Hugging Face's logo

ArunKr
/
LLM-Models

GGUF
Inference Endpoints
Model card Files Community
Arun Kumar Tiwary commited on
Commit
ae919d8
·
verified ·
1 Parent(s): 9140e55

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. .gitattributes +12 -0
  2. Meta-Llama-3-70B_fp16_shards/-00001-of-00006.gguf +3 -0
  3. Meta-Llama-3-70B_fp16_shards/-00002-of-00006.gguf +3 -0
  4. Meta-Llama-3-70B_fp16_shards/-00003-of-00006.gguf +3 -0
  5. Meta-Llama-3-70B_fp16_shards/-00004-of-00006.gguf +3 -0
  6. Meta-Llama-3-70B_fp16_shards/-00005-of-00006.gguf +3 -0
  7. Meta-Llama-3-70B_fp16_shards/-00006-of-00006.gguf +3 -0
  8. Meta-Llama-3-8B-Instruct_fp16_Q4_K_M_shards/-00001-of-00003.gguf +3 -0
  9. Meta-Llama-3-8B-Instruct_fp16_Q4_K_M_shards/-00002-of-00003.gguf +3 -0
  10. Meta-Llama-3-8B-Instruct_fp16_Q4_K_M_shards/-00003-of-00003.gguf +3 -0
  11. convert.sh +3 -0
  12. download.sh +3 -0
  13. gguf-split +3 -0
  14. main +3 -0
  15. quantize +3 -0
  16. quantize.sh +1 -0
  17. run_gguf.sh +3 -0
  18. upload.py +8 -0
.gitattributes CHANGED
@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Meta-Llama-3-70B_fp16_shards/-00001-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Meta-Llama-3-70B_fp16_shards/-00002-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Meta-Llama-3-70B_fp16_shards/-00003-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Meta-Llama-3-70B_fp16_shards/-00004-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Meta-Llama-3-70B_fp16_shards/-00005-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Meta-Llama-3-70B_fp16_shards/-00006-of-00006.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Meta-Llama-3-8B-Instruct_fp16_Q4_K_M_shards/-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Meta-Llama-3-8B-Instruct_fp16_Q4_K_M_shards/-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Meta-Llama-3-8B-Instruct_fp16_Q4_K_M_shards/-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
45
+ gguf-split filter=lfs diff=lfs merge=lfs -text
46
+ main filter=lfs diff=lfs merge=lfs -text
47
+ quantize filter=lfs diff=lfs merge=lfs -text
Meta-Llama-3-70B_fp16_shards/-00001-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f2237fbc58d038cb0f436ea19a6da8a9782c7d7b1a25e8a62788fa3437fa308
3
+ size 26067986816
Meta-Llama-3-70B_fp16_shards/-00002-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6784fb148bd8eb5c4b7d17692d2bb82c9cde73199a94b7298e04d6590d8587a7
3
+ size 24898313824
Meta-Llama-3-70B_fp16_shards/-00003-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9ba6a12166b98d8893125636c5a9150166de6fb6c77c83d2471bfb67dfc2c41
3
+ size 24428584544
Meta-Llama-3-70B_fp16_shards/-00004-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:881eb8fbd3e1471f013857b82847976cd56e84fea064e6728d81b19ad77b95aa
3
+ size 24109784672
Meta-Llama-3-70B_fp16_shards/-00005-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94b6fc47be4848e0ed78bf8fa19c2e7e30dbcab5704cba27ca653976108647f6
3
+ size 24109784672
Meta-Llama-3-70B_fp16_shards/-00006-of-00006.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7858be011be80f826cdb7c673e502a01ac04c18f3a5392c93325c4c1ecca08e6
3
+ size 17503458240
Meta-Llama-3-8B-Instruct_fp16_Q4_K_M_shards/-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98690f3d11533142dc9eee68f0ad84314dbbd0ffd87e5a42436bd13ce1d0af4d
3
+ size 2134911840
Meta-Llama-3-8B-Instruct_fp16_Q4_K_M_shards/-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee304f00ba0108d18168282b7354a094fe04402bd51ca01d5163033f08c33941
3
+ size 1880333920
Meta-Llama-3-8B-Instruct_fp16_Q4_K_M_shards/-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e68c199179dc76e5362031e96310f53b9c67c2e70dcca0620f8eed1a9b67a33f
3
+ size 905488544
convert.sh ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 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
2
+ #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
3
+ #python llm/llama.cpp/convert.py ./llama2_model --outtype f16 --outfile output/converted_f16.bin
download.sh ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ # huggingface-cli download meta-llama/Meta-Llama-3-8B-Instruct --local-dir model
2
+ #huggingface-cli download meta-llama/Llama-2-7b-chat-hf --local-dir llama2_model
3
+ huggingface-cli download meta-llama/Meta-Llama-3-70B --local-dir models/meta-llama/Meta-Llama-3-70B
gguf-split ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57a7232df2a25f491d0bbaaea3e7c9b105059917f45fe5567dac63d7dd67a35f
3
+ size 2706592
main ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51f84777134fc9bce0629b439728a4f8646f4b762530ca6a3a1a3eb279c00658
3
+ size 2754104
quantize ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:902554ec6ae6c085f6fc2ba7958ba031046fb46748315f9ce639d58673772c75
3
+ size 2718304
quantize.sh ADDED
@@ -0,0 +1 @@
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ ./main -m output/Meta-Llama-3-70B_fp16.bin -p "hi"
2
+ #./main -m output/Meta-Llama-3-8B-Instruct_fp16.bin -p "hi"
3
+ #./main -m output/converted_f16.bin -p "hi"
upload.py ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ from huggingface_hub import HfApi
2
+ api = HfApi()
3
+
4
+ api.upload_folder(
5
+ folder_path="containers_with_ha_proxy",
6
+ repo_id="Arun1982/llama2-docker-compose",
7
+ repo_type="model",
8
+ )