Upload 7 files
Browse files- config.json +2 -2
- pytorch_model.bin.index.json +1 -226
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- training_args.bin +3 -0
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "Dampish/
|
3 |
"architectures": [
|
4 |
"GPTNeoXForCausalLM"
|
5 |
],
|
@@ -14,7 +14,7 @@
|
|
14 |
"max_position_embeddings": 2048,
|
15 |
"model_type": "gpt_neox",
|
16 |
"num_attention_heads": 32,
|
17 |
-
"num_hidden_layers":
|
18 |
"rotary_emb_base": 10000,
|
19 |
"rotary_pct": 1.0,
|
20 |
"tie_word_embeddings": false,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "Dampish/stellar7CHPT",
|
3 |
"architectures": [
|
4 |
"GPTNeoXForCausalLM"
|
5 |
],
|
|
|
14 |
"max_position_embeddings": 2048,
|
15 |
"model_type": "gpt_neox",
|
16 |
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
"rotary_emb_base": 10000,
|
19 |
"rotary_pct": 1.0,
|
20 |
"tie_word_embeddings": false,
|
pytorch_model.bin.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"embed_out.weight": "pytorch_model-00002-of-00002.bin",
|
@@ -397,126 +397,6 @@
|
|
397 |
"gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
398 |
"gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
399 |
"gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
400 |
-
"gpt_neox.layers.32.attention.bias": "pytorch_model-00002-of-00002.bin",
|
401 |
-
"gpt_neox.layers.32.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
402 |
-
"gpt_neox.layers.32.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
403 |
-
"gpt_neox.layers.32.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
|
404 |
-
"gpt_neox.layers.32.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
405 |
-
"gpt_neox.layers.32.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
406 |
-
"gpt_neox.layers.32.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
407 |
-
"gpt_neox.layers.32.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
408 |
-
"gpt_neox.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
409 |
-
"gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
410 |
-
"gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
411 |
-
"gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
412 |
-
"gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
413 |
-
"gpt_neox.layers.32.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
414 |
-
"gpt_neox.layers.32.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
415 |
-
"gpt_neox.layers.33.attention.bias": "pytorch_model-00002-of-00002.bin",
|
416 |
-
"gpt_neox.layers.33.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
417 |
-
"gpt_neox.layers.33.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
418 |
-
"gpt_neox.layers.33.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
|
419 |
-
"gpt_neox.layers.33.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
420 |
-
"gpt_neox.layers.33.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
421 |
-
"gpt_neox.layers.33.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
422 |
-
"gpt_neox.layers.33.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
423 |
-
"gpt_neox.layers.33.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
424 |
-
"gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
425 |
-
"gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
426 |
-
"gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
427 |
-
"gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
428 |
-
"gpt_neox.layers.33.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
429 |
-
"gpt_neox.layers.33.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
430 |
-
"gpt_neox.layers.34.attention.bias": "pytorch_model-00002-of-00002.bin",
|
431 |
-
"gpt_neox.layers.34.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
432 |
-
"gpt_neox.layers.34.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
433 |
-
"gpt_neox.layers.34.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
|
434 |
-
"gpt_neox.layers.34.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
435 |
-
"gpt_neox.layers.34.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
436 |
-
"gpt_neox.layers.34.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
437 |
-
"gpt_neox.layers.34.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
438 |
-
"gpt_neox.layers.34.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
439 |
-
"gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
440 |
-
"gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
441 |
-
"gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
442 |
-
"gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
443 |
-
"gpt_neox.layers.34.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
444 |
-
"gpt_neox.layers.34.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
445 |
-
"gpt_neox.layers.35.attention.bias": "pytorch_model-00002-of-00002.bin",
|
446 |
-
"gpt_neox.layers.35.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
447 |
-
"gpt_neox.layers.35.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
448 |
-
"gpt_neox.layers.35.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
|
449 |
-
"gpt_neox.layers.35.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
450 |
-
"gpt_neox.layers.35.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
451 |
-
"gpt_neox.layers.35.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
452 |
-
"gpt_neox.layers.35.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
453 |
-
"gpt_neox.layers.35.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
454 |
-
"gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
455 |
-
"gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
456 |
-
"gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
457 |
-
"gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
458 |
-
"gpt_neox.layers.35.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
459 |
-
"gpt_neox.layers.35.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
460 |
-
"gpt_neox.layers.36.attention.bias": "pytorch_model-00002-of-00002.bin",
|
461 |
-
"gpt_neox.layers.36.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
462 |
-
"gpt_neox.layers.36.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
463 |
-
"gpt_neox.layers.36.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
|
464 |
-
"gpt_neox.layers.36.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
465 |
-
"gpt_neox.layers.36.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
466 |
-
"gpt_neox.layers.36.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
467 |
-
"gpt_neox.layers.36.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
468 |
-
"gpt_neox.layers.36.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
469 |
-
"gpt_neox.layers.36.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
470 |
-
"gpt_neox.layers.36.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
471 |
-
"gpt_neox.layers.36.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
472 |
-
"gpt_neox.layers.36.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
473 |
-
"gpt_neox.layers.36.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
474 |
