Hugging Face's logo

FastFlowLM
/
Llama-3.1-8B-NPU2

Text Generation
English
llama
llama-3.1
AMD
Ryzen
NPU
conversational
Model card Files
xet
Community
AlfredXu2 commited on
Commit
179fd34
·
1 Parent(s): a3e5801

support_prefill

Browse files
Files changed (7) hide show
  1. .gitattributes +3 -0
  2. attn.xclbin +3 -0
  3. config.json +4 -1
  4. dequant.xclbin +3 -0
  5. layer.xclbin +2 -2
  6. lm_head.xclbin +1 -1
  7. mm.xclbin +3 -0
.gitattributes CHANGED
@@ -2,3 +2,6 @@ model.q4nx filter=lfs diff=lfs merge=lfs -text
2
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
3
  layer.xclbin filter=lfs diff=lfs merge=lfs -text
4
  lm_head.xclbin filter=lfs diff=lfs merge=lfs -text
 
 
 
 
2
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
3
  layer.xclbin filter=lfs diff=lfs merge=lfs -text
4
  lm_head.xclbin filter=lfs diff=lfs merge=lfs -text
5
+ attn.xclbin filter=lfs diff=lfs merge=lfs -text
6
+ dequant.xclbin filter=lfs diff=lfs merge=lfs -text
7
+ mm.xclbin filter=lfs diff=lfs merge=lfs -text
attn.xclbin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb8e7bef68c19797d9f57c163ba8943fa3bd474af6c9e82c0c4a7554852afd4a
3
+ size 698331
config.json CHANGED
@@ -37,5 +37,8 @@
37
  "use_cache": true,
38
  "vocab_size": 128256,
39
  "addr_qk": 9216,
40
- "addr_kv": 34816
 
 
 
41
  }
 
37
  "use_cache": true,
38
  "vocab_size": 128256,
39
  "addr_qk": 9216,
40
+ "addr_kv": 34816,
41
+ "addr_l_begin_mha": 54272,
42
+ "addr_l_end_mha": 25600,
43
+ "addr_kk": 45056
44
  }
dequant.xclbin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db8cae1f4d64509ee9b107c78679a1e8c02cdc2f48322e93613f794ec66ab926
3
+ size 116715
layer.xclbin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdbe167429785c0b5df9887a9239b7ee29e10101d290a31b7ed511ce0d20c1b1
3
- size 332347
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f637754dc209cae44bb2e671c490b3cf87c68930109af589b25518522c865c20
3
+ size 332459
lm_head.xclbin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cff5585c779c53fef9a3631a9f387d386c340d59d22a4e2fe4667f0a5685f956
3
  size 152843
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d2ebc16daf6a75e4bdefa499fccccc2bafd7c122bf4a1c3e73d66e8538f592d
3
  size 152843
mm.xclbin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26dcd71ca8a438a9f0621e18c4703a10f19068d7f580589a0f03834ec86d18f3
3
+ size 179195