hofitB commited on
Commit
b57ba6c
1 Parent(s): e6ea823

Model save

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +69 -0
  2. config.json +45 -0
  3. generation_config.json +10 -0
  4. model-00001-of-00042.safetensors +3 -0
  5. model-00002-of-00042.safetensors +3 -0
  6. model-00003-of-00042.safetensors +3 -0
  7. model-00004-of-00042.safetensors +3 -0
  8. model-00005-of-00042.safetensors +3 -0
  9. model-00006-of-00042.safetensors +3 -0
  10. model-00007-of-00042.safetensors +3 -0
  11. model-00008-of-00042.safetensors +3 -0
  12. model-00009-of-00042.safetensors +3 -0
  13. model-00010-of-00042.safetensors +3 -0
  14. model-00011-of-00042.safetensors +3 -0
  15. model-00012-of-00042.safetensors +3 -0
  16. model-00013-of-00042.safetensors +3 -0
  17. model-00014-of-00042.safetensors +3 -0
  18. model-00015-of-00042.safetensors +3 -0
  19. model-00016-of-00042.safetensors +3 -0
  20. model-00017-of-00042.safetensors +3 -0
  21. model-00018-of-00042.safetensors +3 -0
  22. model-00019-of-00042.safetensors +3 -0
  23. model-00020-of-00042.safetensors +3 -0
  24. model-00021-of-00042.safetensors +3 -0
  25. model-00022-of-00042.safetensors +3 -0
  26. model-00023-of-00042.safetensors +3 -0
  27. model-00024-of-00042.safetensors +3 -0
  28. model-00025-of-00042.safetensors +3 -0
  29. model-00026-of-00042.safetensors +3 -0
  30. model-00027-of-00042.safetensors +3 -0
  31. model-00028-of-00042.safetensors +3 -0
  32. model-00029-of-00042.safetensors +3 -0
  33. model-00030-of-00042.safetensors +3 -0
  34. model-00031-of-00042.safetensors +3 -0
  35. model-00032-of-00042.safetensors +3 -0
  36. model-00033-of-00042.safetensors +3 -0
  37. model-00034-of-00042.safetensors +3 -0
  38. model-00035-of-00042.safetensors +3 -0
  39. model-00036-of-00042.safetensors +3 -0
  40. model-00037-of-00042.safetensors +3 -0
  41. model-00038-of-00042.safetensors +3 -0
  42. model-00039-of-00042.safetensors +3 -0
  43. model-00040-of-00042.safetensors +3 -0
  44. model-00041-of-00042.safetensors +3 -0
  45. model-00042-of-00042.safetensors +3 -0
  46. model.safetensors.index.json +0 -0
  47. special_tokens_map.json +48 -0
  48. tokenizer.json +0 -0
  49. tokenizer.model +3 -0
  50. tokenizer_config.json +196 -0
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: ai21labs/AI21-Jamba-1.5-Mini
5
+ tags:
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
+ datasets:
10
+ - generator
11
+ model-index:
12
+ - name: Jamba-1.5-Mini-Full-FT
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # Jamba-1.5-Mini-Full-FT
20
+
21
+ This model is a fine-tuned version of [ai21labs/AI21-Jamba-1.5-Mini](https://huggingface.co/ai21labs/AI21-Jamba-1.5-Mini) on the generator dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.7744
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 1e-06
43
+ - train_batch_size: 2
44
+ - eval_batch_size: 1
45
+ - seed: 42
46
+ - distributed_type: multi-GPU
47
+ - num_devices: 64
48
+ - total_train_batch_size: 128
49
+ - total_eval_batch_size: 64
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: cosine
52
+ - lr_scheduler_warmup_ratio: 0.01
53
+ - num_epochs: 3
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss |
58
+ |:-------------:|:-----:|:----:|:---------------:|
59
+ | 0.778 | 1.0 | 159 | 0.8063 |
60
+ | 0.7417 | 2.0 | 318 | 0.7769 |
61
+ | 0.7136 | 3.0 | 477 | 0.7744 |
62
+
63
+
64
+ ### Framework versions
65
+
66
+ - Transformers 4.45.0.dev0
67
+ - Pytorch 2.1.0
68
+ - Datasets 2.18.0
69
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ai21labs/AI21-Jamba-1.5-Mini",
3
+ "architectures": [
4
+ "JambaForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "attn_layer_offset": 4,
8
+ "attn_layer_period": 8,
9
+ "bos_token_id": 1,
10
+ "eos_token_id": [
11
+ 2,
12
+ 518
13
+ ],
14
+ "expert_layer_offset": 1,
15
+ "expert_layer_period": 2,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 4096,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 14336,
20
+ "mamba_conv_bias": true,
21
+ "mamba_d_conv": 4,
22
+ "mamba_d_state": 16,
