commit 09d1d7d3f6464e11d2390d1ac9dcafc226001050 Author: ModelHub XC Date: Mon Jun 15 10:41:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/malayalam_llama_3.2-1B_Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5768c4f --- /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_3.2-1B_Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +malayalam_llama_3.2-1B_Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +malayalam_llama_3.2-1B_Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +malayalam_llama_3.2-1B_Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +malayalam_llama_3.2-1B_Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +malayalam_llama_3.2-1B_Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +malayalam_llama_3.2-1B_Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +malayalam_llama_3.2-1B_Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +malayalam_llama_3.2-1B_Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +malayalam_llama_3.2-1B_Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +malayalam_llama_3.2-1B_Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +malayalam_llama_3.2-1B_Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8c8b4a0 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: vineethn/malayalam_llama_3.2-1B_Instruct +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/vineethn/malayalam_llama_3.2-1B_Instruct + + +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_3.2-1B_Instruct-GGUF/resolve/main/malayalam_llama_3.2-1B_Instruct.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/malayalam_llama_3.2-1B_Instruct-GGUF/resolve/main/malayalam_llama_3.2-1B_Instruct.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/malayalam_llama_3.2-1B_Instruct-GGUF/resolve/main/malayalam_llama_3.2-1B_Instruct.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/malayalam_llama_3.2-1B_Instruct-GGUF/resolve/main/malayalam_llama_3.2-1B_Instruct.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/malayalam_llama_3.2-1B_Instruct-GGUF/resolve/main/malayalam_llama_3.2-1B_Instruct.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/malayalam_llama_3.2-1B_Instruct-GGUF/resolve/main/malayalam_llama_3.2-1B_Instruct.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/malayalam_llama_3.2-1B_Instruct-GGUF/resolve/main/malayalam_llama_3.2-1B_Instruct.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/malayalam_llama_3.2-1B_Instruct-GGUF/resolve/main/malayalam_llama_3.2-1B_Instruct.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/malayalam_llama_3.2-1B_Instruct-GGUF/resolve/main/malayalam_llama_3.2-1B_Instruct.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/malayalam_llama_3.2-1B_Instruct-GGUF/resolve/main/malayalam_llama_3.2-1B_Instruct.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/malayalam_llama_3.2-1B_Instruct-GGUF/resolve/main/malayalam_llama_3.2-1B_Instruct.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/malayalam_llama_3.2-1B_Instruct-GGUF/resolve/main/malayalam_llama_3.2-1B_Instruct.f16.gguf) | f16 | 2.6 | 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. + + diff --git a/malayalam_llama_3.2-1B_Instruct.IQ4_XS.gguf b/malayalam_llama_3.2-1B_Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..e1347df --- /dev/null +++ b/malayalam_llama_3.2-1B_Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d8a0a01a3a074d9a39865e7e0dee186bb38b6ab205cf45191410f83934fdaff +size 748384672 diff --git a/malayalam_llama_3.2-1B_Instruct.Q2_K.gguf b/malayalam_llama_3.2-1B_Instruct.Q2_K.gguf new file mode 100644 index 0000000..aa6214a --- /dev/null +++ b/malayalam_llama_3.2-1B_Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c85dd242e58bc67dbfc20a4553cc08825980e370fa67562213a0817bc576bd18 +size 580874656 diff --git a/malayalam_llama_3.2-1B_Instruct.Q3_K_L.gguf b/malayalam_llama_3.2-1B_Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..c9efb91 --- /dev/null +++ b/malayalam_llama_3.2-1B_Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dfdaca298e7557a641b0bfcc488747c5aae1e833c9d30dd59cc2a35f54237db +size 732524960 diff --git a/malayalam_llama_3.2-1B_Instruct.Q3_K_M.gguf b/malayalam_llama_3.2-1B_Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..668cd77 --- /dev/null +++ b/malayalam_llama_3.2-1B_Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5cbf20632e6a2b1c3fbda8628ec1971f98b99e674220caa896fe7471146cd38 +size 690844064 diff --git a/malayalam_llama_3.2-1B_Instruct.Q3_K_S.gguf b/malayalam_llama_3.2-1B_Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..c1833e1 --- /dev/null +++ b/malayalam_llama_3.2-1B_Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffbeaabdd2e9097305be3e34d40546e9eebbcdf37234af5a39d200b1a83d92d0 +size 641692064 diff --git a/malayalam_llama_3.2-1B_Instruct.Q4_K_M.gguf b/malayalam_llama_3.2-1B_Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..2c49f01 --- /dev/null +++ b/malayalam_llama_3.2-1B_Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09221768b5c33a3509f3bab6429b939c20121ccf3c265792ccb9678c9958016a +size 807694752 diff --git a/malayalam_llama_3.2-1B_Instruct.Q4_K_S.gguf b/malayalam_llama_3.2-1B_Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..2716db3 --- /dev/null +++ b/malayalam_llama_3.2-1B_Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cc5609d0c3b8a5cac0506b2d0160915094fb71efa98d94c78c4d21b71583d39 +size 775647648 diff --git a/malayalam_llama_3.2-1B_Instruct.Q5_K_M.gguf b/malayalam_llama_3.2-1B_Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..2054615 --- /dev/null +++ b/malayalam_llama_3.2-1B_Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06ab3daf613fd7846737cf45ee63e5767a89438ed84770560f88b94f2a260920 +size 911503776 diff --git a/malayalam_llama_3.2-1B_Instruct.Q5_K_S.gguf b/malayalam_llama_3.2-1B_Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..801367d --- /dev/null +++ b/malayalam_llama_3.2-1B_Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b44f742d30ba498e8966f40849d0a424f1fde172d3d5bed168ad2a104872624 +size 892563872 diff --git a/malayalam_llama_3.2-1B_Instruct.Q6_K.gguf b/malayalam_llama_3.2-1B_Instruct.Q6_K.gguf new file mode 100644 index 0000000..2b7b869 --- /dev/null +++ b/malayalam_llama_3.2-1B_Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4285fcff71def2b7dd3557467dd03aa5d325697424ded4e0cc52fefe8914d7c3 +size 1021800864 diff --git a/malayalam_llama_3.2-1B_Instruct.Q8_0.gguf b/malayalam_llama_3.2-1B_Instruct.Q8_0.gguf new file mode 100644 index 0000000..d1e57a2 --- /dev/null +++ b/malayalam_llama_3.2-1B_Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89e7828d20ab3aac912810510c09a86d4b8455d09e3bd860a78865bc60b0ce68 +size 1321083296 diff --git a/malayalam_llama_3.2-1B_Instruct.f16.gguf b/malayalam_llama_3.2-1B_Instruct.f16.gguf new file mode 100644 index 0000000..d3d266c --- /dev/null +++ b/malayalam_llama_3.2-1B_Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a73b1f52b6e00a8516a564b562a8c39593717145f7ce0bfc485cfa9e1cbb121d +size 2479595936