Hugging Face's logo

Esperanto
/
llama3.1-8b-Instruct-kvc-AWQ-int4-onnx

Text Generation
ONNX
text-generation-inference
llama
llama3
4-bit precision
AWQ
Model card Files Community
ericsorides commited on
Commit
4a00c78
·
1 Parent(s): 3b8db7c

Added model and tokenizer

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +4 -0
  2. model-fixed-dims.onnx +3 -0
  3. model.embed_tokens.weight +3 -0
  4. model.layers.0.input_layernorm.weight +3 -0
  5. model.layers.0.mlp.down_proj.qweight +3 -0
  6. model.layers.0.mlp.down_proj.qzeros +3 -0
  7. model.layers.0.mlp.down_proj.scales +3 -0
  8. model.layers.0.mlp.gate_proj.qweight +3 -0
  9. model.layers.0.mlp.gate_proj.qzeros +3 -0
  10. model.layers.0.mlp.gate_proj.scales +3 -0
  11. model.layers.0.mlp.up_proj.qweight +3 -0
  12. model.layers.0.mlp.up_proj.qzeros +3 -0
  13. model.layers.0.mlp.up_proj.scales +3 -0
  14. model.layers.0.post_attention_layernorm.weight +3 -0
  15. model.layers.0.self_attn.k_proj.qweight +3 -0
  16. model.layers.0.self_attn.k_proj.qzeros +3 -0
  17. model.layers.0.self_attn.k_proj.scales +3 -0
  18. model.layers.0.self_attn.o_proj.qweight +3 -0
  19. model.layers.0.self_attn.o_proj.qzeros +3 -0
  20. model.layers.0.self_attn.o_proj.scales +3 -0
  21. model.layers.0.self_attn.q_proj.qweight +3 -0
  22. model.layers.0.self_attn.q_proj.qzeros +3 -0
  23. model.layers.0.self_attn.q_proj.scales +3 -0
  24. model.layers.0.self_attn.v_proj.qweight +3 -0
  25. model.layers.0.self_attn.v_proj.qzeros +3 -0
  26. model.layers.0.self_attn.v_proj.scales +3 -0
  27. model.layers.1.input_layernorm.weight +3 -0
  28. model.layers.1.mlp.down_proj.qweight +3 -0
  29. model.layers.1.mlp.down_proj.qzeros +3 -0
  30. model.layers.1.mlp.down_proj.scales +3 -0
  31. model.layers.1.mlp.gate_proj.qweight +3 -0
  32. model.layers.1.mlp.gate_proj.qzeros +3 -0
  33. model.layers.1.mlp.gate_proj.scales +3 -0
  34. model.layers.1.mlp.up_proj.qweight +3 -0
  35. model.layers.1.mlp.up_proj.qzeros +3 -0
  36. model.layers.1.mlp.up_proj.scales +3 -0
  37. model.layers.1.post_attention_layernorm.weight +3 -0
  38. model.layers.1.self_attn.k_proj.qweight +3 -0
  39. model.layers.1.self_attn.k_proj.qzeros +3 -0
  40. model.layers.1.self_attn.k_proj.scales +3 -0
  41. model.layers.1.self_attn.o_proj.qweight +3 -0
  42. model.layers.1.self_attn.o_proj.qzeros +3 -0
  43. model.layers.1.self_attn.o_proj.scales +3 -0
  44. model.layers.1.self_attn.q_proj.qweight +3 -0
  45. model.layers.1.self_attn.q_proj.qzeros +3 -0
  46. model.layers.1.self_attn.q_proj.scales +3 -0
  47. model.layers.1.self_attn.v_proj.qweight +3 -0
  48. model.layers.1.self_attn.v_proj.qzeros +3 -0
  49. model.layers.1.self_attn.v_proj.scales +3 -0
  50. model.layers.10.input_layernorm.weight +3 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ 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
+ onnx__* filter=lfs diff=lfs merge=lfs -text
37
+ model.__* filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer* filter=lfs diff=lfs merge=lfs -text
39
+ model.* filter=lfs diff=lfs merge=lfs -text
model-fixed-dims.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0c892a4b55ccd796532678d7ddef6968d43bb543fb333e3be9675cd9a8391d4
3
+ size 2219288
model.embed_tokens.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e979c418bb40e497b73c6ad34d90be9a44c9f5373336cf49249c33f550f4036f
3
+ size 1050673152
model.layers.0.input_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4102ebeeda2b39c259718c52145dc9d042bb0e01ab5af1cba5488d35c3fb10e8
3
+ size 8192
model.layers.0.mlp.down_proj.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:472b2eae557966e880098be42437e4b8c18d8a6b213871a2384fd9d1e28f26e1
3
+ size 29360128
