Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,10 @@ 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
+snowflake-arctic-embed-m-v1.5-F16.gguf filter=lfs diff=lfs merge=lfs -text
+snowflake-arctic-embed-m-v1.5-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+snowflake-arctic-embed-m-v1.5-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
+snowflake-arctic-embed-m-v1.5-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+snowflake-arctic-embed-m-v1.5-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+snowflake-arctic-embed-m-v1.5-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+snowflake-arctic-embed-m-v1.5-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,34 @@
+# yixuan-chia/snowflake-arctic-embed-m-v1.5-GGUF
+This model was converted to GGUF format from [`Snowflake/snowflake-arctic-embed-m-v1.5`](https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v1.5) using llama.cpp.
+Refer to the [original model card](https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v1.5) for more details on the model.
+## Use with llama.cpp
+Install llama.cpp through brew (works on Mac and Linux)
+```bash
+brew install llama.cpp
+```
+Invoke the llama.cpp server or the CLI.
+### CLI:
+```bash
+llama-cli --hf-repo yixuan-chia/snowflake-arctic-embed-m-v1.5-GGUF --hf-file snowflake-arctic-embed-m-v1.5-q8_0.gguf -p "The meaning to life and the universe is"
+```
+### Server:
+```bash
+llama-server --hf-repo yixuan-chia/snowflake-arctic-embed-m-v1.5-GGUF --hf-file snowflake-arctic-embed-m-v1.5-q8_0.gguf -c 2048
+```
+Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
+Step 1: Clone llama.cpp from GitHub.
+```
+git clone https://github.com/ggerganov/llama.cpp
+```
+Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
+```
+cd llama.cpp && LLAMA_CURL=1 make
+```
+Step 3: Run inference through the main binary.
+```
+./llama-cli --hf-repo yixuan-chia/snowflake-arctic-embed-m-v1.5-GGUF --hf-file snowflake-arctic-embed-m-v1.5-q8_0.gguf -p "The meaning to life and the universe is"
+```
+or 
+```
+./llama-server --hf-repo yixuan-chia/snowflake-arctic-embed-m-v1.5-GGUF --hf-file snowflake-arctic-embed-m-v1.5-q8_0.gguf -c 2048
+```

snowflake-arctic-embed-m-v1.5-F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ece140d563b01d1e0cdbf836d5ac002c0a1e5bb254540177f4f4c4ae0793853a
+size 219454752

snowflake-arctic-embed-m-v1.5-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96a9ef4ba8b16c514e926b5675c7ddc3f28f9cd73b7c3a0b5a7ac208ce46aa40
+size 69708256

snowflake-arctic-embed-m-v1.5-Q4_0_4_8.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:993cb14d1f22fba4a80b584c6dd7735626d369dd703d727f7d36bbee12234473
+size 69708256

snowflake-arctic-embed-m-v1.5-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3e684cd112492cd51c9b1276252810f03f4d0ecb1c12998799edab9e3eceec4
+size 74270176

snowflake-arctic-embed-m-v1.5-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7afb109db04a61dfe1746d82744302d2f52b71d92e7112d501623b43fb30cfd3
+size 80325088

snowflake-arctic-embed-m-v1.5-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a38f3ad36b36a65736b77fb39e7e36ecac25173f306e006fd1e2ddd1023b3317
+size 82675168

snowflake-arctic-embed-m-v1.5-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1073b6711706f55b451efe6c3ecf7398bf93c8c3b9b2df918673df9b77146a34
+size 117852672