afshinO commited on
Commit
9bd4ce4
1 Parent(s): 228fc2a

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +8 -1
  2. tokenizer.json +583 -1
  3. tokenizer_config.json +520 -1
special_tokens_map.json CHANGED
@@ -7,7 +7,14 @@
7
  "single_word": false
8
  },
9
  "eos_token": {
10
- "content": "<|end_of_text|>",
 
 
 
 
 
 
 
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
 
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|eot_id|>",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
@@ -2306,6 +2311,582 @@
2306
  "rstrip": false,
2307
  "normalized": false,
2308
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2309
  }
2310
  ],
2311
  "normalizer": null,
@@ -2407,6 +2988,7 @@
2407
  "end_of_word_suffix": null,
2408
  "fuse_unk": false,
2409
  "byte_fallback": false,
 
2410
  "vocab": {
2411
  "!": 0,
2412
  "\"": 1,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 8001,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
2311
  "rstrip": false,
2312
  "normalized": false,
2313
  "special": true
2314
+ },
2315
+ {
2316
+ "id": 128256,
2317
+ "content": "<|im_start|>",
2318
+ "single_word": false,
2319
+ "lstrip": false,
2320
+ "rstrip": false,
2321
+ "normalized": false,
2322
+ "special": false
2323
+ },
2324
+ {
2325
+ "id": 128257,
2326
+ "content": "<|im_end|>",
2327
+ "single_word": false,
2328
+ "lstrip": false,
2329
+ "rstrip": false,
2330
+ "normalized": false,
2331
+ "special": false
2332
+ },
2333
+ {
2334
+ "id": 128258,
2335
+ "content": "<|special_0|>",
2336
+ "single_word": false,
2337
+ "lstrip": false,
2338
+ "rstrip": false,
2339
+ "normalized": false,
2340
+ "special": false
2341
+ },
2342
+ {
2343
+ "id": 128259,
2344
+ "content": "<|special_1|>",
2345
+ "single_word": false,
2346
+ "lstrip": false,
2347
+ "rstrip": false,
2348
+ "normalized": false,
2349
+ "special": false
2350
+ },
2351
+ {
2352
+ "id": 128260,
2353
+ "content": "<|special_2|>",
2354
+ "single_word": false,
2355
+ "lstrip": false,
2356
+ "rstrip": false,
2357
+ "normalized": false,
2358
+ "special": false
2359
+ },
2360
+ {
2361
+ "id": 128261,
2362
+ "content": "<|special_3|>",
2363
+ "single_word": false,
2364
+ "lstrip": false,
2365
+ "rstrip": false,
2366
+ "normalized": false,
2367
+ "special": false
2368
+ },
2369
+ {
2370
+ "id": 128262,
2371
+ "content": "<|special_4|>",
2372
+ "single_word": false,
2373
+ "lstrip": false,
2374
+ "rstrip": false,
2375
+ "normalized": false,
2376
+ "special": false
2377
+ },
2378
+ {
2379
+ "id": 128263,
2380
+ "content": "<|special_5|>",
2381
+ "single_word": false,
2382
+ "lstrip": false,
2383
+ "rstrip": false,
2384
+ "normalized": false,
2385
+ "special": false
2386
+ },
2387
+ {
2388
+ "id": 128264,
2389
+ "content": "<|special_6|>",
2390
+ "single_word": false,
2391
+ "lstrip": false,
2392
+ "rstrip": false,
2393
+ "normalized": false,
2394
+ "special": false
2395
+ },
2396
+ {
2397
+ "id": 128265,
2398
+ "content": "<|special_7|>",
2399
+ "single_word": false,
2400
+ "lstrip": false,
2401
+ "rstrip": false,
2402
+ "normalized": false,
2403
+ "special": false
2404
+ },
2405
+ {
2406
+ "id": 128266,
2407
+ "content": "<|special_8|>",
2408
+ "single_word": false,
2409
+ "lstrip": false,
2410
+ "rstrip": false,
2411
+ "normalized": false,
2412
+ "special": false
2413
+ },
2414
+ {
2415
+ "id": 128267,
2416
+ "content": "<|special_9|>",
2417
+ "single_word": false,
2418
+ "lstrip": false,
2419
+ "rstrip": false,
2420
+ "normalized": false,
2421
+ "special": false