model.layers.0.mlp.down_proj.qzeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26bed4aa5d000901c027c5f325b8687614f23da227c14c2d30fb1b4ec16ebd5f
3
+ size 229376
model.layers.0.mlp.down_proj.scales ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7197e1ea2f847eeb5bb00270a6e95d578f4f1621dab0708cff9a857615dc30b
3
+ size 917504
model.layers.0.mlp.gate_proj.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a43533d8678f9f5570e4dcfe54ff8bd6eb74b4a9eb0f43ab35dc4ae1c8df00
3
+ size 29360128
model.layers.0.mlp.gate_proj.qzeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7bff46f69da2f252824695d0657f16d5721a60a844f0a6a55b3a283ed468026
3
+ size 229376
model.layers.0.mlp.gate_proj.scales ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70a2c5b1261ac8f28142a56917b271b4f40b6675edab2d9cedda29796b2470ed
3
+ size 917504
model.layers.0.mlp.up_proj.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5980e0035199569cf19082e9ea725b611adec5a4901b2b16f44a38a621dc0ec7
3
+ size 29360128
model.layers.0.mlp.up_proj.qzeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6e9351a3877ee782e698185e823153fc1d36ff0b1f2f8d326cbc90f6e217c21
3
+ size 229376
model.layers.0.mlp.up_proj.scales ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94cb52bc6f9e10181ea7d6b2e4b106ffa9301fd413ed3ca675c2fd74cc0bed3a
3
+ size 917504
model.layers.0.post_attention_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe93f721bbcc19d1ef5e126cd7d294bd96a497e905fd303976a298f22720c462
3
+ size 8192
model.layers.0.self_attn.k_proj.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a072792736599449bc57271753602c0b9277ac5833606793b7f7bcc75ba1088
3
+ size 2097152
model.layers.0.self_attn.k_proj.qzeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31b0622fa462db6f226a59ee605d9a861f3b92673a5329c30d6a2cb325eb333c
3
+ size 16384
model.layers.0.self_attn.k_proj.scales ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e35fb02fb45105518e8cad37b30307418cdc93fbd92afe7c99dcade93e774f8c
3
+ size 65536
model.layers.0.self_attn.o_proj.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a6b7bd0da66f0f8ce8cdf231d6713d360bde64e52ecc65f4a76bf943ab76273
3
+ size 8388608
model.layers.0.self_attn.o_proj.qzeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82fd467f04d57051ef026bbbcad8fd06e0b3d384ac091ece945a6f41b54febd3
3
+ size 65536
model.layers.0.self_attn.o_proj.scales ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8ccd5c90b834244b962110b6fe7d0954715f332a8bf95182b04482eed30facb
3
+ size 262144
model.layers.0.self_attn.q_proj.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0eba8dd944b464d5dab4fb25fa4f2ca336ed59201ce75a57ceac97e21bffa57
3
+ size 8388608
model.layers.0.self_attn.q_proj.qzeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d18fb45389a4ccf00b0d7bd5dd696045586ce40825065fdf13e3c29e29540fcd
3
+ size 65536
model.layers.0.self_attn.q_proj.scales ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7c1c1db8d3d426c42bfc5120216d3f3fbc87f9458731aabefd9109bd07dd9d3
3
+ size 262144
model.layers.0.self_attn.v_proj.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3e2524161847592622b73db069691225ea5545a1d9ab1231e2a8296c387c737
3
+ size 2097152
model.layers.0.self_attn.v_proj.qzeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d175edd58ce4d89814d653b9dc7f5e47264d6aaded5b2d4d0762a493e88ae673
3
+ size 16384
model.layers.0.self_attn.v_proj.scales ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2fac174e27be7503afad3f246a58e91de967e60ea7d2389aa0fdd4c67e9b0b9
3
+ size 65536
model.layers.1.input_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8be602a6a89c9c2d6be080e3c73918779b85c6618a39a597c89475f768561363
3
+ size 8192
model.layers.1.mlp.down_proj.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be6916e7324198218d5ca1068fa00a750c77312717c8ca336e9db5ad9aa9509c
