From db7bffd2ae2ab4cbe4888072e5c3a7ea345e5a11 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 28 Sep 2026 05:43:17 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF Source: Original Platform --- .gitattributes | 57 ++++++++++++++ README.md | 74 +++++++++++++++++++ bangla-llama-7b-instruct-v0.1.i1-IQ1_M.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-IQ1_S.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-IQ2_M.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-IQ2_S.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-IQ2_XS.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-IQ2_XXS.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-IQ3_M.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-IQ3_S.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-IQ3_XS.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-IQ3_XXS.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-IQ4_XS.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-Q2_K.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-Q3_K_L.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-Q3_K_M.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-Q3_K_S.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-Q4_0.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-Q4_K_M.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-Q4_K_S.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-Q5_K_M.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-Q5_K_S.gguf | 3 + bangla-llama-7b-instruct-v0.1.i1-Q6_K.gguf | 3 + imatrix.dat | 3 + 24 files changed, 197 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 bangla-llama-7b-instruct-v0.1.i1-IQ1_M.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-IQ1_S.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-IQ2_M.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-IQ2_S.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-IQ2_XS.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-IQ2_XXS.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-IQ3_M.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-IQ3_S.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-IQ3_XS.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-IQ3_XXS.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-IQ4_XS.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-Q2_K.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-Q3_K_L.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-Q3_K_M.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-Q3_K_S.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-Q4_0.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-Q4_K_M.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-Q4_K_S.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-Q5_K_M.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-Q5_K_S.gguf create mode 100644 bangla-llama-7b-instruct-v0.1.i1-Q6_K.gguf create mode 100644 imatrix.dat diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d396c95 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +bangla-llama-7b-instruct-v0.1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a2c6088 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: BanglaLLM/bangla-llama-7b-instruct-v0.1 +language: +- bn +- en +library_name: transformers +license: llama2 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/BanglaLLM/bangla-llama-7b-instruct-v0.1 + + +static quants are available at https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-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/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-IQ1_M.gguf) | i1-IQ1_M | 1.8 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-IQ2_M.gguf) | i1-IQ2_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-Q2_K.gguf) | i1-Q2_K | 2.7 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-IQ3_S.gguf) | i1-IQ3_S | 3.1 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.1 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-IQ3_M.gguf) | i1-IQ3_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-Q4_0.gguf) | i1-Q4_0 | 4.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.1 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/bangla-llama-7b-instruct-v0.1-i1-GGUF/resolve/main/bangla-llama-7b-instruct-v0.1.i1-Q6_K.gguf) | i1-Q6_K | 5.8 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/bangla-llama-7b-instruct-v0.1.i1-IQ1_M.gguf b/bangla-llama-7b-instruct-v0.1.i1-IQ1_M.gguf new file mode 100644 index 0000000..36ff7ea --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4220ec5788f0d5942d94534cf1a4fb0ac6939b759416eef4b538040e9c2e4743 +size 1728232672 diff --git a/bangla-llama-7b-instruct-v0.1.i1-IQ1_S.gguf b/bangla-llama-7b-instruct-v0.1.i1-IQ1_S.gguf new file mode 100644 index 0000000..6350b31 --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c3ff368afb8d865bb1ad35a9e702f9318c9600ea0dabbc6b9276837d8a34446 +size 1605844192 diff --git a/bangla-llama-7b-instruct-v0.1.i1-IQ2_M.gguf b/bangla-llama-7b-instruct-v0.1.i1-IQ2_M.gguf new file mode 100644 index 0000000..f926779 --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f0e5e7ec89f21de510b1e3455da5ff49200348e48fa9d9fceeb44580c348943 +size 2444682496 diff --git a/bangla-llama-7b-instruct-v0.1.i1-IQ2_S.gguf b/bangla-llama-7b-instruct-v0.1.i1-IQ2_S.gguf new file mode 