Hugging Face's logo

MaziyarPanahi
/
Llama-3.1-Nemotron-70B-Instruct-HF-GGUF

Text Generation
GGUF
quantized
2-bit
3-bit
4-bit precision
5-bit
6-bit
8-bit precision
GGUF
imatrix
conversational
Model card Files Community
2

[WIP] Upload folder using huggingface_hub (multi-commit b54a82fab5266c8a35a9c3a129d469db5193b8c155e4353e08fe5b0036c1cfb8)

#1
by MaziyarPanahi - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+52
-0
Files changed (14) hide show
  1. .gitattributes +13 -0
  2. Llama-3.1-Nemotron-70B-Instruct-HF.IQ1_M.gguf +3 -0
  3. Llama-3.1-Nemotron-70B-Instruct-HF.IQ1_S.gguf +3 -0
  4. Llama-3.1-Nemotron-70B-Instruct-HF.IQ2_XS.gguf +3 -0
  5. Llama-3.1-Nemotron-70B-Instruct-HF.IQ3_XS.gguf +3 -0
  6. Llama-3.1-Nemotron-70B-Instruct-HF.IQ4_XS.gguf +3 -0
  7. Llama-3.1-Nemotron-70B-Instruct-HF.Q2_K.gguf +3 -0
  8. Llama-3.1-Nemotron-70B-Instruct-HF.Q3_K_L.gguf +3 -0
  9. Llama-3.1-Nemotron-70B-Instruct-HF.Q3_K_M.gguf +3 -0
  10. Llama-3.1-Nemotron-70B-Instruct-HF.Q3_K_S.gguf +3 -0
  11. Llama-3.1-Nemotron-70B-Instruct-HF.Q4_K_M.gguf +3 -0
  12. Llama-3.1-Nemotron-70B-Instruct-HF.Q4_K_S.gguf +3 -0
  13. Llama-3.1-Nemotron-70B-Instruct-HF.Q5_K_M.gguf +3 -0
  14. Llama-3.1-Nemotron-70B-Instruct-HF.Q5_K_S.gguf +3 -0
.gitattributes CHANGED
@@ -33,3 +33,16 @@ 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
+ Llama-3.1-Nemotron-70B-Instruct-HF.IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Llama-3.1-Nemotron-70B-Instruct-HF.IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Llama-3.1-Nemotron-70B-Instruct-HF.IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Llama-3.1-Nemotron-70B-Instruct-HF.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Llama-3.1-Nemotron-70B-Instruct-HF.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Llama-3.1-Nemotron-70B-Instruct-HF.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Llama-3.1-Nemotron-70B-Instruct-HF.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Llama-3.1-Nemotron-70B-Instruct-HF.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Llama-3.1-Nemotron-70B-Instruct-HF.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Llama-3.1-Nemotron-70B-Instruct-HF.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Llama-3.1-Nemotron-70B-Instruct-HF.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Llama-3.1-Nemotron-70B-Instruct-HF.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
48
+ Llama-3.1-Nemotron-70B-Instruct-HF.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-Nemotron-70B-Instruct-HF.IQ1_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41f313c3c7d98edd9a6de3fc9818f45c7d2610b764b6a4aecd47f20c7bfb3ce8
3
+ size 16751201120
Llama-3.1-Nemotron-70B-Instruct-HF.IQ1_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ec0579ef6c323aca2a340605219d41afa2f226cbfd5df6f20a00f5c7dd14dcd
3
+ size 15343487840
Llama-3.1-Nemotron-70B-Instruct-HF.IQ2_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a8e2332d9268854da9d38357c32442e9343ee2c734d5f35df97c99e1d8030e4
3
+ size 21142113120
Llama-3.1-Nemotron-70B-Instruct-HF.IQ3_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:699f9dfb81128cda313baf8f2df80c869d6dbfbac2436c08e7d67500701b217c
3
+ size 29307734880
Llama-3.1-Nemotron-70B-Instruct-HF.IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee5d989b33d1e2a3fa362296d7aa6bddd7eaa6e66696cf4885cf361f59f2efbc
3
+ size 37902666592
Llama-3.1-Nemotron-70B-Instruct-HF.Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e59ad4007ac9f53f4ce2119866e2e3fd4b78365db970ed308cb2d1655212985c
3
+ size 26375113568
Llama-3.1-Nemotron-70B-Instruct-HF.Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8787efc0c3677b7aedf735bea0b5bc174fc555ee817f095b3d86b6365ace51c
3
+ size 37140597600
Llama-3.1-Nemotron-70B-Instruct-HF.Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c47f5c84be68a3707005ac159a1ceec26cea11175ea72d6fba9ba8af72597a1
3
+ size 34267499360
Llama-3.1-Nemotron-70B-Instruct-HF.Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca7f046248173c26c2e9018975902531458414390e96ce65e33ee03deb16391d
3
+ size 30912056160
Llama-3.1-Nemotron-70B-Instruct-HF.Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:970b7de65a5f232304b18a76cf7434b7c83e8e119f99142f6df65e347e12aa39
3
+ size 42520398688
Llama-3.1-Nemotron-70B-Instruct-HF.Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8698bcaac7becfef800f1da37fc6e35995c91f50c4293337a46d0ab502049c8c
3
+ size 40347224928
Llama-3.1-Nemotron-70B-Instruct-HF.Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d20579232a93a97c4ea95e242a474c7d744fc3cb936678b8958ff7dab5b3295
3
+ size 49949821792
Llama-3.1-Nemotron-70B-Instruct-HF.Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:090e65dd4f48e6d62bf91f0fca0c31065fea9a5e3b4eb0e8d6269e5e73c63442
3
+ size 48657451872