-
"gpt_neox.layers.36.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
475 |
-
"gpt_neox.layers.37.attention.bias": "pytorch_model-00002-of-00002.bin",
|
476 |
-
"gpt_neox.layers.37.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
477 |
-
"gpt_neox.layers.37.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
478 |
-
"gpt_neox.layers.37.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
|
479 |
-
"gpt_neox.layers.37.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
480 |
-
"gpt_neox.layers.37.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
481 |
-
"gpt_neox.layers.37.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
482 |
-
"gpt_neox.layers.37.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
483 |
-
"gpt_neox.layers.37.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
484 |
-
"gpt_neox.layers.37.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
485 |
-
"gpt_neox.layers.37.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
486 |
-
"gpt_neox.layers.37.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
487 |
-
"gpt_neox.layers.37.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
488 |
-
"gpt_neox.layers.37.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
489 |
-
"gpt_neox.layers.37.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
490 |
-
"gpt_neox.layers.38.attention.bias": "pytorch_model-00002-of-00002.bin",
|
491 |
-
"gpt_neox.layers.38.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
492 |
-
"gpt_neox.layers.38.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
493 |
-
"gpt_neox.layers.38.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
|
494 |
-
"gpt_neox.layers.38.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
495 |
-
"gpt_neox.layers.38.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
496 |
-
"gpt_neox.layers.38.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
497 |
-
"gpt_neox.layers.38.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
498 |
-
"gpt_neox.layers.38.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
499 |
-
"gpt_neox.layers.38.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
500 |
-
"gpt_neox.layers.38.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
501 |
-
"gpt_neox.layers.38.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
502 |
-
"gpt_neox.layers.38.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
503 |
-
"gpt_neox.layers.38.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
504 |
-
"gpt_neox.layers.38.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
505 |
-
"gpt_neox.layers.39.attention.bias": "pytorch_model-00002-of-00002.bin",
|
506 |
-
"gpt_neox.layers.39.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
507 |
-
"gpt_neox.layers.39.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
508 |
-
"gpt_neox.layers.39.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
|
509 |
-
"gpt_neox.layers.39.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
510 |
-
"gpt_neox.layers.39.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
511 |
-
"gpt_neox.layers.39.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
512 |
-
"gpt_neox.layers.39.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
513 |
-
"gpt_neox.layers.39.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
514 |
-
"gpt_neox.layers.39.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
515 |
-
"gpt_neox.layers.39.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
516 |
-
"gpt_neox.layers.39.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
517 |
-
"gpt_neox.layers.39.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
518 |
-
"gpt_neox.layers.39.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
519 |
-
"gpt_neox.layers.39.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
520 |
"gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00002.bin",
|
521 |
"gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
522 |
"gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
@@ -532,111 +412,6 @@
|
|
532 |
"gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
533 |
"gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
534 |
"gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
535 |
-
"gpt_neox.layers.40.attention.bias": "pytorch_model-00002-of-00002.bin",
|
536 |
-
"gpt_neox.layers.40.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
537 |
-
"gpt_neox.layers.40.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
538 |
-
"gpt_neox.layers.40.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
|
539 |
-
"gpt_neox.layers.40.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
540 |
-
"gpt_neox.layers.40.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
541 |
-
"gpt_neox.layers.40.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
542 |
-
"gpt_neox.layers.40.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
543 |
-
"gpt_neox.layers.40.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
544 |
-
"gpt_neox.layers.40.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
545 |
-
"gpt_neox.layers.40.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
546 |
-
"gpt_neox.layers.40.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
547 |
-
"gpt_neox.layers.40.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
548 |
-
"gpt_neox.layers.40.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
549 |
-
"gpt_neox.layers.40.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
550 |
-
"gpt_neox.layers.41.attention.bias": "pytorch_model-00002-of-00002.bin",
|
551 |
-
"gpt_neox.layers.41.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
552 |
-
"gpt_neox.layers.41.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
553 |
-
"gpt_neox.layers.41.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
|
554 |
-
"gpt_neox.layers.41.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
555 |
-
"gpt_neox.layers.41.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
556 |
-
"gpt_neox.layers.41.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
557 |
-
"gpt_neox.layers.41.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
558 |
-
"gpt_neox.layers.41.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
559 |
-
"gpt_neox.layers.41.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
560 |
-
"gpt_neox.layers.41.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
561 |
-
"gpt_neox.layers.41.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
562 |
-
"gpt_neox.layers.41.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
563 |
-
"gpt_neox.layers.41.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
564 |
-
"gpt_neox.layers.41.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
565 |
-
"gpt_neox.layers.42.attention.bias": "pytorch_model-00002-of-00002.bin",
|
566 |
-
"gpt_neox.layers.42.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
567 |
-
"gpt_neox.layers.42.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
568 |
-
"gpt_neox.layers.42.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
|
569 |
-
"gpt_neox.layers.42.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