2422
+ },
2423
+ {
2424
+ "id": 128268,
2425
+ "content": "<|special_10|>",
2426
+ "single_word": false,
2427
+ "lstrip": false,
2428
+ "rstrip": false,
2429
+ "normalized": false,
2430
+ "special": false
2431
+ },
2432
+ {
2433
+ "id": 128269,
2434
+ "content": "<|special_11|>",
2435
+ "single_word": false,
2436
+ "lstrip": false,
2437
+ "rstrip": false,
2438
+ "normalized": false,
2439
+ "special": false
2440
+ },
2441
+ {
2442
+ "id": 128270,
2443
+ "content": "<|special_12|>",
2444
+ "single_word": false,
2445
+ "lstrip": false,
2446
+ "rstrip": false,
2447
+ "normalized": false,
2448
+ "special": false
2449
+ },
2450
+ {
2451
+ "id": 128271,
2452
+ "content": "<|special_13|>",
2453
+ "single_word": false,
2454
+ "lstrip": false,
2455
+ "rstrip": false,
2456
+ "normalized": false,
2457
+ "special": false
2458
+ },
2459
+ {
2460
+ "id": 128272,
2461
+ "content": "<|special_14|>",
2462
+ "single_word": false,
2463
+ "lstrip": false,
2464
+ "rstrip": false,
2465
+ "normalized": false,
2466
+ "special": false
2467
+ },
2468
+ {
2469
+ "id": 128273,
2470
+ "content": "<|special_15|>",
2471
+ "single_word": false,
2472
+ "lstrip": false,
2473
+ "rstrip": false,
2474
+ "normalized": false,
2475
+ "special": false
2476
+ },
2477
+ {
2478
+ "id": 128274,
2479
+ "content": "<|special_16|>",
2480
+ "single_word": false,
2481
+ "lstrip": false,
2482
+ "rstrip": false,
2483
+ "normalized": false,
2484
+ "special": false
2485
+ },
2486
+ {
2487
+ "id": 128275,
2488
+ "content": "<|special_17|>",
2489
+ "single_word": false,
2490
+ "lstrip": false,
2491
+ "rstrip": false,
2492
+ "normalized": false,
2493
+ "special": false
2494
+ },
2495
+ {
2496
+ "id": 128276,
2497
+ "content": "<|special_18|>",
2498
+ "single_word": false,
2499
+ "lstrip": false,
2500
+ "rstrip": false,
2501
+ "normalized": false,
2502
+ "special": false
2503
+ },
2504
+ {
2505
+ "id": 128277,
2506
+ "content": "<|special_19|>",
2507
+ "single_word": false,
2508
+ "lstrip": false,
2509
+ "rstrip": false,
2510
+ "normalized": false,
2511
+ "special": false
2512
+ },
2513
+ {
2514
+ "id": 128278,
2515
+ "content": "<|special_20|>",
2516
+ "single_word": false,
2517
+ "lstrip": false,
2518
+ "rstrip": false,
2519
+ "normalized": false,
2520
+ "special": false
2521
+ },
2522
+ {
2523
+ "id": 128279,
2524
+ "content": "<|special_21|>",
2525
+ "single_word": false,
2526
+ "lstrip": false,
2527
+ "rstrip": false,
2528
+ "normalized": false,
2529
+ "special": false
2530
+ },
2531
+ {
2532
+ "id": 128280,
2533
+ "content": "<|special_22|>",
2534
+ "single_word": false,
2535
+ "lstrip": false,
2536
+ "rstrip": false,
2537
+ "normalized": false,
2538
+ "special": false
2539
+ },
2540
+ {
2541
+ "id": 128281,
2542
+ "content": "<|special_23|>",
2543
+ "single_word": false,
2544
+ "lstrip": false,
2545
+ "rstrip": false,
2546
+ "normalized": false,
2547
+ "special": false
2548
+ },
2549
+ {
2550
+ "id": 128282,
2551
+ "content": "<|special_24|>",
2552
+ "single_word": false,
2553
+ "lstrip": false,
2554
+ "rstrip": false,
2555
+ "normalized": false,
2556
+ "special": false
2557
+ },
2558
+ {
2559
+ "id": 128283,
2560
+ "content": "<|special_25|>",
2561
+ "single_word": false,
2562
+ "lstrip": false,
2563
+ "rstrip": false,
2564
+ "normalized": false,
2565
+ "special": false
2566
+ },
2567
+ {
2568
+ "id": 128284,
2569
+ "content": "<|special_26|>",
2570
+ "single_word": false,
2571
+ "lstrip": false,
2572
+ "rstrip": false,
2573
+ "normalized": false,