23
+ "mamba_dt_rank": 256,
24
+ "mamba_expand": 2,
25
+ "mamba_proj_bias": false,
26
+ "max_position_embeddings": 262144,
27
+ "model_type": "jamba",
28
+ "num_attention_heads": 32,
29
+ "num_experts": 16,
30
+ "num_experts_per_tok": 2,
31
+ "num_hidden_layers": 32,
32
+ "num_key_value_heads": 8,
33
+ "num_logits_to_keep": 1,
34
+ "output_router_logits": false,
35
+ "pad_token_id": 0,
36
+ "rms_norm_eps": 1e-06,
37
+ "router_aux_loss_coef": 0.001,
38
+ "sliding_window": null,
39
+ "tie_word_embeddings": false,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.45.0.dev0",
42
+ "use_cache": true,
43
+ "use_mamba_kernels": true,
44
+ "vocab_size": 65536
45
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 2,
6
+ 518
7
+ ],
8
+ "pad_token_id": 0,
9
+ "transformers_version": "4.45.0.dev0"
10
+ }
model-00001-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ce57a60656c177403d4e85a660ec1552d9a89b901b3d66f2bf8d279ad6edecf
3
+ size 4869299856
model-00002-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6caec630cf4718587424bec6052184231e3f5c332037affcfb127e41381785c3
3
+ size 4932504312
model-00003-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cc46fa7c2152f199d5c3b349c4c21aa7c6b117dceed98feb61fa65955bbc4b6
3
+ size 4835778096
model-00004-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fa2bc4f5f7e5ef7693fc25e8893859c3956d40e3ea5f4c0e2056cb9aee35abb
3
+ size 4932504312
model-00005-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cbd4cb8eeb3a616886a7f2477e2ffc0f41a802e787e193c76dcae549fcc0718
3
+ size 4932504320
model-00006-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9795a9272b92b6cbecfebc79dba272c80a40ef93b17f9c1dacd1c7bc7a14c1b1
3
+ size 4817196776
model-00007-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79f0272c8607ac80bd3d05484c7af3ac4ccf215309dfcc481f0a947e16245faa
3
+ size 4932504312
model-00008-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad0d6d9c7d2c2d7b4b694cd04487dc2b3bf57d5d81c6fe23153a6e1531412f02
3
+ size 4884010072
model-00009-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b7c1cc79f96f7e814aa8571438aa8e7560dd705643bc46c8497eed4ec83b842
3
+ size 4884272328
model-00010-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e23b72989930b0c8673f8749bf3a0ea7a4d861ec7c27914f263b407aed9b562c
3
+ size 4932504320
model-00011-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec8ddd7591c9a3bbd7bf5cd614514eb22624088a0217f121d3dd5f2515ce33d
3
+ size 4835778088
model-00012-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23759fff6560e56d6c260249e5eade6161eea490a056117948c88d8553dea1d3
3
+ size 4932504312
model-00013-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2620baf3d354148ca7a49e1a13fe0e7826f23abb0589f82ba017f9c9821216dd
3
+ size 4932504328
model-00014-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00367b4839aee9cfd3991f9201db55f04d6df90236b5c2fb21f51e125f6cface
3
+ size 4835778104
model-00015-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c5663cca40eb9b79116e306fd2329d7305b6315c75e11ea2c2d8c8aa72e28b6
3
+ size 4932504336
model-00016-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a38049b0710af1f5b735ab40dcc2dda5cb247fa3f5c6c680224d7cb3e5819e98
3
+ size 4817196824
model-00017-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fedd0b53b9e0d32aa5116bdce89dec90ba512f7ca02c602b9fa797ca4e65bc4b
3
+ size 4932504328
model-00018-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c77c131f719a5d09a6d422e2b814fc341f9ab41280f7b53b5b0e818b1d6acbd6
3
+ size 4932504344
model-00019-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac5343a630dcb2205e8c71b3a70166c0813c1c2251bb10deb20744f7f45a187f
3
+ size 4835778128
model-00020-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a55e0b0c96e319c0c26c6f59bd04a23e076c666abbdcdf42b2b729e68e48f67a
3
+ size 4932504328
model-00021-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d81124ee6d092a1e3fb66033bbde0f1a1fcafe8a210cfcdd5b91402bb3edc3a6
3
+ size 4884010120
model-00022-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5792374f5b1532453abb221e338094df364cc6faf1ae7b3880d1550e7a30ccbc
