leonardlin
commited on
Upload folder using huggingface_hub
Browse files- config.json +49 -0
- generation_config.json +8 -0
- pytorch_model-00001-of-00021.bin +3 -0
- pytorch_model-00002-of-00021.bin +3 -0
- pytorch_model-00003-of-00021.bin +3 -0
- pytorch_model-00004-of-00021.bin +3 -0
- pytorch_model-00005-of-00021.bin +3 -0
- pytorch_model-00006-of-00021.bin +3 -0
- pytorch_model-00007-of-00021.bin +3 -0
- pytorch_model-00008-of-00021.bin +3 -0
- pytorch_model-00009-of-00021.bin +3 -0
- pytorch_model-00010-of-00021.bin +3 -0
- pytorch_model-00011-of-00021.bin +3 -0
- pytorch_model-00012-of-00021.bin +3 -0
- pytorch_model-00013-of-00021.bin +3 -0
- pytorch_model-00014-of-00021.bin +3 -0
- pytorch_model-00015-of-00021.bin +3 -0
- pytorch_model-00016-of-00021.bin +3 -0
- pytorch_model-00017-of-00021.bin +3 -0
- pytorch_model-00018-of-00021.bin +3 -0
- pytorch_model-00019-of-00021.bin +3 -0
- pytorch_model-00020-of-00021.bin +3 -0
- pytorch_model-00021-of-00021.bin +3 -0
- pytorch_model.bin.index.json +0 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +48 -0
config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ai21labs/Jamba-v0.1",
|
3 |
+
"architectures": [
|
4 |
+
"JambaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"attn_layer_offset": 4,
|
8 |
+
"attn_layer_period": 8,
|
9 |
+
"auto_map": {
|
10 |
+
"AutoConfig": "ai21labs/Jamba-v0.1--configuration_jamba.JambaConfig",
|
11 |
+
"AutoModel": "ai21labs/Jamba-v0.1--modeling_jamba.JambaModel",
|
12 |
+
"AutoModelForCausalLM": "ai21labs/Jamba-v0.1--modeling_jamba.JambaForCausalLM",
|
13 |
+
"AutoModelForSequenceClassification": "ai21labs/Jamba-v0.1--model.JambaForSequenceClassification"
|
14 |
+
},
|
15 |
+
"bos_token_id": 1,
|
16 |
+
"calc_logits_for_entire_prompt": false,
|
17 |
+
"eos_token_id": 2,
|
18 |
+
"expert_layer_offset": 1,
|
19 |
+
"expert_layer_period": 2,
|
20 |
+
"hidden_act": "silu",
|
21 |
+
"hidden_size": 4096,
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 14336,
|
24 |
+
"mamba_conv_bias": true,
|
25 |
+
"mamba_d_conv": 4,
|
26 |
+
"mamba_d_state": 16,
|
27 |
+
"mamba_dt_rank": 256,
|
28 |
+
"mamba_expand": 2,
|
29 |
+
"mamba_inner_layernorms": true,
|
30 |
+
"mamba_proj_bias": false,
|
31 |
+
"model_type": "jamba",
|
32 |
+
"n_ctx": 262144,
|
33 |
+
"num_attention_heads": 32,
|
34 |
+
"num_experts": 16,
|
35 |
+
"num_experts_per_tok": 2,
|
36 |
+
"num_hidden_layers": 32,
|
37 |
+
"num_key_value_heads": 8,
|
38 |
+
"output_router_logits": false,
|
39 |
+
"pad_token_id": 0,
|
40 |
+
"rms_norm_eps": 1e-06,
|
41 |
+
"router_aux_loss_coef": 0.001,
|
42 |
+
"sliding_window": null,
|
43 |
+
"tie_word_embeddings": false,
|
44 |
+
"torch_dtype": "bfloat16",
|
45 |
+
"transformers_version": "4.40.0.dev0",
|
46 |
+
"use_cache": false,
|
47 |
+
"use_mamba_kernels": true,
|
48 |
+
"vocab_size": 65536
|
49 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"pad_token_id": 0,
|
7 |
+
"transformers_version": "4.40.0.dev0"
|
8 |
+
}
|
pytorch_model-00001-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61117544894b526921f20bb23574bd098ebc9323d948b378ec48e594340b2522
|
3 |
+
size 4951250886
|
pytorch_model-00002-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d5b85999a872c32ac676ff0c9bf3fc75c425b4f3b1beffc7188eeb58776bf10
|
3 |
+
size 4884160124
|
pytorch_model-00003-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a80fac1f62308791207f2d91aafd29763a8412d34f51e912ad4100d2fc5c046b
|
3 |
+
size 4992308496
|
pytorch_model-00004-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef8192c17bfad16dd55fb6fd6cbc1535c505070756c00673da98a418b18dab9d
|
3 |
+
size 4958602752
|
pytorch_model-00005-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c00e0dfce22a7e06f0c8a3aa3511feecb2b290f02847a6ac211183b0101477a
|