2574
+ "special": false
2575
+ },
2576
+ {
2577
+ "id": 128285,
2578
+ "content": "<|special_27|>",
2579
+ "single_word": false,
2580
+ "lstrip": false,
2581
+ "rstrip": false,
2582
+ "normalized": false,
2583
+ "special": false
2584
+ },
2585
+ {
2586
+ "id": 128286,
2587
+ "content": "<|special_28|>",
2588
+ "single_word": false,
2589
+ "lstrip": false,
2590
+ "rstrip": false,
2591
+ "normalized": false,
2592
+ "special": false
2593
+ },
2594
+ {
2595
+ "id": 128287,
2596
+ "content": "<|special_29|>",
2597
+ "single_word": false,
2598
+ "lstrip": false,
2599
+ "rstrip": false,
2600
+ "normalized": false,
2601
+ "special": false
2602
+ },
2603
+ {
2604
+ "id": 128288,
2605
+ "content": "<|special_30|>",
2606
+ "single_word": false,
2607
+ "lstrip": false,
2608
+ "rstrip": false,
2609
+ "normalized": false,
2610
+ "special": false
2611
+ },
2612
+ {
2613
+ "id": 128289,
2614
+ "content": "<|special_31|>",
2615
+ "single_word": false,
2616
+ "lstrip": false,
2617
+ "rstrip": false,
2618
+ "normalized": false,
2619
+ "special": false
2620
+ },
2621
+ {
2622
+ "id": 128290,
2623
+ "content": "<|special_32|>",
2624
+ "single_word": false,
2625
+ "lstrip": false,
2626
+ "rstrip": false,
2627
+ "normalized": false,
2628
+ "special": false
2629
+ },
2630
+ {
2631
+ "id": 128291,
2632
+ "content": "<|special_33|>",
2633
+ "single_word": false,
2634
+ "lstrip": false,
2635
+ "rstrip": false,
2636
+ "normalized": false,
2637
+ "special": false
2638
+ },
2639
+ {
2640
+ "id": 128292,
2641
+ "content": "<|special_34|>",
2642
+ "single_word": false,
2643
+ "lstrip": false,
2644
+ "rstrip": false,
2645
+ "normalized": false,
2646
+ "special": false
2647
+ },
2648
+ {
2649
+ "id": 128293,
2650
+ "content": "<|special_35|>",
2651
+ "single_word": false,
2652
+ "lstrip": false,
2653
+ "rstrip": false,
2654
+ "normalized": false,
2655
+ "special": false
2656
+ },
2657
+ {
2658
+ "id": 128294,
2659
+ "content": "<|special_36|>",
2660
+ "single_word": false,
2661
+ "lstrip": false,
2662
+ "rstrip": false,
2663
+ "normalized": false,
2664
+ "special": false
2665
+ },
2666
+ {
2667
+ "id": 128295,
2668
+ "content": "<|special_37|>",
2669
+ "single_word": false,
2670
+ "lstrip": false,
2671
+ "rstrip": false,
2672
+ "normalized": false,
2673
+ "special": false
2674
+ },
2675
+ {
2676
+ "id": 128296,
2677
+ "content": "<|special_38|>",
2678
+ "single_word": false,
2679
+ "lstrip": false,
2680
+ "rstrip": false,
2681
+ "normalized": false,
2682
+ "special": false
2683
+ },
2684
+ {
2685
+ "id": 128297,
2686
+ "content": "<|special_39|>",
2687
+ "single_word": false,
2688
+ "lstrip": false,
2689
+ "rstrip": false,
2690
+ "normalized": false,
2691
+ "special": false
2692
+ },
2693
+ {
2694
+ "id": 128298,
2695
+ "content": "<|special_40|>",
2696
+ "single_word": false,
2697
+ "lstrip": false,
2698
+ "rstrip": false,
2699
+ "normalized": false,
2700
+ "special": false
2701
+ },
2702
+ {
2703
+ "id": 128299,
2704
+ "content": "<|special_41|>",
2705
+ "single_word": false,
2706
+ "lstrip": false,
2707
+ "rstrip": false,
2708
+ "normalized": false,
2709
+ "special": false
2710
+ },
2711
+ {
2712
+ "id": 128300,
2713
+ "content": "<|special_42|>",
2714
+ "single_word": false,
2715
+ "lstrip": false,
2716
+ "rstrip": false,
2717
+ "normalized": false,
2718
+ "special": false
2719
+ },
2720
+ {
2721
+ "id": 128301,
2722
+ "content": "<|special_43|>",
2723
+ "single_word": false,
2724
+ "lstrip": false,
2725
+ "rstrip": false,
2726
