Hugging Face's logo

leonardlin
/
shisa-jamba-v1-checkpoint-2416

Text Generation
Transformers
PyTorch
jamba
conversational
custom_code
Model card Files
xet
 Community
1
leonardlin commited on
Commit
c4f1f2c
·
verified ·
1 Parent(s): 20ed3b1

Upload folder using huggingface_hub

Browse files
Files changed (28) hide show
  1. config.json +49 -0
  2. generation_config.json +8 -0
  3. pytorch_model-00001-of-00021.bin +3 -0
  4. pytorch_model-00002-of-00021.bin +3 -0
  5. pytorch_model-00003-of-00021.bin +3 -0
  6. pytorch_model-00004-of-00021.bin +3 -0
  7. pytorch_model-00005-of-00021.bin +3 -0
  8. pytorch_model-00006-of-00021.bin +3 -0
  9. pytorch_model-00007-of-00021.bin +3 -0
  10. pytorch_model-00008-of-00021.bin +3 -0
  11. pytorch_model-00009-of-00021.bin +3 -0
  12. pytorch_model-00010-of-00021.bin +3 -0
  13. pytorch_model-00011-of-00021.bin +3 -0
  14. pytorch_model-00012-of-00021.bin +3 -0
  15. pytorch_model-00013-of-00021.bin +3 -0
  16. pytorch_model-00014-of-00021.bin +3 -0
  17. pytorch_model-00015-of-00021.bin +3 -0
  18. pytorch_model-00016-of-00021.bin +3 -0
  19. pytorch_model-00017-of-00021.bin +3 -0
  20. pytorch_model-00018-of-00021.bin +3 -0
  21. pytorch_model-00019-of-00021.bin +3 -0
  22. pytorch_model-00020-of-00021.bin +3 -0
  23. pytorch_model-00021-of-00021.bin +3 -0
  24. pytorch_model.bin.index.json +0 -0
  25. special_tokens_map.json +30 -0
  26. tokenizer.json +0 -0
  27. tokenizer.model +3 -0
  28. 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:c992a52c0c4593add0405df0086407230482cc97283ee7859a4b80f3995c1d4e
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 sha256:61e97e899d5a71130daa4f4a6fe2e9394ca2d64e0cfea2a05331e3a6574aab2e
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 sha256:780b578011f46752d50a378c4faa0e82aaf5114d876a5765d7e821039004a94d
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:cc65c1f88196bb2c205984cc620f6a37cd8c389bd1d2aabcf016a260e7f6036b
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:acb2ce0ec4a4f27ff36ea3fca5034bec05313a5ecae6663e32ec3a7ed2b6de2d
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 sha256:3ce27d7a25c27e2573905ab8ecc6c15626626886251ac06c3bebdad51aada671
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:c4227a52d435ba30c7b44922b718d09f9d9eab451cd82cb5023ed36d76ae97ce
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 sha256:5d579f405918dd12f9c29621d284dd95df086f354a42d5b8b5c8379585affffd
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:e8200f013f9e7758f278d7543aded9eee8c45f30553c846b917c8b8ad145676c
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:e8f1106fd2c6d32bfa2dcd88d14788dca271bcb1c02f04753ff5a7fdbee1baad
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 sha256:4217eb3fb0e79a0c277218f7e0159af5bef0b1036b1d265719fa032900904074
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 sha256:72b1faac4147a410e60200c0600dbce1d6e6ae80dc9d2aa618b933f1b132c149
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:ef21496baaf6729cc809e79a60fe9adc2e33085b252fb4af36ed5c745ae2a87a
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 sha256:4d080f942b993c7f58bd9fde334a8d827be78f8ee309b27d40c328f1523e8479
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:ad241f7de682d97ab5b5fc0cab764713401c924195b23167e091f395d23f06fc
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 sha256:6c311b7abece05f37e311a65d02698a4158c1559a0b870bb1953a4337b099e81
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 sha256:45c9de6dd7ee8f022e2cdf6ef32b0cdf4c8c21820a79f80133ddd42e4676f645
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 sha256:358d50dd24c6ef5ddf9f81ce261b770765bb0db8a41e5c673f851afd411006a2
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 sha256:613323a70af4597b103ca7d02879ccdb6b4978f0d240a0c9ae1c831aa9a98dbc
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 sha256:08000ba082c498def96f0e101c281f9e553b9fb1c5e2edeba94880c596467aa6
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 sha256:0d4c1b8aa165657e0689d26b5b24ba70df65e9f7d5c83ee9cebbc6089578858f
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
+ }