3
+ size 29360128
model.layers.1.mlp.down_proj.qzeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05513d3a76569348324af395ea8d866146866e7826f5311c16ac4470c5019731
3
+ size 229376
model.layers.1.mlp.down_proj.scales ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11206bbb53b0f782af7e366ecd2dcfbe904edc22a6be306b1881b2051099f911
3
+ size 917504
model.layers.1.mlp.gate_proj.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74ccbe0c92623eac34d2b26bffce9373667df24c5f068ec8a8452ac5a80f01eb
3
+ size 29360128
model.layers.1.mlp.gate_proj.qzeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c37666b72535e32e46f2af4fab74a8ddc2389806e8f115841addaa5d50e6281e
3
+ size 229376
model.layers.1.mlp.gate_proj.scales ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62cfe14905b276db4ded8da79f677c2fe38f7a913a7979a96e74dd1cc5d269a5
3
+ size 917504
model.layers.1.mlp.up_proj.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d01b38de2ba4c6723d971cfd4e654be7883abc029f5d7752037b2f865dc8b101
3
+ size 29360128
model.layers.1.mlp.up_proj.qzeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9e7a3a2d43bb428f29a703a37f1c2d9cd75c53455f5dcc82f5f323a78762e9a
3
+ size 229376
model.layers.1.mlp.up_proj.scales ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75a39105a9d0497d500bde6c7858672119c9f31d87861b079db7f57771e8b1fc
3
+ size 917504
model.layers.1.post_attention_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fad8665e3c849edac7576572757558406379156a21d781a1ce3dbf37a68a543
3
+ size 8192
model.layers.1.self_attn.k_proj.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e199c6c1de080be50df1846331adfc9f5157f5b65b23783cfbba161b08c5462a
3
+ size 2097152
model.layers.1.self_attn.k_proj.qzeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:640a8b96e370a6805f5f74fd5e7527035ed1ec373984a0e8012557c6f98bbc74
3
+ size 16384
model.layers.1.self_attn.k_proj.scales ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7234b0102c9e068d4b24066aba4e3d227580a30b98a3da45847f670268885da1
3
+ size 65536
model.layers.1.self_attn.o_proj.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76bb949afcff5957b8ba3cb3d9f85dfc5ea02e360c9635ece985c93bf5a1af1f
3
+ size 8388608
model.layers.1.self_attn.o_proj.qzeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffb626864f0d96313855cc778556f97992147c6ac2382c3e45b1ff9ff5f4fefd
3
+ size 65536
model.layers.1.self_attn.o_proj.scales ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b199ea316764c5027cbfcdf1247078c6f24f3b43aefedf3e21f49ffd8fa8327b
3
+ size 262144
model.layers.1.self_attn.q_proj.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b41ecd647312b5152e3d5d1bedcef084e06c3ad3f549b4e55485cf325d73b1fe
3
+ size 8388608
model.layers.1.self_attn.q_proj.qzeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e78107aa53be5920d0fc0411838aee288f201cb78e2e33422cc5fd20d096e45a
3
+ size 65536
model.layers.1.self_attn.q_proj.scales ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23834af460f85257c6fc7540c927316ac23741e6b1a9a30c73a2ae46978d17ac
3
+ size 262144
model.layers.1.self_attn.v_proj.qweight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74b20312c3ee2033d735de2f5ca8f6e624a9e859b9e1f40581540f8d9b12cf5e
3
+ size 2097152
model.layers.1.self_attn.v_proj.qzeros ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:126bd3c37e86a358af41e553534c16cadefb0066047bdbdd499c5f0ce9ba030f
3
+ size 16384
model.layers.1.self_attn.v_proj.scales ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f53f2b4ed5a18ffd53b272061d54bf85edea7295c44b87a099d873a75a12672
3
+ size 65536
model.layers.10.input_layernorm.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0629cd373c99b6a3da4fb1d1ac07e1a663b12b529f5e630263fd6a7ddddea44
3
+ size 8192