+ "normalized": false,
2727
+ "special": false
2728
+ },
2729
+ {
2730
+ "id": 128302,
2731
+ "content": "<|special_44|>",
2732
+ "single_word": false,
2733
+ "lstrip": false,
2734
+ "rstrip": false,
2735
+ "normalized": false,
2736
+ "special": false
2737
+ },
2738
+ {
2739
+ "id": 128303,
2740
+ "content": "<|special_45|>",
2741
+ "single_word": false,
2742
+ "lstrip": false,
2743
+ "rstrip": false,
2744
+ "normalized": false,
2745
+ "special": false
2746
+ },
2747
+ {
2748
+ "id": 128304,
2749
+ "content": "<|special_46|>",
2750
+ "single_word": false,
2751
+ "lstrip": false,
2752
+ "rstrip": false,
2753
+ "normalized": false,
2754
+ "special": false
2755
+ },
2756
+ {
2757
+ "id": 128305,
2758
+ "content": "<|special_47|>",
2759
+ "single_word": false,
2760
+ "lstrip": false,
2761
+ "rstrip": false,
2762
+ "normalized": false,
2763
+ "special": false
2764
+ },
2765
+ {
2766
+ "id": 128306,
2767
+ "content": "<|special_48|>",
2768
+ "single_word": false,
2769
+ "lstrip": false,
2770
+ "rstrip": false,
2771
+ "normalized": false,
2772
+ "special": false
2773
+ },
2774
+ {
2775
+ "id": 128307,
2776
+ "content": "<|special_49|>",
2777
+ "single_word": false,
2778
+ "lstrip": false,
2779
+ "rstrip": false,
2780
+ "normalized": false,
2781
+ "special": false
2782
+ },
2783
+ {
2784
+ "id": 128308,
2785
+ "content": "<|special_50|>",
2786
+ "single_word": false,
2787
+ "lstrip": false,
2788
+ "rstrip": false,
2789
+ "normalized": false,
2790
+ "special": false
2791
+ },
2792
+ {
2793
+ "id": 128309,
2794
+ "content": "<|special_51|>",
2795
+ "single_word": false,
2796
+ "lstrip": false,
2797
+ "rstrip": false,
2798
+ "normalized": false,
2799
+ "special": false
2800
+ },
2801
+ {
2802
+ "id": 128310,
2803
+ "content": "<|special_52|>",
2804
+ "single_word": false,
2805
+ "lstrip": false,
2806
+ "rstrip": false,
2807
+ "normalized": false,
2808
+ "special": false
2809
+ },
2810
+ {
2811
+ "id": 128311,
2812
+ "content": "<|special_53|>",
2813
+ "single_word": false,
2814
+ "lstrip": false,
2815
+ "rstrip": false,
2816
+ "normalized": false,
2817
+ "special": false
2818
+ },
2819
+ {
2820
+ "id": 128312,
2821
+ "content": "<|special_54|>",
2822
+ "single_word": false,
2823
+ "lstrip": false,
2824
+ "rstrip": false,
2825
+ "normalized": false,
2826
+ "special": false
2827
+ },
2828
+ {
2829
+ "id": 128313,
2830
+ "content": "<|special_55|>",
2831
+ "single_word": false,
2832
+ "lstrip": false,
2833
+ "rstrip": false,
2834
+ "normalized": false,
2835
+ "special": false
2836
+ },
2837
+ {
2838
+ "id": 128314,
2839
+ "content": "<|special_56|>",
2840
+ "single_word": false,
2841
+ "lstrip": false,
2842
+ "rstrip": false,
2843
+ "normalized": false,
2844
+ "special": false
2845
+ },
2846
+ {
2847
+ "id": 128315,
2848
+ "content": "<|special_57|>",
2849
+ "single_word": false,
2850
+ "lstrip": false,
2851
+ "rstrip": false,
2852
+ "normalized": false,
2853
+ "special": false
2854
+ },
2855
+ {
2856
+ "id": 128316,
2857
+ "content": "<|special_58|>",
2858
+ "single_word": false,
2859
+ "lstrip": false,
2860
+ "rstrip": false,
2861
+ "normalized": false,
2862
+ "special": false
2863
+ },
2864
+ {
2865
+ "id": 128317,
2866
+ "content": "<|special_59|>",
2867
+ "single_word": false,
2868
+ "lstrip": false,
2869
+ "rstrip": false,
2870
+ "normalized": false,
2871
+ "special": false
2872
+ },
2873
+ {
2874
+ "id": 128318,
2875
+ "content": "<|special_60|>",
2876
+ "single_word": false,
2877
+ "lstrip": false,
2878
+ "rstrip": false,
