fa --- /dev/null +++ b/MLlamav1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c37aac8fec0e266324aea5977c33a8ab9d443bdd2cbc7727ac50d36e1193c2da +size 4929298656 diff --git a/MLlamav1.Q3_K_M.gguf b/MLlamav1.Q3_K_M.gguf new file mode 100644 index 0000000..2a1ab1a --- /dev/null +++ b/MLlamav1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02163b3a4a5afb8ad42cee6004e6f1158bbf20e12c87cf54f80b583364d7487f +size 4712489184 diff --git a/MLlamav1.Q3_K_S.gguf b/MLlamav1.Q3_K_S.gguf new file mode 100644 index 0000000..980b446 --- /dev/null +++ b/MLlamav1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69e9857eafe40cee33f46b59b5e20a163428330af216e749d775997865efcd90 +size 4335050976 diff --git a/MLlamav1.Q4_K_M.gguf b/MLlamav1.Q4_K_M.gguf new file mode 100644 index 0000000..81020b3 --- /dev/null +++ b/MLlamav1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a27d9d781c3d58658ad29d90a1d9c63bef70727b15eecb74f4f3c1b34f980d62 +size 5875202272 diff --git a/MLlamav1.Q4_K_S.gguf b/MLlamav1.Q4_K_S.gguf new file mode 100644 index 0000000..6e0ef53 --- /dev/null +++ b/MLlamav1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03e1d296e3a4a56a7cbc7dfb0ad211d6538b0047e9f574d6bc670d762ae485cb +size 5473319136 diff --git a/MLlamav1.Q5_K_M.gguf b/MLlamav1.Q5_K_M.gguf new file mode 100644 index 0000000..675d08e --- /dev/null +++ b/MLlamav1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f55433ab1386be5c222f8f8edfacac35e18897a1cf7e3b4ef6645284c0fc82e +size 6729365728 diff --git a/MLlamav1.Q5_K_S.gguf b/MLlamav1.Q5_K_S.gguf new file mode 100644 index 0000000..94be35e --- /dev/null +++ b/MLlamav1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a64d1c3e6952b71f3c8485f46752d0e50c48a8ed3c4ad5a89a59eb4888714950 +size 6385531104 diff --git a/MLlamav1.Q6_K.gguf b/MLlamav1.Q6_K.gguf new file mode 100644 index 0000000..fbfc18d --- /dev/null +++ b/MLlamav1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9832ae3d1c1db3dbcdd7b0cd727b8d3a02bdba27b26e2a8520362f0eb3f8d91 +size 7939346656 diff --git a/MLlamav1.Q8_0.gguf b/MLlamav1.Q8_0.gguf new file mode 100644 index 0000000..a47e162 --- /dev/null +++ b/MLlamav1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab4e377d3db8c58c19cef8fd889ec78f63cf500922d1ff1ec14176a2d9d537f4 +size 9559179488 diff --git a/MLlamav1.f16.gguf b/MLlamav1.f16.gguf new file mode 100644 index 0000000..5cd73d2 --- /dev/null +++ b/MLlamav1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e9ac401e4fb68f86a1b38776628ca8ab6f9724a31912cc6a9e630e1b2cd111f +size 17989730528 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5945262 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Haesteining/MLlamav1 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Haesteining/MLlamav1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MLlamav1-GGUF).*** + +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/MLlamav1-GGUF/resolve/main/MLlamav1.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MLlamav1-GGUF/resolve/main/MLlamav1.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MLlamav1-GGUF/resolve/main/MLlamav1.Q3_K_M.gguf) | Q3_K_M | 4.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MLlamav1-GGUF/resolve/main/MLlamav1.Q3_K_L.gguf) | Q3_K_L | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/MLlamav1-GGUF/resolve/main/MLlamav1.IQ4_XS.gguf) | IQ4_XS | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/MLlamav1-GGUF/resolve/main/MLlamav1.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MLlamav1-GGUF/resolve/main/MLlamav1.Q4_K_M.gguf) | Q4_K_M | 6.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MLlamav1-GGUF/resolve/main/MLlamav1.Q5_K_S.gguf) | Q5_K_S | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/MLlamav1-GGUF/resolve/main/MLlamav1.Q5_K_M.gguf) | Q5_K_M | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/MLlamav1-GGUF/resolve/main/MLlamav1.Q6_K.gguf) | Q6_K | 8.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MLlamav1-GGUF/resolve/main/MLlamav1.Q8_0.gguf) | Q8_0 | 9.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MLlamav1-GGUF/resolve/main/MLlamav1.f16.gguf) | f16 | 18.1 | 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. + +