3 |
+
size 4975514704
|
pytorch_model-00006-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a64125f3064b25672848161fbc9a76912547457608d65b6a1804c96ea1b82f5b
|
3 |
+
size 4884160124
|
pytorch_model-00007-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07688c7108339b1a7af2007d1e3a148bf053ac09fc10021e8d2a19761c368c59
|
3 |
+
size 4884160188
|
pytorch_model-00008-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b3acf958bc63b6ef7ddd76a1d514320b0ee8e1de2b00c07a035f27602d1873e
|
3 |
+
size 4992308808
|
pytorch_model-00009-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab67d56f9f601cdf22e5eaae2975eb81779384052e4298466119a0d95d1071bd
|
3 |
+
size 4932516474
|
pytorch_model-00010-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf11a69fec0e125569ebbd4514fca69979cad5529404d4f78027e273b44e75d6
|
3 |
+
size 4884160224
|
pytorch_model-00011-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d792c8a0da576758d5354cddd3633473715bf95e62f0708832d62e5ac29526bd
|
3 |
+
size 4884160188
|
pytorch_model-00012-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb762ea4287fcc80fbc658c7828172c42b1b32d11b849ba23b8f1369d259a621
|
3 |
+
size 4884160188
|
pytorch_model-00013-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f53c2a11c78a39998fa22d4864b8258ab12104b53b851d25449bf49bded71296
|
3 |
+
size 4932516474
|
pytorch_model-00014-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f786a6a2079803a928fe449852a1f65066b76e16440df63bf4d6e6dd7902f7b9
|
3 |
+
size 4992308532
|
pytorch_model-00015-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6655b55f311ebd89715715d0672df81f83e2732cd60ec68a2a648c48a7264167
|
3 |
+
size 4884160188
|
pytorch_model-00016-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:113bda65d155000d6e8ec469bb00388cdd3f136f54084451789ac7fa1f24c1e6
|
3 |
+
size 4884160188
|
pytorch_model-00017-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64d697b3882f784632c8ec09164bbb5f6a110e55c712d6cc30a2a79fed4424f7
|
3 |
+
size 4908272822
|
pytorch_model-00018-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01ea3b6d47021a84ce4f70da51db5c1ca57a09e455bb8c801952551a6d21fdbd
|
3 |
+
size 4908404040
|
pytorch_model-00019-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fe480d2b418201551ec14c12f29826e496d567adea9e4affccfe03a64894a7a
|
3 |
+
size 4992308496
|
pytorch_model-00020-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe93e1e8b40d9583142ce5eac58ed7e55f168b479601f2518e5238674eaa7984
|
3 |
+
size 4884160188
|
pytorch_model-00021-of-00021.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:272ed20632179b7664a9abbcb31800ab127c34b3d21bac9918758a9dd9dbd394
|
3 |
+
size 4647327276
|
pytorch_model.bin.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|pad|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|unk|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
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 sha256:02fd6530b8ede0eedd8e509fcab32da7b1dd04c8119f8498c787100f13112713
|
3 |
+
size 1124742
|
tokenizer_config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<|pad|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<|startoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<|endoftext|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<|unk|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"bos_token": "<|startoftext|>",
|
39 |
+
"clean_up_tokenization_spaces": false,
|
40 |
+
"eos_token": "<|endoftext|>",
|
41 |
+
"model_max_length": 1000000000000000019884624838656,
|
42 |
+
"pad_token": "<|pad|>",
|
43 |
+
"spaces_between_special_tokens": false,
|
44 |
+
"tokenizer_class": "LlamaTokenizer",
|
45 |
+
"unk_token": "<|unk|>",
|
46 |
+
"use_default_system_prompt": false,
|
47 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
|
48 |
+
}
|