3
+ size 4884272352
model-00023-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15115c0565ed5adab6255ad0958860e7853613bade006890583bf9eda8142a56
3
+ size 4932504336
model-00024-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a523f95edf20db5fb9b62dd6cb0d545c4de790493c31fbcdc6577e45c3dd3a1
3
+ size 4835778136
model-00025-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96e85a3fd2a00e667be004012d11e19fdbd59de21a09da01da954fb293e4a909
3
+ size 4932504328
model-00026-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38976bc4ab2875d6b046dcf3f42fe4dfdf35916c84afe5f762e6427b2cfb7f4a
3
+ size 4932504344
model-00027-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e56c70ba6ce1f9ac631441dcff1edc5a71e08be0f4316a862323d5e2ea1356e
3
+ size 4817196808
model-00028-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9b0afd3ea2c06544d8d4bbb6cfb1f0ee9c431de1af08bd368423bd3d9e549d2
3
+ size 4932504336
model-00029-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc9ff7971e57c9930ede40d2eaea2bd2af0db6ded6483ad3a679d90d0464fbc2
3
+ size 4835778144
model-00030-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d8b95284cd96df60b487d43f88c290d77cb0b46c123fbb9ee47e6f3382dcb32
3
+ size 4932504328
model-00031-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1703f7ae1f91a328a7d3c14a6221a9684d9be7d2a95c1ab578e50ca18e74be75
3
+ size 4932504344
model-00032-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:461b7f455cdde676cfde81cc77dbbc6b2337ddd0bddc564bdc095a90f442ea59
3
+ size 4835778136
model-00033-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3660298e8e0a33f44ab170d5af82f6fbc4d149b89ac7084fb495304e4343eb58
3
+ size 4932504328
model-00034-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8db7aae443b76a3c6f7ea79000a849e1a8a3b989e21f21f4fdb14b5ddcf04654
3
+ size 4884010128
model-00035-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d022cc6349d96ce40d869e8ed60941f4b8eb6260feb6644f2641afc8a709cbf
3
+ size 4884272344
model-00036-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4b73d204a87f77f65120963dd0b0884e8fc01853b95d603cefc2644a5066d65
3
+ size 4932504336
model-00037-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1cbc9da7d6792866be807656e866264c11b3cef1d9c66211595dbf9c1b66ed6
3
+ size 4817196816
model-00038-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ff1a3a022d5606543cd30051749e53ee6184abe9ab391d56e58fe1fc70648de
3
+ size 4932504328
model-00039-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b343950e9d51619721c5fad790b72e3722b714ec4569cb8a85ef0b08f21e1c52
3
+ size 4932504344
model-00040-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:777f4f484996f31a514b004363f0d14ed3a06ee5c438f7c08e676b5c7dbbf785
3
+ size 4835778128
model-00041-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4bdc6dfa20911ad42b68adad655ce27e216d9552684634daf3d5c83ba2b753d
3
+ size 4932504336
model-00042-of-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff740610e918676127ef76159079a24e4c602625cd3beb477d26291d619ad370
3
+ size 3523250536
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|eom|>",
4
+ "<|bom|>",
5
+ "<|system|>",
6
+ "<|user|>",
7
+ "<|assistant|>",
8
+ "<|tool|>",
9
+ "<documents>",
10
+ "</documents>",
11
+ "<tool_definitions>",
12
+ "</tool_definitions>",
13
+ "<active_output_modes>",
14
+ "</active_output_modes>",
15
+ "<citations>",
16
+ "</citations>",
17
+ "<tool_calls>",
18
+ "</tool_calls>"
19
+ ],
20
+ "bos_token": {
21
+ "content": "<|startoftext|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "eos_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "pad_token": {
35
+ "content": "<|pad|>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "unk_token": {
42
+ "content": "<|unk|>",
43
+ "lstrip": false,
44
+ "normalized": false,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ }
48
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b0df4fb43262c452ef37061951a06df4c63ca191d02a60ea08f14428af24376
3
+ size 1124714
tokenizer_config.json ADDED
