Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,15 @@ 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
+Meta-Llama-3-70B_fp16_shards/-00001-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-70B_fp16_shards/-00002-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-70B_fp16_shards/-00003-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-70B_fp16_shards/-00004-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-70B_fp16_shards/-00005-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-70B_fp16_shards/-00006-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct_fp16_Q4_K_M_shards/-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct_fp16_Q4_K_M_shards/-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct_fp16_Q4_K_M_shards/-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+gguf-split filter=lfs diff=lfs merge=lfs -text
+main filter=lfs diff=lfs merge=lfs -text
+quantize filter=lfs diff=lfs merge=lfs -text

Meta-Llama-3-70B_fp16_shards/-00001-of-00006.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f2237fbc58d038cb0f436ea19a6da8a9782c7d7b1a25e8a62788fa3437fa308
+size 26067986816

Meta-Llama-3-70B_fp16_shards/-00002-of-00006.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6784fb148bd8eb5c4b7d17692d2bb82c9cde73199a94b7298e04d6590d8587a7
+size 24898313824

Meta-Llama-3-70B_fp16_shards/-00003-of-00006.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9ba6a12166b98d8893125636c5a9150166de6fb6c77c83d2471bfb67dfc2c41
+size 24428584544

Meta-Llama-3-70B_fp16_shards/-00004-of-00006.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881eb8fbd3e1471f013857b82847976cd56e84fea064e6728d81b19ad77b95aa
+size 24109784672

Meta-Llama-3-70B_fp16_shards/-00005-of-00006.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94b6fc47be4848e0ed78bf8fa19c2e7e30dbcab5704cba27ca653976108647f6
+size 24109784672

Meta-Llama-3-70B_fp16_shards/-00006-of-00006.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7858be011be80f826cdb7c673e502a01ac04c18f3a5392c93325c4c1ecca08e6
+size 17503458240

Meta-Llama-3-8B-Instruct_fp16_Q4_K_M_shards/-00001-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98690f3d11533142dc9eee68f0ad84314dbbd0ffd87e5a42436bd13ce1d0af4d
+size 2134911840

Meta-Llama-3-8B-Instruct_fp16_Q4_K_M_shards/-00002-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee304f00ba0108d18168282b7354a094fe04402bd51ca01d5163033f08c33941
+size 1880333920

Meta-Llama-3-8B-Instruct_fp16_Q4_K_M_shards/-00003-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e68c199179dc76e5362031e96310f53b9c67c2e70dcca0620f8eed1a9b67a33f
+size 905488544

convert.sh

@@ -0,0 +1,3 @@
+python llm/llama.cpp/convert-hf-to-gguf.py  /home/amd/workspace/Arun/data_dir/llamaCpp/ollama/models/meta-llama/Meta-Llama-3-70B --outtype f16 --outfile output/Meta-Llama-3-70B_fp16.bin
+#python llm/llama.cpp/convert-hf-to-gguf.py  models/meta-llama/llama3_model/ --outtype f16 --outfile output/Meta-Llama-3-8B-Instruct_fp16.bin
+#python llm/llama.cpp/convert.py ./llama2_model --outtype f16 --outfile output/converted_f16.bin

download.sh

@@ -0,0 +1,3 @@
+# huggingface-cli download  meta-llama/Meta-Llama-3-8B-Instruct --local-dir model 
+ #huggingface-cli download  meta-llama/Llama-2-7b-chat-hf --local-dir llama2_model 
+ huggingface-cli download   meta-llama/Meta-Llama-3-70B --local-dir models/meta-llama/Meta-Llama-3-70B

gguf-split

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57a7232df2a25f491d0bbaaea3e7c9b105059917f45fe5567dac63d7dd67a35f
+size 2706592

main

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51f84777134fc9bce0629b439728a4f8646f4b762530ca6a3a1a3eb279c00658
+size 2754104

quantize

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:902554ec6ae6c085f6fc2ba7958ba031046fb46748315f9ce639d58673772c75
+size 2718304

quantize.sh

@@ -0,0 +1 @@
+./quantize  ./Meta-Llama-3-8B-Instruct_fp16.bin output/Meta-Llama-3-8B-Instruct_fp16_Q4_K_M.bin Q4_K_M

run_gguf.sh

@@ -0,0 +1,3 @@
+./main -m output/Meta-Llama-3-70B_fp16.bin -p "hi"
+#./main -m output/Meta-Llama-3-8B-Instruct_fp16.bin -p "hi"
+#./main -m output/converted_f16.bin -p "hi"

upload.py

@@ -0,0 +1,8 @@
+from huggingface_hub import HfApi
+api = HfApi()
+
+api.upload_folder(
+    folder_path="containers_with_ha_proxy",
+    repo_id="Arun1982/llama2-docker-compose",
+    repo_type="model",
+)