commit 22e3d1b305a20845df37f413d7806102d3e9a457 Author: ModelHub XC Date: Sun Jul 12 20:21:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SILMA-Kashif-2B-Instruct-v1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b56502c --- /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 +SILMA-Kashif-2B-Instruct-v1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +SILMA-Kashif-2B-Instruct-v1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SILMA-Kashif-2B-Instruct-v1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SILMA-Kashif-2B-Instruct-v1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SILMA-Kashif-2B-Instruct-v1.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SILMA-Kashif-2B-Instruct-v1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SILMA-Kashif-2B-Instruct-v1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SILMA-Kashif-2B-Instruct-v1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SILMA-Kashif-2B-Instruct-v1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SILMA-Kashif-2B-Instruct-v1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SILMA-Kashif-2B-Instruct-v1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SILMA-Kashif-2B-Instruct-v1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a502ccd --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: silma-ai/SILMA-Kashif-2B-Instruct-v1.0 +extra_gated_button_content: Acknowledge license +language: +- ar +- en +library_name: transformers +license: gemma +quantized_by: mradermacher +tags: +- rag +- qa +--- +## About + + + + + + +static quants of https://huggingface.co/silma-ai/SILMA-Kashif-2B-Instruct-v1.0 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/SILMA-Kashif-2B-Instruct-v1.0-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/SILMA-Kashif-2B-Instruct-v1.0-GGUF/resolve/main/SILMA-Kashif-2B-Instruct-v1.0.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/SILMA-Kashif-2B-Instruct-v1.0-GGUF/resolve/main/SILMA-Kashif-2B-Instruct-v1.0.Q3_K_S.gguf) | Q3_K_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/SILMA-Kashif-2B-Instruct-v1.0-GGUF/resolve/main/SILMA-Kashif-2B-Instruct-v1.0.Q3_K_M.gguf) | Q3_K_M | 1.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SILMA-Kashif-2B-Instruct-v1.0-GGUF/resolve/main/SILMA-Kashif-2B-Instruct-v1.0.Q3_K_L.gguf) | Q3_K_L | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/SILMA-Kashif-2B-Instruct-v1.0-GGUF/resolve/main/SILMA-Kashif-2B-Instruct-v1.0.IQ4_XS.gguf) | IQ4_XS | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/SILMA-Kashif-2B-Instruct-v1.0-GGUF/resolve/main/SILMA-Kashif-2B-Instruct-v1.0.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SILMA-Kashif-2B-Instruct-v1.0-GGUF/resolve/main/SILMA-Kashif-2B-Instruct-v1.0.Q4_K_M.gguf) | Q4_K_M | 1.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SILMA-Kashif-2B-Instruct-v1.0-GGUF/resolve/main/SILMA-Kashif-2B-Instruct-v1.0.Q5_K_S.gguf) | Q5_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/SILMA-Kashif-2B-Instruct-v1.0-GGUF/resolve/main/SILMA-Kashif-2B-Instruct-v1.0.Q5_K_M.gguf) | Q5_K_M | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/SILMA-Kashif-2B-Instruct-v1.0-GGUF/resolve/main/SILMA-Kashif-2B-Instruct-v1.0.Q6_K.gguf) | Q6_K | 2.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SILMA-Kashif-2B-Instruct-v1.0-GGUF/resolve/main/SILMA-Kashif-2B-Instruct-v1.0.Q8_0.gguf) | Q8_0 | 2.