Yazeed Kamel commited on
Commit
d5ad0de
·
verified ·
1 Parent(s): 10e7d10

Upload 6 files

Browse files
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "inceptionai/jais-family-590m-chat",
3
+ "activation_function": "swiglu",
4
+ "alibi_scaling": null,
5
+ "architectures": [
6
+ "JAISLMHeadModel"
7
+ ],
8
+ "attn_pdrop": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "inceptionai/jais-family-590m-chat--configuration_jais.JAISConfig",
11
+ "AutoModel": "inceptionai/jais-family-590m-chat--modeling_jais.JAISModel",
12
+ "AutoModelForCausalLM": "inceptionai/jais-family-590m-chat--modeling_jais.JAISLMHeadModel",
13
+ "AutoModelForQuestionAnswering": "inceptionai/jais-family-590m-chat--modeling_jais.JAISForQuestionAnswering",
14
+ "AutoModelForSequenceClassification": "inceptionai/jais-family-590m-chat--modeling_jais.JAISForSequenceClassification",
15
+ "AutoModelForTokenClassification": "inceptionai/jais-family-590m-chat--modeling_jais.JAISForTokenClassification"
16
+ },
17
+ "bos_token_id": 0,
18
+ "embd_pdrop": 0.0,
19
+ "eos_token_id": 0,
20
+ "initializer_range": 0.02,
21
+ "layer_norm_epsilon": 1e-05,
22
+ "model_type": "jais",
23
+ "mup_embeddings_scale": 9.1705785388303,
24
+ "mup_output_alpha": 1.09518349815769,
25
+ "mup_scale_qk_dot_by_d": true,
26
+ "mup_width_scale": 0.16666666666666666,
27
+ "n_embd": 1536,
28
+ "n_head": 12,
29
+ "n_inner": 4096,
30
+ "n_layer": 18,
31
+ "n_positions": 2048,
32
+ "pad_token_id": 0,
33
+ "position_embedding_type": "alibi",
34
+ "reorder_and_upcast_attn": false,
35
+ "resid_pdrop": 0.0,
36
+ "rotary_dim": null,
37
+ "scale_attn_by_inverse_layer_idx": false,
38
+ "scale_attn_weights": true,
39
+ "tie_word_embeddings": false,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.47.1",
42
+ "use_cache": true,
43
+ "vocab_size": 84992
44
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.47.1"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16b1c002ad73b4af9ed8495681220ac522aedb1d84c41e9cfb195cafd315f033
3
+ size 3084494990
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
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": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
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_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ }
11
+ },
12
+ "bos_token": "<|endoftext|>",
13
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = '### Instruction: ' + messages[0]['content'] + '\nComplete the conversation below between [|Human|] and [|AI|]:\n### Input:'%}{% else %}{% set loop_messages = messages %}{% set system_message = '### Instruction: Your name is \\'Jais\\', and you are named after Jebel Jais, the highest mountain in UAE. You were made by \\'Inception\\' in the UAE. You are a helpful, respectful, and honest assistant. Always answer as helpfully as possible, while being safe. Complete the conversation below between [|Human|] and [|AI|]:\n### Input:' %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = system_message %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{% if loop.index0 == 0 %}{{ content + ' [|Human|] ' + message['content'] }}{% else %}{{ '\n[|Human|] ' + content.strip() }}{% endif %}{% elif message['role'] == 'assistant' %}{{ '\n[|AI|] ' + content.strip() }}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %} {{'\n[|AI|]\n### Response:'}}{% endif %}",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 2048,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "PreTrainedTokenizerFast",
20
+ "unk_token": "<|endoftext|>"
21
+ }