Upload 28 files
Browse files- config.json +49 -0
- generation_config.json +7 -0
- model-00001-of-00021.safetensors +3 -0
- model-00002-of-00021.safetensors +3 -0
- model-00003-of-00021.safetensors +3 -0
- model-00004-of-00021.safetensors +3 -0
- model-00005-of-00021.safetensors +3 -0
- model-00006-of-00021.safetensors +3 -0
- model-00007-of-00021.safetensors +3 -0
- model-00008-of-00021.safetensors +3 -0
- model-00009-of-00021.safetensors +3 -0
- model-00010-of-00021.safetensors +3 -0
- model-00011-of-00021.safetensors +3 -0
- model-00012-of-00021.safetensors +3 -0
- model-00013-of-00021.safetensors +3 -0
- model-00014-of-00021.safetensors +3 -0
- model-00015-of-00021.safetensors +3 -0
- model-00016-of-00021.safetensors +3 -0
- model-00017-of-00021.safetensors +3 -0
- model-00018-of-00021.safetensors +3 -0
- model-00019-of-00021.safetensors +3 -0
- model-00020-of-00021.safetensors +3 -0
- model-00021-of-00021.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +47 -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": "float16",
|
45 |
+
"transformers_version": "4.39.2",
|
46 |
+
"use_cache": true,
|
47 |
+
"use_mamba_kernels": true,
|
48 |
+
"vocab_size": 65536
|
49 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.39.2"
|
7 |
+
}
|
model-00001-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:321523a2641bf08581335071a9e0fa448c5f4b2ca77dadec0e5cee8f6ec5af03
|
3 |
+
size 4951761080
|
model-00002-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffca6771fc4ceeaa6d18dd0ff52c105907271eb001cf4e6c9ec24ce060f3492f
|
3 |
+
size 4884669232
|
model-00003-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcd5f21d5b6e230c16640fc80c7d0aff21cdc4155f121da06134770b8f93de2f
|
3 |
+
size 4992556712
|
model-00004-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5b61812da79aadca39fbbdc07361dcce35a3baa193b76763e6f040620fa6d6f
|
3 |
+
size 4958853128
|
model-00005-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da9acafc14dde0a0e41a8e8939d897d3674d2d1045e3965aae4b2e4407d65560
|
3 |
+
size 4975763392
|
model-00006-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d5516379b2fa507399b33c8fc242504078bbd38884c1f948a6ecce2f0d61fa7
|
3 |
+
size 4884669224
|
model-00007-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffefc2593d4dab8c7fb9d562b799ea6f9957ab91588685a43f98213aa60f73d9
|
3 |
+
size 4884669208
|
model-00008-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1271db4d71b86f3ffb6b189fc9f0e9ebc67385e8d598dcdf79a17bc2235d3a4c
|
3 |
+
size 4992556768
|
model-00009-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f7240f5758eccb16235708b21d189e3154db693f24f60e4865d66a08f17a53b
|
3 |
+
size 4932506760
|
model-00010-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fecad5527545a01dbd9138f632d249797078ae74a055665bbca3ae333dcfde72
|
3 |
+
size 4884669272
|
model-00011-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83878315b353ab552ce2162435dd5f95671f9828a39e86d9afeaf97485aace29
|
3 |
+
size 4884669304
|
model-00012-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26d245b4c38644f0019159c40ded3ee8481ddc004cbc5fe0b01ae08ea64055de
|
3 |
+
size 4884669304
|
model-00013-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f034c6a48f5f0597cb65941bb1b8ce2ac32efca291eea00e60f006244cb29ab
|
3 |
+
size 4932506760
|
model-00014-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08fbabef85c417c2eaffeb9902ccd39fa3e37c033096e7af5cb41bc6d10e2493
|
3 |
+
size 4992556728
|
model-00015-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b88726c78a3e7a70138a38e35821e418faa6471f4a0a5165a40f35ab02bf6ab
|
3 |
+
size 4884669296
|
model-00016-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a4a9463be1d9b4cb485dd5bf2918ecb404685faff4d765977a6f2d8b555c675
|
3 |
+
size 4884669304
|
model-00017-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1e3e185c1d0f94c05f99da7a49e6429205057a1bbf96d1165612a27bdb9daeb
|
3 |
+
size 4908522432
|
model-00018-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7511d9443819ba859118f0d8865d642c831e3e90c7086fdbc6b3eacadb93e67c
|
3 |
+
size 4908653584
|
model-00019-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb4093457bc3e76711c9a0d734860d7f354e699d62b51c18d4a21dc057de7d39
|
3 |
+
size 4992556768
|
model-00020-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c895f1b73d44134c66a5848f99d3364eb157738a7655f355885cf05d7c9ca8fd
|
3 |
+
size 4884669304
|
model-00021-of-00021.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35fee5c3585de5f986aa7c49037926d5eea5389f026ae3659b6b393e30b24c4b
|
3 |
+
size 4647318216
|
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 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
}
|