2879
+ "normalized": false,
2880
+ "special": false
2881
+ },
2882
+ {
2883
+ "id": 128319,
2884
+ "content": "<|special_61|>",
2885
+ "single_word": false,
2886
+ "lstrip": false,
2887
+ "rstrip": false,
2888
+ "normalized": false,
2889
+ "special": false
2890
  }
2891
  ],
2892
  "normalizer": null,
 
2988
  "end_of_word_suffix": null,
2989
  "fuse_unk": false,
2990
  "byte_fallback": false,
2991
+ "ignore_merges": true,
2992
  "vocab": {
2993
  "!": 0,
2994
  "\"": 1,
tokenizer_config.json CHANGED
@@ -2047,16 +2047,535 @@
2047
  "rstrip": false,
2048
  "single_word": false,
2049
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|eot_id|>",
 
 
2056
  "model_input_names": [
2057
  "input_ids",
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 1000000000000000019884624838656,
2061
- "tokenizer_class": "PreTrainedTokenizerFast"
 
 
 
 
 
2062
  }
 
2047
  "rstrip": false,
2048
  "single_word": false,
2049
  "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<|im_start|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": false
2058
+ },
2059
+ "128257": {
2060
+ "content": "<|im_end|>",
2061
+ "lstrip": false,
2062
+ "normalized": false,
2063
+ "rstrip": false,
2064
+ "single_word": false,
2065
+ "special": false
2066
+ },
2067
+ "128258": {
2068
+ "content": "<|special_0|>",
2069
+ "lstrip": false,
2070
+ "normalized": false,
2071
+ "rstrip": false,
2072
+ "single_word": false,
2073
+ "special": false
2074
+ },
2075
+ "128259": {
2076
+ "content": "<|special_1|>",
2077
+ "lstrip": false,
2078
+ "normalized": false,
2079
+ "rstrip": false,
2080
+ "single_word": false,
2081
+ "special": false
2082
+ },
2083
+ "128260": {
2084
+ "content": "<|special_2|>",
2085
+ "lstrip": false,
2086
+ "normalized": false,
2087
+ "rstrip": false,
2088
+ "single_word": false,
2089
+ "special": false
2090
+ },
2091
+ "128261": {
2092
+ "content": "<|special_3|>",
2093
+ "lstrip": false,
2094
+ "normalized": false,
2095
+ "rstrip": false,
2096
+ "single_word": false,
2097
+ "special": false
2098
+ },
2099
+ "128262": {
2100
+ "content": "<|special_4|>",
2101
+ "lstrip": false,
2102
+ "normalized": false,
2103
+ "rstrip": false,
2104
+ "single_word": false,
2105
+ "special": false
2106
+ },
2107
+ "128263": {
2108
+ "content": "<|special_5|>",
2109
+ "lstrip": false,
2110
+ "normalized": false,
2111
+ "rstrip": false,
2112
+ "single_word": false,
2113
+ "special": false
2114
+ },
2115
+ "128264": {
2116
+ "content": "<|special_6|>",
2117
+ "lstrip": false,
2118
+ "normalized": false,
2119
+ "rstrip": false,
2120
+ "single_word": false,
2121
+ "special": false
2122
+ },
2123
+ "128265": {
2124
+ "content": "<|special_7|>",
2125
+ "lstrip": false,
2126
+ "normalized": false,
2127
+ "rstrip": false,
2128
+ "single_word": false,
2129
+ "special": false
2130
+ },
2131
+ "128266": {
2132
+ "content": "<|special_8|>",
2133
+ "lstrip": false,
2134
+ "normalized": false,
2135
+ "rstrip": false,
2136
+ "single_word": false,
2137
+ "special": false
2138
+ },
2139
+ "128267": {
2140
+ "content": "<|special_9|>",
2141
+ "lstrip": false,
2142
+ "normalized": false,
2143
+ "rstrip": false,
2144
+ "single_word": false,
2145
+ "special": false
2146
+ },
2147
+ "128268": {
2148
+ "content": "<|special_10|>",
2149
+ "lstrip": false,
2150
+ "normalized": false,
2151
+ "rstrip": false,
2152
+ "single_word": false,
2153
+ "special": false
2154
+ },
2155
+ "128269": {
2156
+ "content": "<|special_11|>",
2157
+ "lstrip": false,
2158
