Hugging Face's logo

arshiaafshani
/
Arsh-llm-0.7b

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Model card Files
xet
Community
arshiaafshani commited on
Commit
4acdc46
·
verified ·
1 Parent(s): 12bbe22

Training in progress, step 350

Browse files
Files changed (7) hide show
  1. chat_template.jinja +9 -0
  2. config.json +39 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +29 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +98 -0
  7. training_args.bin +3 -0
chat_template.jinja ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {%- for message in messages %}
2
+ {%- if message['role'] == 'system' %}
3
+ {{ '<|system|>' + ' ' + message['content'].strip() }}
4
+ {%- elif message['role'] == 'user' %}
5
+ {{ '<|instruction|>' + ' ' + message['content'].strip() }}
6
+ {%- elif message['role'] == 'assistant' %}
7
+ {{ '<|response|>' + ' ' + message['content'].strip() }}
8
+ {%- endif %}
9
+ {%- endfor %}
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attention_implementation": "flash_attention_2",
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 2,
10
+ "head_dim": 68,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 816,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 9856,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 26,
20
+ "num_key_value_heads": 6,
21
+ "pad_token_id": 1,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_scaling": {
25
+ "factor": 2.0,
26
+ "rope_type": "dynamic",
27
+ "type": "dynamic"
28
+ },
29
+ "rope_theta": 10000.0,
30
+ "rotary_embedding_base": 10000,
31
+ "tie_word_embeddings": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.52.4",
34
+ "use_cache": true,
35
+ "use_flash_attention": true,
36
+ "use_memory_efficient_attention": true,
37
+ "use_scaled_dot_product": true,
38
+ "vocab_size": 32768
39
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1928d43c6bf9b9c0d3e51a10e6a7c5b4c1d7679420b2d7bbef61e0c79c30161d
3
+ size 2824160232
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|system|>",
4
+ "<|instruction|>",
5
+ "<|response|>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<sos>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": "<|endoftext|>",
22
+ "unk_token": {
23
+ "content": "<unk>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<sos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<|endoftext|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<|system|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<|user|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<|assistant|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<|instruction|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "<|response|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "9": {
76
+ "content": "<|separator|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ }
83
+ },
84
+ "additional_special_tokens": [
85
+ "<|system|>",
86
+ "<|instruction|>",
87
+ "<|response|>"
88
+ ],
89
+ "bos_token": "<sos>",
90
+ "clean_up_tokenization_spaces": true,
91
+ "eos_token": "<|endoftext|>",
92
+ "extra_special_tokens": {},
93
+ "model_max_length": 1000000000000000019884624838656,
94
+ "pad_token": "<|endoftext|>",
95
+ "tokenizer_class": "PreTrainedTokenizer",
96
+ "trim_offsets": true,
97
+ "unk_token": "<unk>"
98
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee09149868612de836e41b64f2d7d096f1a74adac2dab8412da8c402541a8b4
3
+ size 5240