Hugging Face's logo

FastFlowLM
/
Llama-3.2-3B-NPU2

Text Generation
English
llama
llama-3.2
AMD
Ryzen
NPU
conversational
Model card Files
xet
Community
AlfredXu2 commited on
Commit
91ca36a
·
1 Parent(s): 8ea4f54

prefill_supported

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 +1 -1
  6. lm_head.xclbin +1 -1
  7. mm.xclbin +3 -0
.gitattributes CHANGED
@@ -2,3 +2,6 @@ tokenizer.json filter=lfs diff=lfs merge=lfs -text
2
  model.q4nx 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
  model.q4nx 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 sha256:5a83098ca9a3392330e666c7fe2d1bc155d12b0226fa5fa75e973cf0c14ef558
3
+ size 527083
config.json CHANGED
@@ -37,5 +37,8 @@
37
  "use_cache": true,
38
  "vocab_size": 128256,
39
  "addr_qk": 9216,
40
- "addr_kv": 34304
 
 
 
41
  }
 
37
  "use_cache": true,
38
  "vocab_size": 128256,
39
  "addr_qk": 9216,
40
+ "addr_kv": 34304,
41
+ "addr_l_begin_mha": 54016,
42
+ "addr_l_end_mha": 25344,
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:d33bb9549061937d2b5ecadec22b6ee257500edb6c4b6980890a0e36d19e9ed7
3
  size 331003
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d28f0aaddb26b79cab28b425866b4e8f7aebda47bb1e718049d1ac7f567d3be
3
  size 331003
lm_head.xclbin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28b4bab3cc798c0ce0d149be30b5495ec79bee5e711614c4770b71445917c2bd
3
  size 152843
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c4dbf0fbc075344ced55e26912d516ba9e797b29597088b12e357fda06e80c0
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