+ "normalized": false,
2159
+ "rstrip": false,
2160
+ "single_word": false,
2161
+ "special": false
2162
+ },
2163
+ "128270": {
2164
+ "content": "<|special_12|>",
2165
+ "lstrip": false,
2166
+ "normalized": false,
2167
+ "rstrip": false,
2168
+ "single_word": false,
2169
+ "special": false
2170
+ },
2171
+ "128271": {
2172
+ "content": "<|special_13|>",
2173
+ "lstrip": false,
2174
+ "normalized": false,
2175
+ "rstrip": false,
2176
+ "single_word": false,
2177
+ "special": false
2178
+ },
2179
+ "128272": {
2180
+ "content": "<|special_14|>",
2181
+ "lstrip": false,
2182
+ "normalized": false,
2183
+ "rstrip": false,
2184
+ "single_word": false,
2185
+ "special": false
2186
+ },
2187
+ "128273": {
2188
+ "content": "<|special_15|>",
2189
+ "lstrip": false,
2190
+ "normalized": false,
2191
+ "rstrip": false,
2192
+ "single_word": false,
2193
+ "special": false
2194
+ },
2195
+ "128274": {
2196
+ "content": "<|special_16|>",
2197
+ "lstrip": false,
2198
+ "normalized": false,
2199
+ "rstrip": false,
2200
+ "single_word": false,
2201
+ "special": false
2202
+ },
2203
+ "128275": {
2204
+ "content": "<|special_17|>",
2205
+ "lstrip": false,
2206
+ "normalized": false,
2207
+ "rstrip": false,
2208
+ "single_word": false,
2209
+ "special": false
2210
+ },
2211
+ "128276": {
2212
+ "content": "<|special_18|>",
2213
+ "lstrip": false,
2214
+ "normalized": false,
2215
+ "rstrip": false,
2216
+ "single_word": false,
2217
+ "special": false
2218
+ },
2219
+ "128277": {
2220
+ "content": "<|special_19|>",
2221
+ "lstrip": false,
2222
+ "normalized": false,
2223
+ "rstrip": false,
2224
+ "single_word": false,
2225
+ "special": false
2226
+ },
2227
+ "128278": {
2228
+ "content": "<|special_20|>",
2229
+ "lstrip": false,
2230
+ "normalized": false,
2231
+ "rstrip": false,
2232
+ "single_word": false,
2233
+ "special": false
2234
+ },
2235
+ "128279": {
2236
+ "content": "<|special_21|>",
2237
+ "lstrip": false,
2238
+ "normalized": false,
2239
+ "rstrip": false,
2240
+ "single_word": false,
2241
+ "special": false
2242
+ },
2243
+ "128280": {
2244
+ "content": "<|special_22|>",
2245
+ "lstrip": false,
2246
+ "normalized": false,
2247
+ "rstrip": false,
2248
+ "single_word": false,
2249
+ "special": false
2250
+ },
2251
+ "128281": {
2252
+ "content": "<|special_23|>",
2253
+ "lstrip": false,
2254
+ "normalized": false,
2255
+ "rstrip": false,
2256
+ "single_word": false,
2257
+ "special": false
2258
+ },
2259
+ "128282": {
2260
+ "content": "<|special_24|>",
2261
+ "lstrip": false,
2262
+ "normalized": false,
2263
+ "rstrip": false,
2264
+ "single_word": false,
2265
+ "special": false
2266
+ },
2267
+ "128283": {
2268
+ "content": "<|special_25|>",
2269
+ "lstrip": false,
2270
+ "normalized": false,
2271
+ "rstrip": false,
2272
+ "single_word": false,
2273
+ "special": false
2274
+ },
2275
+ "128284": {
2276
+ "content": "<|special_26|>",
2277
+ "lstrip": false,
2278
+ "normalized": false,
2279
+ "rstrip": false,
2280
+ "single_word": false,
2281
+ "special": false
2282
+ },
2283
+ "128285": {
2284
+ "content": "<|special_27|>",
2285
+ "lstrip": false,
2286
+ "normalized": false,
2287
+ "rstrip": false,
2288
+ "single_word": false,
2289
+ "special": false
2290
+ },
2291
+ "128286": {
2292
+ "content": "<|special_28|>",
2293
+ "lstrip": false,
2294
+ "normalized": false,
2295
+ "rstrip": false,
2296
+ "single_word": false,
2297
+ "special": false
2298
+ },
2299
+ "128287": {
2300
+ "content": "<|special_29|>",
2301
+ "lstrip": false,
