commit 4bf9cab2f394878ee35f9d469208436be6c2ba23 Author: ModelHub XC Date: Wed Sep 2 02:52:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SindhiLlama-1.1B-v0.01-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8988533 --- /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 +SindhiLlama-1.1B-v0.01.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +SindhiLlama-1.1B-v0.01.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SindhiLlama-1.1B-v0.01.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SindhiLlama-1.1B-v0.01.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SindhiLlama-1.1B-v0.01.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SindhiLlama-1.1B-v0.01.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SindhiLlama-1.1B-v0.01.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SindhiLlama-1.1B-v0.01.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SindhiLlama-1.1B-v0.01.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SindhiLlama-1.1B-v0.01.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SindhiLlama-1.1B-v0.01.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SindhiLlama-1.1B-v0.01.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e8b97dc --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: jamalimubashirali/SindhiLlama-1.1B-v0.01 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/jamalimubashirali/SindhiLlama-1.1B-v0.01 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SindhiLlama-1.1B-v0.01-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/SindhiLlama-1.1B-v0.01-GGUF/resolve/main/SindhiLlama-1.1B-v0.01.Q2_K.gguf) | Q2_K | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/SindhiLlama-1.1B-v0.01-GGUF/resolve/main/SindhiLlama-1.1B-v0.01.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/SindhiLlama-1.1B-v0.01-GGUF/resolve/main/SindhiLlama-1.1B-v0.01.Q3_K_M.gguf) | Q3_K_M | 0.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SindhiLlama-1.1B-v0.01-GGUF/resolve/main/SindhiLlama-1.1B-v0.01.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/SindhiLlama-1.1B-v0.01-GGUF/resolve/main/SindhiLlama-1.1B-v0.01.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/SindhiLlama-1.1B-v0.01-GGUF/resolve/main/SindhiLlama-1.1B-v0.01.Q4_K_S.gguf) | Q4_K_S | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SindhiLlama-1.1B-v0.01-GGUF/resolve/main/SindhiLlama-1.1B-v0.01.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SindhiLlama-1.1B-v0.01-GGUF/resolve/main/SindhiLlama-1.1B-v0.01.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/SindhiLlama-1.1B-v0.01-GGUF/resolve/main/SindhiLlama-1.1B-v0.01.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/SindhiLlama-1.1B-v0.01-GGUF/resolve/main/SindhiLlama-1.1B-v0.01.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SindhiLlama-1.1B-v0.01-GGUF/resolve/main/SindhiLlama-1.1B-v0.01.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SindhiLlama-1.1B-v0.01-GGUF/resolve/main/SindhiLlama-1.1B-v0.01.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/SindhiLlama-1.1B-v0.01.IQ4_XS.gguf b/SindhiLlama-1.1B-v0.01.IQ4_XS.gguf new file mode 100644 index 0000000..a2d0eb1 --- /dev/null +++ b/SindhiLlama-1.1B-v0.01.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26db4aa09399b89449d13bc5144c14bffa0d9786b3c0f01db4d76dd7ee3ca5d5 +size 698199744 diff --git a/SindhiLlama-1.1B-v0.01.Q2_K.gguf b/SindhiLlama-1.1B-v0.01.Q2_K.gguf new file mode 100644 index 0000000..b0d6d0d --- /dev/null +++ b/SindhiLlama-1.1B-v0.01.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1495f6d31ea8bf62f475250b66013e69b19dfa9ccb40de8d2ecd9ac73b34d07 +size 507369536 diff --git a/SindhiLlama-1.1B-v0.01.Q3_K_L.gguf b/SindhiLlama-1.1B-v0.01.Q3_K_L.gguf new file mode 100644 index 0000000..66cc211 --- /dev/null +++ b/SindhiLlama-1.1B-v0.01.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ce02bf5dd9390b34c0b9ee0264169f3499b869732f2aaffc8d178a2fcf1a13e +size 673342336 diff --git a/SindhiLlama-1.1B-v0.01.Q3_K_M.gguf b/SindhiLlama-1.1B-v0.01.Q3_K_M.gguf new file mode 100644 index 0000000..e87deec --- /dev/null +++ b/SindhiLlama-1.1B-v0.01.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed48b119ea826394b9ef592e8305e6c7b611470ff3859959faa3b4f1c4734961 +size 630219648 diff --git a/SindhiLlama-1.1B-v0.01.Q3_K_S.gguf b/SindhiLlama-1.1B-v0.01.Q3_K_S.gguf new file mode 100644 index 0000000..dba5106 --- /dev/null +++ b/SindhiLlama-1.1B-v0.01.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89932f4f9c85f344258bc6326370533341b8bf2c6413f421e4827ef0493f2630 +size 581157760 diff --git a/SindhiLlama-1.1B-v0.01.Q4_K_M.gguf b/SindhiLlama-1.1B-v0.01.Q4_K_M.gguf new file mode 100644 index 0000000..b0cc564 --- /dev/null +++ b/SindhiLlama-1.1B-v0.01.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fe6e75e9803c23900936fbd23657f02ae3dbacc58ea34462b49ee6923e8a4f6 +size 758230976 diff --git a/SindhiLlama-1.1B-v0.01.Q4_K_S.gguf b/SindhiLlama-1.1B-v0.01.Q4_K_S.gguf new file mode 100644 index 0000000..a65dbf7 --- /dev/null +++ b/SindhiLlama-1.1B-v0.01.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ba1a799ed6f71ae2a735d3480d97c1376fd24e3a7a9a502034f1fb7dc1f6af4 +size 730288064 diff --git a/SindhiLlama-1.1B-v0.01.Q5_K_M.gguf b/SindhiLlama-1.1B-v0.01.Q5_K_M.gguf new file mode 100644 index 0000000..4c6ce51 --- /dev/null +++ b/SindhiLlama-1.1B-v0.01.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d8c035f472c511ed9fcda9b3a96216d6f35d9b5926d3693caf8a53bfd558d36 +size 880554944 diff --git a/SindhiLlama-1.1B-v0.01.Q5_K_S.gguf b/SindhiLlama-1.1B-v0.01.Q5_K_S.gguf new file mode 100644 index 0000000..341414b --- /dev/null +++ b/SindhiLlama-1.1B-v0.01.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b057f964c4c52a8e73b95d982d18e948dd0d681d2eb32457cd0d08b5da744a6b +size 864539584 diff --git a/SindhiLlama-1.1B-v0.01.Q6_K.gguf b/SindhiLlama-1.1B-v0.01.Q6_K.gguf new file mode 100644 index 0000000..4b1bbac --- /dev/null +++ b/SindhiLlama-1.1B-v0.01.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e51409701507c4782e7b5db72a82ddb196bc6b147b086216321504bb5a11ebc6 +size 1010524160 diff --git a/SindhiLlama-1.1B-v0.01.Q8_0.gguf b/SindhiLlama-1.1B-v0.01.Q8_0.gguf new file mode 100644 index 0000000..b173fa1 --- /dev/null +++ b/SindhiLlama-1.1B-v0.01.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f89b946f2081d9bb262c013de101533028be3c82e172a31ab14853d722f23870 +size 1308286848 diff --git a/SindhiLlama-1.1B-v0.01.f16.gguf b/SindhiLlama-1.1B-v0.01.f16.gguf new file mode 100644 index 0000000..1c12d7e --- /dev/null +++ b/SindhiLlama-1.1B-v0.01.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c8690768d16bf3aee08a23c0098b8ce453b01e601532ae958693713ad91d74e +size 2460916608