Upload folder using huggingface_hub
Browse files
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e6cea304838cf10bff5173536e091ba28652fade7c7619fb44e22829c1f4b73
|
3 |
+
size 4999430536
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5809b5e350dc7f61455f842c579a826ad23570e002171c77ae72f931927211bc
|
3 |
+
size 4084634840
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00002-of-00002.safetensors",
|
@@ -230,6 +230,7 @@
|
|
230 |
"model.layers.15.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
231 |
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
232 |
"model.layers.15.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
|
|
233 |
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
234 |
"model.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
235 |
"model.layers.15.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
@@ -237,9 +238,11 @@
|
|
237 |
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
238 |
"model.layers.15.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
239 |
"model.layers.15.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
|
|
240 |
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
241 |
"model.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
242 |
"model.layers.15.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
|
|
243 |
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
244 |
"model.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
245 |
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
@@ -454,6 +457,7 @@
|
|
454 |
"model.layers.21.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
|
455 |
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
456 |
"model.layers.22.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
|
|
|
457 |
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
458 |
"model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
459 |
"model.layers.22.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
|
@@ -483,6 +487,7 @@
|
|
483 |
"model.layers.22.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
|
484 |
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
485 |
"model.layers.23.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
|
|
|
486 |
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
487 |
"model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
488 |
"model.layers.23.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
|
@@ -662,6 +667,7 @@
|
|
662 |
"model.layers.28.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
|
663 |
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
664 |
"model.layers.29.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
|
|
|
665 |
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
666 |
"model.layers.29.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
667 |
"model.layers.29.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
|
@@ -725,9 +731,11 @@
|
|
725 |
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
726 |
"model.layers.30.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
727 |
"model.layers.30.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
|
|
|
728 |
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
729 |
"model.layers.30.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
|
730 |
"model.layers.30.mlp.up_proj.input_scale": "model-00002-of-00002.safetensors",
|
|
|
731 |
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
732 |
"model.layers.30.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
733 |
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
@@ -873,9 +881,11 @@
|
|
873 |
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
874 |
"model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
875 |
"model.layers.7.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
|
|
876 |
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
877 |
"model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
878 |
"model.layers.7.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
|
|
879 |
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
880 |
"model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
881 |
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
@@ -927,6 +937,7 @@
|
|
927 |
"model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
928 |
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
929 |
"model.layers.9.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
|
|
930 |
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
931 |
"model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
932 |
"model.layers.9.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 9083953824
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00002-of-00002.safetensors",
|
|
|
230 |
"model.layers.15.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
231 |
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
232 |
"model.layers.15.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
|
233 |
+
"model.layers.15.self_attn.k_proj.input_zero_point": "model-00001-of-00002.safetensors",
|
234 |
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
235 |
"model.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
|
236 |
"model.layers.15.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
|
|
|
238 |
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
239 |
"model.layers.15.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
|
240 |
"model.layers.15.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
|
241 |
+
"model.layers.15.self_attn.q_proj.input_zero_point": "model-00001-of-00002.safetensors",
|
242 |
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
243 |
"model.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
|
244 |
"model.layers.15.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
|
245 |
+
"model.layers.15.self_attn.v_proj.input_zero_point": "model-00001-of-00002.safetensors",
|
246 |
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
247 |
"model.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
248 |
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
457 |
"model.layers.21.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
|
458 |
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
459 |
"model.layers.22.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
|
460 |
+
"model.layers.22.mlp.down_proj.input_zero_point": "model-00002-of-00002.safetensors",
|
461 |
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
462 |
"model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
463 |
"model.layers.22.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
|
|
|
487 |
"model.layers.22.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
|
488 |
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
489 |
"model.layers.23.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
|
490 |
+
"model.layers.23.mlp.down_proj.input_zero_point": "model-00002-of-00002.safetensors",
|
491 |
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
492 |
"model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
493 |
"model.layers.23.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
|
|
|
667 |
"model.layers.28.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
|
668 |
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
669 |
"model.layers.29.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
|
670 |
+
"model.layers.29.mlp.down_proj.input_zero_point": "model-00002-of-00002.safetensors",
|
671 |
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
672 |
"model.layers.29.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
673 |
"model.layers.29.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
|
|
|
731 |
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
732 |
"model.layers.30.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
|
733 |
"model.layers.30.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
|
734 |
+
"model.layers.30.mlp.gate_proj.input_zero_point": "model-00002-of-00002.safetensors",
|
735 |
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
736 |
"model.layers.30.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
|
737 |
"model.layers.30.mlp.up_proj.input_scale": "model-00002-of-00002.safetensors",
|
738 |
+
"model.layers.30.mlp.up_proj.input_zero_point": "model-00002-of-00002.safetensors",
|
739 |
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
740 |
"model.layers.30.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
|
741 |
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
|
|
881 |
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
882 |
"model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
883 |
"model.layers.7.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|
884 |
+
"model.layers.7.mlp.gate_proj.input_zero_point": "model-00001-of-00002.safetensors",
|
885 |
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
886 |
"model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
|
887 |
"model.layers.7.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
|
888 |
+
"model.layers.7.mlp.up_proj.input_zero_point": "model-00001-of-00002.safetensors",
|
889 |
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
890 |
"model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
|
891 |
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
937 |
"model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
|
938 |
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
939 |
"model.layers.9.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
|
940 |
+
"model.layers.9.mlp.down_proj.input_zero_point": "model-00001-of-00002.safetensors",
|
941 |
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
942 |
"model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
|
943 |
"model.layers.9.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
|