2302
+ "normalized": false,
2303
+ "rstrip": false,
2304
+ "single_word": false,
2305
+ "special": false
2306
+ },
2307
+ "128288": {
2308
+ "content": "<|special_30|>",
2309
+ "lstrip": false,
2310
+ "normalized": false,
2311
+ "rstrip": false,
2312
+ "single_word": false,
2313
+ "special": false
2314
+ },
2315
+ "128289": {
2316
+ "content": "<|special_31|>",
2317
+ "lstrip": false,
2318
+ "normalized": false,
2319
+ "rstrip": false,
2320
+ "single_word": false,
2321
+ "special": false
2322
+ },
2323
+ "128290": {
2324
+ "content": "<|special_32|>",
2325
+ "lstrip": false,
2326
+ "normalized": false,
2327
+ "rstrip": false,
2328
+ "single_word": false,
2329
+ "special": false
2330
+ },
2331
+ "128291": {
2332
+ "content": "<|special_33|>",
2333
+ "lstrip": false,
2334
+ "normalized": false,
2335
+ "rstrip": false,
2336
+ "single_word": false,
2337
+ "special": false
2338
+ },
2339
+ "128292": {
2340
+ "content": "<|special_34|>",
2341
+ "lstrip": false,
2342
+ "normalized": false,
2343
+ "rstrip": false,
2344
+ "single_word": false,
2345
+ "special": false
2346
+ },
2347
+ "128293": {
2348
+ "content": "<|special_35|>",
2349
+ "lstrip": false,
2350
+ "normalized": false,
2351
+ "rstrip": false,
2352
+ "single_word": false,
2353
+ "special": false
2354
+ },
2355
+ "128294": {
2356
+ "content": "<|special_36|>",
2357
+ "lstrip": false,
2358
+ "normalized": false,
2359
+ "rstrip": false,
2360
+ "single_word": false,
2361
+ "special": false
2362
+ },
2363
+ "128295": {
2364
+ "content": "<|special_37|>",
2365
+ "lstrip": false,
2366
+ "normalized": false,
2367
+ "rstrip": false,
2368
+ "single_word": false,
2369
+ "special": false
2370
+ },
2371
+ "128296": {
2372
+ "content": "<|special_38|>",
2373
+ "lstrip": false,
2374
+ "normalized": false,
2375
+ "rstrip": false,
2376
+ "single_word": false,
2377
+ "special": false
2378
+ },
2379
+ "128297": {
2380
+ "content": "<|special_39|>",
2381
+ "lstrip": false,
2382
+ "normalized": false,
2383
+ "rstrip": false,
2384
+ "single_word": false,
2385
+ "special": false
2386
+ },
2387
+ "128298": {
2388
+ "content": "<|special_40|>",
2389
+ "lstrip": false,
2390
+ "normalized": false,
2391
+ "rstrip": false,
2392
+ "single_word": false,
2393
+ "special": false
2394
+ },
2395
+ "128299": {
2396
+ "content": "<|special_41|>",
2397
+ "lstrip": false,
2398
+ "normalized": false,
2399
+ "rstrip": false,
2400
+ "single_word": false,
2401
+ "special": false
2402
+ },
2403
+ "128300": {
2404
+ "content": "<|special_42|>",
2405
+ "lstrip": false,
2406
+ "normalized": false,
2407
+ "rstrip": false,
2408
+ "single_word": false,
2409
+ "special": false
2410
+ },
2411
+ "128301": {
2412
+ "content": "<|special_43|>",
2413
+ "lstrip": false,
2414
+ "normalized": false,
2415
+ "rstrip": false,
2416
+ "single_word": false,
2417
+ "special": false
2418
+ },
2419
+ "128302": {
2420
+ "content": "<|special_44|>",
2421
+ "lstrip": false,
2422
+ "normalized": false,
2423
+ "rstrip": false,
2424
+ "single_word": false,
2425
+ "special": false
2426
+ },
2427
+ "128303": {
2428
+ "content": "<|special_45|>",
2429
+ "lstrip": false,
2430
+ "normalized": false,
2431
+ "rstrip": false,
2432
+ "single_word": false,
2433
+ "special": false
2434
+ },
2435
+ "128304": {
2436
+ "content": "<|special_46|>",
2437
+ "lstrip": false,
2438
+ "normalized": false,
2439
+ "rstrip": false,
2440
+ "single_word": false,
2441
+ "special": false
2442
+ },
2443
+ "128305": {
2444
+ "content": "<|special_47|>",
