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 +1,51 @@
+---
+license: cc-by-4.0
+base_model: hiieu/halong_embedding
+language: ["vi"]
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+inference: false
+---
+
+# `hiieu/halong_embedding` in GGUF format
+
+original: https://huggingface.co/hiieu/halong_embedding
+
+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/hiieu/halong_embedding models/tmp
+huggingface-cli download intfloat/multilingual-e5-base sentencepiece.bpe.model --local-dir 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 halong-embedding-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 512 -m model-q5_k_m.gguf
+```

model-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4675ee972142e8d697d3252a5e75fd5fcf38eae30702b7edf43c2d8e137e211
+size 562765792

model-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5402c0f0210ddbd6dfe9f8ec48ac079ce6f410501228537370dc81675f8527f2
+size 562765792

model-f32.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa77076af3abf138c1acdc3229e3f29d93b795e7620508f197254bcbba32e32d
+size 1116638176

model-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:619c5b87e4ba33fe4a2d862ad341cc956a6b0baf3d0b613b1d239e106b892b10
+size 218732352

model-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfde0699ceb1fa4f4a07f9d507b032b02d7b8aab2e960040f3f6332dc03738b0
+size 214760256

model-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68171ad40f84b25288b347469147f3e9bf18b5b9d5e0a731b74b0a199deb1fea
+size 227137344

model-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59a742f2e225fab6c0fb5f4689d216aa352d69c9bc29a1a6b7d0dbbeb73ccfaa
+size 224787264

model-q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8772f28a0f5f72254bc1ac3f21f801fa9b032ca405a43b562b10d32dd8bc934c
+size 236067648

model-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91a4d02d544dd90dd04692e73641e89c1a383fce54af813ecdf20124d3973230
+size 303138112