commit e5c209c33f11b25442a9f798f5fcb26f1a29e268 Author: ModelHub XC Date: Sat Sep 26 07:11:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/malayalam-Llama-3.2-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7406f5b --- /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 +malayalam-Llama-3.2-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +malayalam-Llama-3.2-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +malayalam-Llama-3.2-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +malayalam-Llama-3.2-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +malayalam-Llama-3.2-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +malayalam-Llama-3.2-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +malayalam-Llama-3.2-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +malayalam-Llama-3.2-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +malayalam-Llama-3.2-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +malayalam-Llama-3.2-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +malayalam-Llama-3.2-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +malayalam-Llama-3.2-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2eb153d --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: traromal/malayalam-Llama-3.2-3B +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/traromal/malayalam-Llama-3.2-3B + + +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/malayalam-Llama-3.2-3B-GGUF/resolve/main/malayalam-Llama-3.2-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/malayalam-Llama-3.2-3B-GGUF/resolve/main/malayalam-Llama-3.2-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/malayalam-Llama-3.2-3B-GGUF/resolve/main/malayalam-Llama-3.2-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/malayalam-Llama-3.2-3B-GGUF/resolve/main/malayalam-Llama-3.2-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/malayalam-Llama-3.2-3B-GGUF/resolve/main/malayalam-Llama-3.2-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/malayalam-Llama-3.2-3B-GGUF/resolve/main/malayalam-Llama-3.2-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/malayalam-Llama-3.2-3B-GGUF/resolve/main/malayalam-Llama-3.2-3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/malayalam-Llama-3.2-3B-GGUF/resolve/main/malayalam-Llama-3.2-3B.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/malayalam-Llama-3.2-3B-GGUF/resolve/main/malayalam-Llama-3.2-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/malayalam-Llama-3.2-3B-GGUF/resolve/main/malayalam-Llama-3.2-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/malayalam-Llama-3.2-3B-GGUF/resolve/main/malayalam-Llama-3.2-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/malayalam-Llama-3.2-3B-GGUF/resolve/main/malayalam-Llama-3.2-3B.f16.gguf) | f16 | 6.5 | 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/malayalam-Llama-3.2-3B.IQ4_XS.gguf b/malayalam-Llama-3.2-3B.IQ4_XS.gguf new file mode 100644 index 0000000..ce16961 --- /dev/null +++ b/malayalam-Llama-3.2-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b9ade239a828f030c85020152bdf4e73b57ca34d31b1bbd63d6f253c40e27ec +size 1840907072 diff --git a/malayalam-Llama-3.2-3B.Q2_K.gguf b/malayalam-Llama-3.2-3B.Q2_K.gguf new file mode 100644 index 0000000..e55e85c --- /dev/null +++ b/malayalam-Llama-3.2-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f83a19fd48e99d749b2d2521479c66c72835776d82efe09379e7bbca0cf279b +size 1363936064 diff --git a/malayalam-Llama-3.2-3B.Q3_K_L.gguf b/malayalam-Llama-3.2-3B.Q3_K_L.gguf new file mode 100644 index 0000000..c8c92c3 --- /dev/null +++ b/malayalam-Llama-3.2-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d0a72f832b6350cbced74e3aa0eb83a30f1b55b4b08be9058c7cf71ecd54d55 +size 1815348032 diff --git a/malayalam-Llama-3.2-3B.Q3_K_M.gguf b/malayalam-Llama-3.2-3B.Q3_K_M.gguf new file mode 100644 index 0000000..2a83c40 --- /dev/null +++ b/malayalam-Llama-3.2-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:254f3e6df45b0e9ec24e7036d702c253a4df5bad0ca8a9c0e9f8d0a78a91e557 +size 1687159616 diff --git a/malayalam-Llama-3.2-3B.Q3_K_S.gguf b/malayalam-Llama-3.2-3B.Q3_K_S.gguf new file mode 100644 index 0000000..5a5566d --- /dev/null +++ b/malayalam-Llama-3.2-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67b721eb40919ee9b94a6a1ee5f8ef898845a1d5b95c4c80163bad4801d52054 +size 1542849344 diff --git a/malayalam-Llama-3.2-3B.Q4_K_M.gguf b/malayalam-Llama-3.2-3B.Q4_K_M.gguf new file mode 100644 index 0000000..e087dc2 --- /dev/null +++ b/malayalam-Llama-3.2-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48443f00165598f856d57b3f91039cc092e826ef1e4794f2c900cda313d8c5b5 +size 2019377984 diff --git a/malayalam-Llama-3.2-3B.Q4_K_S.gguf b/malayalam-Llama-3.2-3B.Q4_K_S.gguf new file mode 100644 index 0000000..a022884 --- /dev/null +++ b/malayalam-Llama-3.2-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9e3382d4d5327ea134005b4cc58f1679a4e2971772c6d81822a0a31eac11a90 +size 1928201024 diff --git a/malayalam-Llama-3.2-3B.Q5_K_M.gguf b/malayalam-Llama-3.2-3B.Q5_K_M.gguf new file mode 100644 index 0000000..130ca60 --- /dev/null +++ b/malayalam-Llama-3.2-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c0bb0d2c733c3cf62cf9bd96007bf52d773e2970aa5bb8af8073e4722815b87 +size 2322154304 diff --git a/malayalam-Llama-3.2-3B.Q5_K_S.gguf b/malayalam-Llama-3.2-3B.Q5_K_S.gguf new file mode 100644 index 0000000..b8906ec --- /dev/null +++ b/malayalam-Llama-3.2-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c365db30febe6f21fd157dc345d90dc5d1514b9d277c6df04f29a90ad509fc4 +size 2269512512 diff --git a/malayalam-Llama-3.2-3B.Q6_K.gguf b/malayalam-Llama-3.2-3B.Q6_K.gguf new file mode 100644 index 0000000..9d72221 --- /dev/null +++ b/malayalam-Llama-3.2-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb2f908e0c939e720e02f44338d8b2c79bf777bf49d15d41153fd5f48f0d373b +size 2643854144 diff --git a/malayalam-Llama-3.2-3B.Q8_0.gguf b/malayalam-Llama-3.2-3B.Q8_0.gguf new file mode 100644 index 0000000..e536f36 --- /dev/null +++ b/malayalam-Llama-3.2-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1822c874da0e8804a1c44d130519de4fc798529cfd9ce9f62ef2b7ab6e0f7fb2 +size 3421899584 diff --git a/malayalam-Llama-3.2-3B.f16.gguf b/malayalam-Llama-3.2-3B.f16.gguf new file mode 100644 index 0000000..e783f6e --- /dev/null +++ b/malayalam-Llama-3.2-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8225fe34b48a3f8b1aa35210288b14b8a76589d0dd3a14b62875d287e10d5d7 +size 6433688384