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SILMA-Kashif-2B-Instruct-v1.0-GGUF/resolve/main/SILMA-Kashif-2B-Instruct-v1.0.f16.gguf) | f16 | 5.3 | 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/SILMA-Kashif-2B-Instruct-v1.0.IQ4_XS.gguf b/SILMA-Kashif-2B-Instruct-v1.0.IQ4_XS.gguf new file mode 100644 index 0000000..7d27524 --- /dev/null +++ b/SILMA-Kashif-2B-Instruct-v1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:772daa327e2e46f3b021ff9c401b64de73896b0df55ace6f74d03682389efa32 +size 1576204512 diff --git a/SILMA-Kashif-2B-Instruct-v1.0.Q2_K.gguf b/SILMA-Kashif-2B-Instruct-v1.0.Q2_K.gguf new file mode 100644 index 0000000..a063faf --- /dev/null +++ b/SILMA-Kashif-2B-Instruct-v1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18656b716c3d89e528e596b583b5bab67796ba83392bddcfb28f9966bbc2e3a2 +size 1229830368 diff --git a/SILMA-Kashif-2B-Instruct-v1.0.Q3_K_L.gguf b/SILMA-Kashif-2B-Instruct-v1.0.Q3_K_L.gguf new file mode 100644 index 0000000..25efd78 --- /dev/null +++ b/SILMA-Kashif-2B-Instruct-v1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c3c686ec877f658a03e32ff8bc3940aec9ba38f5947ad95cfa851ae072698cf +size 1550436576 diff --git a/SILMA-Kashif-2B-Instruct-v1.0.Q3_K_M.gguf b/SILMA-Kashif-2B-Instruct-v1.0.Q3_K_M.gguf new file mode 100644 index 0000000..90769ca --- /dev/null +++ b/SILMA-Kashif-2B-Instruct-v1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:879d5a4c2bca836a41b1094af6e3a1a821bd6713a8f4a3c60b6d1a1b116f548a +size 1461668064 diff --git a/SILMA-Kashif-2B-Instruct-v1.0.Q3_K_S.gguf b/SILMA-Kashif-2B-Instruct-v1.0.Q3_K_S.gguf new file mode 100644 index 0000000..fbc009a --- /dev/null +++ b/SILMA-Kashif-2B-Instruct-v1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:459d882ddfa2caa500ab32f60507a0e75497d4a9022dd87c3dd219ce3263eb7a +size 1360660704 diff --git a/SILMA-Kashif-2B-Instruct-v1.0.Q4_K_M.gguf b/SILMA-Kashif-2B-Instruct-v1.0.Q4_K_M.gguf new file mode 100644 index 0000000..ab64c1e --- /dev/null +++ b/SILMA-Kashif-2B-Instruct-v1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09171ba64ae008778bcd0c0a9d05d3905b0fa6e39008592c6325c0100e306ad +size 1708583136 diff --git a/SILMA-Kashif-2B-Instruct-v1.0.Q4_K_S.gguf b/SILMA-Kashif-2B-Instruct-v1.0.Q4_K_S.gguf new file mode 100644 index 0000000..2f3b604 --- /dev/null +++ b/SILMA-Kashif-2B-Instruct-v1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4829e14d51971cacb192698894cca8399d7ad42c5e14374376077c1ff9bbee2 +size 1638652128 diff --git a/SILMA-Kashif-2B-Instruct-v1.0.Q5_K_M.gguf b/SILMA-Kashif-2B-Instruct-v1.0.Q5_K_M.gguf new file mode 100644 index 0000000..9b16798 --- /dev/null +++ b/SILMA-Kashif-2B-Instruct-v1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a87df931e06622f94561ffe63d26400460e71315608f1a2cdfae0ac924e01c4 +size 1923279072 diff --git a/SILMA-Kashif-2B-Instruct-v1.0.Q5_K_S.gguf b/SILMA-Kashif-2B-Instruct-v1.0.Q5_K_S.gguf new file mode 100644 index 0000000..6ec295d --- /dev/null +++ b/SILMA-Kashif-2B-Instruct-v1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbc5b45d00ef7a9675d81d884c0e407e88e808a71994aee574a57ff7d0ff21ac +size 1882544352 diff --git a/SILMA-Kashif-2B-Instruct-v1.0.Q6_K.gguf b/SILMA-Kashif-2B-Instruct-v1.0.Q6_K.gguf new file mode 100644 index 0000000..3f850f8 --- /dev/null +++ b/SILMA-Kashif-2B-Instruct-v1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4d9c8159c3f891a0ecce1f4b605ebb6f3e8f0107a93fb7fff73081c00163971 +size 2151393504 diff --git a/SILMA-Kashif-2B-Instruct-v1.0.Q8_0.gguf b/SILMA-Kashif-2B-Instruct-v1.0.Q8_0.gguf new file mode 100644 index 0000000..407e588 --- /dev/null +++ b/SILMA-Kashif-2B-Instruct-v1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:202b9ab19d2cda9b4eb1e82d853fe1092502ae57ccb5d04a7a991b78cf36a216 +size 2784495840 diff --git a/SILMA-Kashif-2B-Instruct-v1.0.f16.gguf b/SILMA-Kashif-2B-Instruct-v1.0.f16.gguf new file mode 100644 index 0000000..6446e9e --- /dev/null +++ b/SILMA-Kashif-2B-Instruct-v1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6f994aa5a76e199437c5c02c1458482d11a80730c5ca511f511636a2ba7c3bf +size 5235214560