2445
+ "lstrip": false,
2446
+ "normalized": false,
2447
+ "rstrip": false,
2448
+ "single_word": false,
2449
+ "special": false
2450
+ },
2451
+ "128306": {
2452
+ "content": "<|special_48|>",
2453
+ "lstrip": false,
2454
+ "normalized": false,
2455
+ "rstrip": false,
2456
+ "single_word": false,
2457
+ "special": false
2458
+ },
2459
+ "128307": {
2460
+ "content": "<|special_49|>",
2461
+ "lstrip": false,
2462
+ "normalized": false,
2463
+ "rstrip": false,
2464
+ "single_word": false,
2465
+ "special": false
2466
+ },
2467
+ "128308": {
2468
+ "content": "<|special_50|>",
2469
+ "lstrip": false,
2470
+ "normalized": false,
2471
+ "rstrip": false,
2472
+ "single_word": false,
2473
+ "special": false
2474
+ },
2475
+ "128309": {
2476
+ "content": "<|special_51|>",
2477
+ "lstrip": false,
2478
+ "normalized": false,
2479
+ "rstrip": false,
2480
+ "single_word": false,
2481
+ "special": false
2482
+ },
2483
+ "128310": {
2484
+ "content": "<|special_52|>",
2485
+ "lstrip": false,
2486
+ "normalized": false,
2487
+ "rstrip": false,
2488
+ "single_word": false,
2489
+ "special": false
2490
+ },
2491
+ "128311": {
2492
+ "content": "<|special_53|>",
2493
+ "lstrip": false,
2494
+ "normalized": false,
2495
+ "rstrip": false,
2496
+ "single_word": false,
2497
+ "special": false
2498
+ },
2499
+ "128312": {
2500
+ "content": "<|special_54|>",
2501
+ "lstrip": false,
2502
+ "normalized": false,
2503
+ "rstrip": false,
2504
+ "single_word": false,
2505
+ "special": false
2506
+ },
2507
+ "128313": {
2508
+ "content": "<|special_55|>",
2509
+ "lstrip": false,
2510
+ "normalized": false,
2511
+ "rstrip": false,
2512
+ "single_word": false,
2513
+ "special": false
2514
+ },
2515
+ "128314": {
2516
+ "content": "<|special_56|>",
2517
+ "lstrip": false,
2518
+ "normalized": false,
2519
+ "rstrip": false,
2520
+ "single_word": false,
2521
+ "special": false
2522
+ },
2523
+ "128315": {
2524
+ "content": "<|special_57|>",
2525
+ "lstrip": false,
2526
+ "normalized": false,
2527
+ "rstrip": false,
2528
+ "single_word": false,
2529
+ "special": false
2530
+ },
2531
+ "128316": {
2532
+ "content": "<|special_58|>",
2533
+ "lstrip": false,
2534
+ "normalized": false,
2535
+ "rstrip": false,
2536
+ "single_word": false,
2537
+ "special": false
2538
+ },
2539
+ "128317": {
2540
+ "content": "<|special_59|>",
2541
+ "lstrip": false,
2542
+ "normalized": false,
2543
+ "rstrip": false,
2544
+ "single_word": false,
2545
+ "special": false
2546
+ },
2547
+ "128318": {
2548
+ "content": "<|special_60|>",
2549
+ "lstrip": false,
2550
+ "normalized": false,
2551
+ "rstrip": false,
2552
+ "single_word": false,
2553
+ "special": false
2554
+ },
2555
+ "128319": {
2556
+ "content": "<|special_61|>",
2557
+ "lstrip": false,
2558
+ "normalized": false,
2559
+ "rstrip": false,
2560
+ "single_word": false,
2561
+ "special": false
2562
  }
2563
  },
2564
  "bos_token": "<|begin_of_text|>",
2565
  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2566
  "clean_up_tokenization_spaces": true,
2567
  "eos_token": "<|eot_id|>",
2568
+ "legacy": false,
2569
+ "max_length": 8001,
2570
  "model_input_names": [
2571
  "input_ids",
2572
  "attention_mask"
2573
  ],
2574
  "model_max_length": 1000000000000000019884624838656,
2575
+ "pad_token": "<|eot_id|>",
2576
+ "padding_side": "right",
2577
+ "stride": 0,
2578
+ "tokenizer_class": "PreTrainedTokenizerFast",
2579
+ "truncation_side": "right",
2580
+ "truncation_strategy": "longest_first"
2581
  }