570 |
-
"gpt_neox.layers.42.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
571 |
-
"gpt_neox.layers.42.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
572 |
-
"gpt_neox.layers.42.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
573 |
-
"gpt_neox.layers.42.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
574 |
-
"gpt_neox.layers.42.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
575 |
-
"gpt_neox.layers.42.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
576 |
-
"gpt_neox.layers.42.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
577 |
-
"gpt_neox.layers.42.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
578 |
-
"gpt_neox.layers.42.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
579 |
-
"gpt_neox.layers.42.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
580 |
-
"gpt_neox.layers.43.attention.bias": "pytorch_model-00002-of-00002.bin",
|
581 |
-
"gpt_neox.layers.43.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
582 |
-
"gpt_neox.layers.43.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
583 |
-
"gpt_neox.layers.43.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
|
584 |
-
"gpt_neox.layers.43.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
585 |
-
"gpt_neox.layers.43.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
586 |
-
"gpt_neox.layers.43.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
587 |
-
"gpt_neox.layers.43.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
588 |
-
"gpt_neox.layers.43.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
589 |
-
"gpt_neox.layers.43.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
590 |
-
"gpt_neox.layers.43.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
591 |
-
"gpt_neox.layers.43.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
592 |
-
"gpt_neox.layers.43.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
593 |
-
"gpt_neox.layers.43.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
594 |
-
"gpt_neox.layers.43.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
595 |
-
"gpt_neox.layers.44.attention.bias": "pytorch_model-00002-of-00002.bin",
|
596 |
-
"gpt_neox.layers.44.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
597 |
-
"gpt_neox.layers.44.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
598 |
-
"gpt_neox.layers.44.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
|
599 |
-
"gpt_neox.layers.44.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
600 |
-
"gpt_neox.layers.44.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
601 |
-
"gpt_neox.layers.44.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
602 |
-
"gpt_neox.layers.44.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
603 |
-
"gpt_neox.layers.44.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
604 |
-
"gpt_neox.layers.44.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
605 |
-
"gpt_neox.layers.44.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
606 |
-
"gpt_neox.layers.44.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
607 |
-
"gpt_neox.layers.44.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
608 |
-
"gpt_neox.layers.44.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
609 |
-
"gpt_neox.layers.44.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
610 |
-
"gpt_neox.layers.45.attention.bias": "pytorch_model-00002-of-00002.bin",
|
611 |
-
"gpt_neox.layers.45.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
612 |
-
"gpt_neox.layers.45.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
613 |
-
"gpt_neox.layers.45.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
|
614 |
-
"gpt_neox.layers.45.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
615 |
-
"gpt_neox.layers.45.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
616 |
-
"gpt_neox.layers.45.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
617 |
-
"gpt_neox.layers.45.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
618 |
-
"gpt_neox.layers.45.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
619 |
-
"gpt_neox.layers.45.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
620 |
-
"gpt_neox.layers.45.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
621 |
-
"gpt_neox.layers.45.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
622 |
-
"gpt_neox.layers.45.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
623 |
-
"gpt_neox.layers.45.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
624 |
-
"gpt_neox.layers.45.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
625 |
-
"gpt_neox.layers.46.attention.bias": "pytorch_model-00002-of-00002.bin",
|
626 |
-
"gpt_neox.layers.46.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
|
627 |
-
"gpt_neox.layers.46.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
628 |
-
"gpt_neox.layers.46.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
|
629 |
-
"gpt_neox.layers.46.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
|
630 |
-
"gpt_neox.layers.46.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
631 |
-
"gpt_neox.layers.46.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
632 |
-
"gpt_neox.layers.46.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
633 |
-
"gpt_neox.layers.46.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
634 |
-
"gpt_neox.layers.46.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
|
635 |
-
"gpt_neox.layers.46.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
636 |
-
"gpt_neox.layers.46.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
|
637 |
-
"gpt_neox.layers.46.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
638 |
-
"gpt_neox.layers.46.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
639 |
-
"gpt_neox.layers.46.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
640 |
"gpt_neox.layers.5.attention.bias": "pytorch_model-00001-of-00002.bin",
|
641 |
"gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
642 |
"gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 11120239744.0
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"embed_out.weight": "pytorch_model-00002-of-00002.bin",
|
|
|
397 |
"gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
398 |
"gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
399 |
"gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
400 |
"gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00002.bin",
|
401 |
"gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
402 |
"gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
|
|
412 |
"gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
413 |
"gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
414 |
"gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
415 |
"gpt_neox.layers.5.attention.bias": "pytorch_model-00001-of-00002.bin",
|
416 |
"gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
|
417 |
"gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 2048,
|
7 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7f5b60fb2e763a22cc0eb206f3b00f7f9f904fed78253adb0c5535ab00f74d3
|
3 |
+
size 3899
|