100644 index 0000000..09daa21 --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b313b158fe142c30eea6b920be34428e4e95757a504915a699085b8957a358e4 +size 2281497856 diff --git a/bangla-llama-7b-instruct-v0.1.i1-IQ2_XS.gguf b/bangla-llama-7b-instruct-v0.1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..ab04c84 --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:064f1356011d35722a50d148707492c3be9d2cf59d58413e8d0766324e020373 +size 2112175328 diff --git a/bangla-llama-7b-instruct-v0.1.i1-IQ2_XXS.gguf b/bangla-llama-7b-instruct-v0.1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..2cc946b --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d883e527d8a88f449f0dc7c516e19ecb365c785ee2929d984a8f52e8d7afae88 +size 1932213472 diff --git a/bangla-llama-7b-instruct-v0.1.i1-IQ3_M.gguf b/bangla-llama-7b-instruct-v0.1.i1-IQ3_M.gguf new file mode 100644 index 0000000..eec5714 --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8208e580994811b41bf8355d5a1751aba61e7a2fb221e7a3e4165608fcd7a73 +size 3209826208 diff --git a/bangla-llama-7b-instruct-v0.1.i1-IQ3_S.gguf b/bangla-llama-7b-instruct-v0.1.i1-IQ3_S.gguf new file mode 100644 index 0000000..50ac96a --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf04182fab790ba6beaa2dc2365af1fbbe2c3dcc2afd5bfd0306c73c7c46266 +size 3043266464 diff --git a/bangla-llama-7b-instruct-v0.1.i1-IQ3_XS.gguf b/bangla-llama-7b-instruct-v0.1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..47c4be5 --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80830892e84ce36cc68d08c7c7ca72c75b4d7760469ad7f880a7ee370b62f787 +size 2891485088 diff --git a/bangla-llama-7b-instruct-v0.1.i1-IQ3_XXS.gguf b/bangla-llama-7b-instruct-v0.1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..362206a --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33ddc60a1a8c4114115491d37926fa4b8935e359a818eb64bdcfba30ec37e2db +size 2670322944 diff --git a/bangla-llama-7b-instruct-v0.1.i1-IQ4_XS.gguf b/bangla-llama-7b-instruct-v0.1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e5179f2 --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d57b9e838efe7b9937c0de4efe1094aff834ecef3b4d00b9c3b225ec8170e5e6 +size 3721967552 diff --git a/bangla-llama-7b-instruct-v0.1.i1-Q2_K.gguf b/bangla-llama-7b-instruct-v0.1.i1-Q2_K.gguf new file mode 100644 index 0000000..be10ef8 --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1f974920d2ff2d1f554edaf3bd1e025053ee93b1a9ae550c2a281c3aa920341 +size 2620155776 diff --git a/bangla-llama-7b-instruct-v0.1.i1-Q3_K_L.gguf b/bangla-llama-7b-instruct-v0.1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..3fd9e9d --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e77b914086189447f7b37796540d626c0120007baa86b11f1b8956d2a7825bb +size 3692072864 diff --git a/bangla-llama-7b-instruct-v0.1.i1-Q3_K_M.gguf b/bangla-llama-7b-instruct-v0.1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..9573a7a --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3833f7bdb4ef7922ee871716ea4162202eb0a2aa5217352387e663332604525b +size 3392966560 diff --git a/bangla-llama-7b-instruct-v0.1.i1-Q3_K_S.gguf b/bangla-llama-7b-instruct-v0.1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..5fb80b0 --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a348938e843027136f1117e6518799d03904faf773e92f68872cd35cdefd1b9 +size 3043266464 diff --git a/bangla-llama-7b-instruct-v0.1.i1-Q4_0.gguf b/bangla-llama-7b-instruct-v0.1.i1-Q4_0.gguf new file mode 100644 index 0000000..1dcb90e --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1df67b9b48e213ca977f58850e0fe21744ed6d32814c3a4a79fef7efc35c8a04 +size 3942070848 diff --git a/bangla-llama-7b-instruct-v0.1.i1-Q4_K_M.gguf b/bangla-llama-7b-instruct-v0.1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..2081b92 --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6957626feb976e1288c11aa9550f77e8324bd32abc6dae2149ed5c26ff825f9 +size 4185995840 diff --git a/bangla-llama-7b-instruct-v0.1.i1-Q4_K_S.gguf b/bangla-llama-7b-instruct-v0.1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..8f184c3 --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a02bf097d14efce885a6dfc2aa1a6b4f5e3a2ef6317199dfc5cdd091418efef5 +size 3961731648 diff --git a/bangla-llama-7b-instruct-v0.1.i1-Q5_K_M.gguf b/bangla-llama-7b-instruct-v0.1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..eb7be8d --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd09ac3933cc5ccfcfe56c88a449eb7c1e82aa450a2f481fc4d1906efa43ca69 +size 4897588288 diff --git a/bangla-llama-7b-instruct-v0.1.i1-Q5_K_S.gguf b/bangla-llama-7b-instruct-v0.1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..4f19dcd --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24f872d088a355392f5bfed0e3938a57de66f5598183df3b961c61c79f8cd32e +size 4766123072 diff --git a/bangla-llama-7b-instruct-v0.1.i1-Q6_K.gguf b/bangla-llama-7b-instruct-v0.1.i1-Q6_K.gguf new file mode 100644 index 0000000..1fcf2e4 --- /dev/null +++ b/bangla-llama-7b-instruct-v0.1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e97d47a9c2d7df392abeecbd38049df77f0c84e03a79d4b450fd9dc082af0c5 +size 5653655264 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..edf119b --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bd2b14952894b65b495d1279a0f013711612d371b017281ea2c7b4dd15e9d25 +size 4562170