Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,12 @@ saved_model/**/* 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
+model-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+model-f16.gguf filter=lfs diff=lfs merge=lfs -text
+model-f32.gguf filter=lfs diff=lfs merge=lfs -text
+model-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+model-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+model-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+model-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+model-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+model-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,50 @@
+---
+license: cc-by-4.0
+base_model: BAAI/bge-m3
+language: ["vi"]
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+inference: false
+---
+
+# `BAAI/bge-m3` in GGUF format
+
+original: https://huggingface.co/BAAI/bge-m3
+
+quantization:
+```bash
+REL=b3827  # can change to a later release
+wget https://github.com/ggerganov/llama.cpp/releases/download/$REL/llama-$REL-bin-ubuntu-x64.zip --content-disposition --continue &> /dev/null
+wget https://github.com/ggerganov/llama.cpp/archive/refs/tags/$REL.zip                           --content-disposition --continue &> /dev/null
+unzip -q llama-$REL-bin-ubuntu-x64.zip
+unzip -q llama.cpp-$REL.zip
+mv llama.cpp-$REL/* .
+rm -r llama.cpp-$REL/ llama-$REL-bin-ubuntu-x64.zip llama.cpp-$REL.zip
+pip install -q -r requirements.txt
+
+rm -rf models/tmp/
+git clone --depth=1 --single-branch https://huggingface.co/BAAI/bge-m3 models/tmp
+python convert_hf_to_gguf.py models/tmp/ --outfile model-f32.gguf --outtype f32
+
+build/bin/llama-quantize model-f32.gguf model-f16.gguf    f16    2> /dev/null
+build/bin/llama-quantize model-f32.gguf model-bf16.gguf   bf16   2> /dev/null
+build/bin/llama-quantize model-f32.gguf model-q8_0.gguf   q8_0   2> /dev/null
+build/bin/llama-quantize model-f32.gguf model-q6_k.gguf   q6_k   2> /dev/null
+build/bin/llama-quantize model-f32.gguf model-q5_k_m.gguf q5_k_m 2> /dev/null
+build/bin/llama-quantize model-f32.gguf model-q5_k_s.gguf q5_k_s 2> /dev/null
+build/bin/llama-quantize model-f32.gguf model-q4_k_m.gguf q4_k_m 2> /dev/null
+build/bin/llama-quantize model-f32.gguf model-q4_k_s.gguf q4_k_s 2> /dev/null
+
+rm -rf models/yolo/
+mkdir -p models/yolo
+mv model-*.gguf models/yolo/
+touch models/yolo/README.md
+huggingface-cli upload bge-m3-gguf models/yolo .
+```
+
+usage:
+```bash
+build/bin/llama-embedding -m model-q5_k_m.gguf -p "Cô ấy cười nói suốt cả ngày" --embd-output-format array 2> /dev/null
+# OR
+build/bin/llama-server --embedding -c 128 -m model-q5_k_m.gguf
+```

model-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:874b570fa474e29c3f6bfee48efa4f2f89ed5c0025fe881726e97ef661768ea2
+size 1157671200

model-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c
+size 1157671200

model-f32.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d925235eecc1c73cbbac5a268e6e8562c82bf341ca36f1c7465bdfd316e63518
+size 2273655072

model-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe3a00f9e92cc07f9745c69d25e17e234e1a7f8cde6e7ebe930dc7516e9accf
+size 437778496

model-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f141d3fdc26f5aab6e18712ba89841f948d1f668b1c3e20ca8bd1dbdd34030b
+size 423655488

model-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94b52ea5a93d9c9246a4e10cc8efb113267364451d57f59218f258b08966f536
+size 467662912

model-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90a9c29e7a70806c64f22ae277e4aad5766f7f9e118adfee9137b09fd5789dec
+size 459307072

model-q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df937a62eea9acbc6990f249558101c545931d72e4aa4e8a4cdbd462895b21b3
+size 499415104

model-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:950f4a8e5e19477a6d3c26d2f162233c20002c601f75e4b002e3239997821167
+size 634553760