@@ -0,0 +1,196 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|pad|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|startoftext|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<|endoftext|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "3": {
31
+ "content": "<|unk|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "518": {
39
+ "content": "<|eom|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "519": {
47
+ "content": "<|bom|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "520": {
55
+ "content": "<|system|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "521": {
63
+ "content": "<|user|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "522": {
71
+ "content": "<|assistant|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "523": {
79
+ "content": "<|tool|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "524": {
87
+ "content": "<documents>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "525": {
95
+ "content": "</documents>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "526": {
103
+ "content": "<tool_definitions>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "527": {
111
+ "content": "</tool_definitions>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "528": {
119
+ "content": "<active_output_modes>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "529": {
127
+ "content": "</active_output_modes>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "530": {
135
+ "content": "<citations>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "531": {
143
+ "content": "</citations>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "532": {
151
+ "content": "<tool_calls>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "533": {
159
+ "content": "</tool_calls>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": true
165
+ }
166
+ },
167
+ "additional_special_tokens": [
168
+ "<|eom|>",
169
+ "<|bom|>",
170
+ "<|system|>",
171
+ "<|user|>",
172
+ "<|assistant|>",
173
+ "<|tool|>",
174
+ "<documents>",
175
+ "</documents>",
176
+ "<tool_definitions>",
177
+ "</tool_definitions>",
178
+ "<active_output_modes>",
179
+ "</active_output_modes>",
180
+ "<citations>",
181
+ "</citations>",
182
+ "<tool_calls>",
183
+ "</tool_calls>"
184
+ ],
185
+ "bos_token": "<|startoftext|>",
186
+ "chat_template": "{# Variables #}\n{% set ns = namespace(message_count=0, is_last_checked_defined=False) %}\n{##}\n{% set bom_str = bom_str or \"<|bom|>\" %}\n{% set eom_str = eom_str or \"<|eom|>\" %}\n{% set default_system_message = \"\" %}\n{##}\n{% set documents_prefix = \"<documents>\" %}\n{% set documents_suffix = \"</documents>\" %}\n{% set tool_definitions_prefix = \"<tool_definitions>\" %}\n{% set tool_definitions_suffix = \"</tool_definitions>\" %}\n{% set active_modes_prefix = \"<active_output_modes>\" %}\n{% set active_modes_suffix = \"</active_output_modes>\" %}\n{##}\n{% set tool_calls_prefix = \"<tool_calls>\" %}\n{% set tool_calls_suffix = \"</tool_calls>\" %}\n{% set citations_prefix = \"<citations>\" %}\n{% set citations_suffix = \"</citations>\" %}\n{##}\n{% if add_generation_prompt is not defined %}\n {% set add_generation_prompt = True %}\n{% endif %}\n{% set role_to_predict = role_to_predict or \"assistant\" %}\n{% if messages|length > 0 and messages[0].role == \"system\" %}\n {% set system_message = messages[0].content %}\n {% set loop_messages = messages[1:] %}\n{% else %}\n {% set system_message = default_system_message %}\n {% set loop_messages = messages %}\n{% endif %}\n{##}\n{##}\n{# Macros #}\n{% macro handle_tool_definitions(tools) %}\n {{- tool_definitions_prefix -}}\n {{- \"\\n# Tools\" -}}\n {{- \"\\n\\n## Functions\" -}}\n {% for tool in tools %}\n {% set _ = is_param_set(tool, field=\"type\") %}\n {% set is_tool_type_set = ns.is_last_checked_defined %}\n {% if is_tool_type_set %}\n {% if tool.type == \"function\" %}\n {% set tool = tool.function %}\n {% else %}\n {{ raise_exception(\"Currently, the only supported tool type is `function`\") }}\n {% endif %}\n {% endif %}\n {{- \"\\n\\n\" + (tool|tojson(indent=2)) -}}\n {% endfor %}\n {{- \"\\n\" + tool_definitions_suffix -}}\n{% endmacro %}\n{##}\n{% macro handle_first_system_message(system_message, tools) %}\n {{- bom_str + handle_role(\"system\") -}}\n {% set _ = is_param_set(system_message) %}\n {% set is_system_message_set = ns.is_last_checked_defined %}\n {% if is_system_message_set %}\n {{- system_message -}}\n {% endif %}\n {% set _ = is_param_set(tools, is_list=True) %}\n {% set is_tools_set = ns.is_last_checked_defined %}\n {% if is_tools_set %}\n {% if system_message %}\n {{- \"\\n\\n\" -}}\n {% endif %}\n {{- handle_tool_definitions(tools) -}}\n {% endif %}\n {% set ns.message_count = ns.message_count + 1 %}\n{% endmacro %}\n{##}\n{% macro handle_tool_calls(tool_calls) %}\n {{- tool_calls_prefix + \"[\\n\" -}}\n {% for tool_call in tool_calls %}\n {% set _ = is_param_set(tool_call, field=\"function\") %}\n {% set is_tool_call_function_set = ns.is_last_checked_defined %}\n {% if is_tool_call_function_set %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {% set arguments = tool_call.arguments %}\n {% if arguments is not string %}\n {%- set arguments = arguments|tojson -%}\n {%- endif %}\n {{ \"{\\\"name\\\": \\\"\" + tool_call.name + \"\\\", \\\"arguments\\\": \" + arguments + \"}\" -}}\n {% if not loop.last %}\n {{- \",\" }}\n {% endif %}\n {% endfor %}\n {{- \"\\n]\" + tool_calls_suffix -}}\n{% endmacro %}\n{##}\n{% macro handle_documents(documents) %}\n {{- documents_prefix -}}\n {{- \"\\n# Documents\" -}}\n {{- \"\\n\\nYou can use the following documents for reference:\" -}}\n {% for doc in documents %}\n {{- \"\\n\\n## Document ID: \" + loop.index0|string -}}\n {% set _ = is_param_set(doc, field=\"title\") %}\n {% set is_doc_title_set = ns.is_last_checked_defined %}\n {% if is_doc_title_set %}\n {{- \"\\nTitle: \" + doc.title -}}\n {% endif %}\n {% for key, value in doc.items() %}\n {% if key not in [\"title\", \"text\"] %}\n {{- \"\\n\" + key|title + \": \" + value|string -}}\n {% endif %}\n {% endfor %}\n {{- \"\\nText: \" + doc.text -}}\n {% endfor %}\n {{- \"\\n\" + documents_suffix -}}\n{% endmacro %}\n{##}\n{% macro handle_knobs(knobs) %}\n {{- active_modes_prefix -}}\n {{- \"\\n# Active Modes\" -}}\n {{ \"\\n\\nThe following modes configure the format or style of your responses. You should adhere to all currently\" -}}\n {{ \" active modes simultaneously.\" -}}\n {% if knobs.citation_mode == \"fast\" %}\n {{- \"\\n\\n## Citation Mode\" -}}\n {{- \"\\n\\nProvide a list of references only for the documents you base your response on. Format your response\" -}}\n {{ \" with the original answer followed by a citation section. Use this template:\" -}}\n {{ \" `{answer}\" + citations_prefix + \"DOCUMENT_IDS\" + citations_suffix + \"`, where DOCUMENT_IDS are the relevant document numbers\" -}}\n {{ \" (e.g. [2, 5, 9]), or [] if the answer cannot be supported by the provided documents.\" -}}\n {% endif %}\n {% if knobs.response_format == \"json_object\" %}\n {{- \"\\n\\n## JSON Mode\" -}}\n {{ \"\\n\\nProvide your response in JSON format. Adhere strictly to any schema given by the user.\" -}}\n {{ \" If an appropriate JSON format exists, use it without modification.\" -}}\n {% endif %}\n {{- \"\\n\" + active_modes_suffix -}}\n{% endmacro %}\n{##}\n{% macro get_last_user_index(messages) %}\n {% set ns.last_user_index = 0 %}\n {% for message in messages %}\n {% if message.role == 'user' %}\n {% set ns.last_user_index = loop.index0 %}\n {% endif %}\n {% endfor %}\n {{- ns.last_user_index -}}\n{% endmacro %}\n{##}\n{% macro handle_last_system_message(documents, knobs, use_documents, use_knobs) %}\n {{- bom_str + handle_role(\"system\") -}}\n {% set macros_to_call = [] %}\n {% set params_for_macros = [] %}\n {% if use_documents %}\n {% set macros_to_call = macros_to_call + [handle_documents] %}\n {% set params_for_macros = params_for_macros + [[documents]] %}\n {% endif %}\n {% if use_knobs %}\n {% set macros_to_call = macros_to_call + [handle_knobs] %}\n {% set params_for_macros = params_for_macros + [[knobs]] %}\n {% endif %}\n {% for i in range(macros_to_call|length) %}\n {% if i > 0 %}\n {{- \"\\n\\n\" -}}\n {% endif %}\n {{- macros_to_call[i](*params_for_macros[i]) -}}\n {% endfor %}\n {% set ns.message_count = ns.message_count + 1 %}\n{% endmacro %}\n{##}\n{% macro handle_role(role, add_space=True) %}\n {{- \"<|\" + role + \"|>\" -}}\n {% if add_space %}\n {{- \" \" -}}\n {% endif %}\n{% endmacro %}\n{##}\n{% macro is_param_set(param, field=none, is_list=False) %}\n {% if field is not none %}\n {% if field in param %}\n {% set param = param[field] %}\n {% else %}\n {% set param = none %}\n {% endif %}\n {% endif %}\n {% set is_defined = param is defined and param is not none %}\n {% if is_list %}\n {% set ns.is_last_checked_defined = is_defined and param|length > 0 %}\n {% else %}\n {% set ns.is_last_checked_defined = is_defined %}\n {% endif %}\n{% endmacro %}\n{##}\n{##}\n{# Template #}\n{{- \"<|startoftext|>\" -}}\n{% set _ = is_param_set(system_message) %}\n{% set is_system_message_set = ns.is_last_checked_defined %}\n{% set _ = is_param_set(tools, is_list=True) %}\n{% set is_tools_set = ns.is_last_checked_defined %}\n{% set has_system_message = (is_system_message_set or is_tools_set) %}\n{% if has_system_message %}\n {{- handle_first_system_message(system_message, tools) -}}\n{% endif %}\n{% set last_user_index = get_last_user_index(loop_messages)|int %}\n{% for message in loop_messages %}\n {% if loop.index0 == last_user_index %}\n {% set _ = is_param_set(documents, is_list=True) %}\n {% set use_documents = ns.is_last_checked_defined %}\n {% set _ = is_param_set(knobs) %}\n {% set use_knobs = ns.is_last_checked_defined and knobs.is_set %}\n {% set add_last_system_message = use_documents or use_knobs %}\n {% if add_last_system_message %}\n {% if ns.message_count > 0 %}\n {{- eom_str -}}\n {% endif %}\n {{- handle_last_system_message(documents, knobs, use_documents, use_knobs) -}}\n {% endif %}\n {% endif %}\n {% set role = message.role %}\n {% set _ = is_param_set(message, field=\"name\") %}\n {% set is_message_name_set = ns.is_last_checked_defined %}\n {% if is_message_name_set %}\n {% set message_prefix = handle_role(role) + \"(\" + message.name + \")\" %}\n {% else %}\n {% set message_prefix = handle_role(role) %}\n {% endif %}\n {% set content = (message.content or \"\") %}\n {% if content is not string %}\n {% set content = content|tojson %}\n {% endif %}\n {% if ns.message_count > 0 %}\n {{- eom_str -}}\n {% endif %}\n {{- bom_str + message_prefix + content -}}\n {% set _ = is_param_set(message, field=\"tool_calls\", is_list=True) %}\n {% set is_tool_calls_set = ns.is_last_checked_defined %}\n {% if role == \"assistant\" and is_tool_calls_set %}\n {{- handle_tool_calls(message.tool_calls) -}}\n {% endif %}\n {% set _ = is_param_set(message, field=\"citations\", is_list=True) %}\n {% set is_citations_set = ns.is_last_checked_defined %}\n {% if role == \"assistant\" and is_citations_set %}\n {{- citations_prefix + message.citations|map(attribute=\"document_id\")|list|string + citations_suffix -}}\n {% endif %}\n {% set ns.message_count = ns.message_count + 1 %}\n{% endfor %}\n{% if add_generation_prompt %}\n {% if ns.message_count > 0 %}\n {{- eom_str -}}\n {% endif %}\n {{- bom_str + handle_role(role_to_predict, add_space=False) -}}\n {% set _ = is_param_set(generation_preamble) %}\n {% set is_generation_preamble_set = ns.is_last_checked_defined %}\n {% if is_generation_preamble_set and generation_preamble.strip() != \"\" %}\n {{- \" \" + generation_preamble -}}\n {% endif %}\n {% set ns.message_count = ns.message_count + 1 %}\n{% else %}\n {% if ns.message_count > 0 %}\n {{- eom_str -}}\n {% endif %}\n{% endif %}\n",
187
+ "clean_up_tokenization_spaces": false,
188
+ "eos_token": "<|endoftext|>",
189
+ "legacy": true,
190
+ "model_max_length": 2048,
191
+ "pad_token": "<|pad|>",
192
+ "spaces_between_special_tokens": false,
193
+ "tokenizer_class": "LlamaTokenizer",
194
+ "unk_token": "<|unk|>",
195
+ "use_default_system_prompt": false
196
+ }