Arun Kumar Tiwary
commited on
Commit
•
89e2fdc
1
Parent(s):
5903f80
Upload folder using huggingface_hub
Browse files- Meta-Llama-3-70B_fp16_Q3_K_S.bin +3 -0
- run_gguf.sh +3 -1
Meta-Llama-3-70B_fp16_Q3_K_S.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:768c31b519abda73053385e10077da8a2abb1f34a8c1349e29f6754f4ba35d2f
|
3 |
+
size 30912050240
|
run_gguf.sh
CHANGED
@@ -1,3 +1,5 @@
|
|
1 |
-
./main -m output/Meta-Llama-3-
|
|
|
|
|
2 |
#./main -m output/Meta-Llama-3-8B-Instruct_fp16.bin -p "hi"
|
3 |
#./main -m output/converted_f16.bin -p "hi"
|
|
|
1 |
+
./main -m output/Meta-Llama-3-70B_fp16_Q3_K_S.bin -p "hi"
|
2 |
+
#./main -m output/Meta-Llama-3-8B-Instruct_fp16_Q4_K_M.bin -p "hi"
|
3 |
+
#./main -m output/Meta-Llama-3-70B_fp16.bin -p "hi"
|
4 |
#./main -m output/Meta-Llama-3-8B-Instruct_fp16.bin -p "hi"
|
5 |
#./main -m output/converted_f16.bin -p "hi"
|