TechxGenus
commited on
Commit
•
7779544
1
Parent(s):
a495bdf
Upload folder using huggingface_hub
Browse files- config.json +39 -0
- generation_config.json +8 -0
- model.safetensors +3 -0
- special_tokens_map.json +40 -0
- tokenizer.json +0 -0
- tokenizer_config.json +137 -0
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "TechxGenus/CursorCore-Yi-1.5B-LC",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 7,
|
10 |
+
"head_dim": 128,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 2048,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 5504,
|
15 |
+
"max_position_embeddings": 131072,
|
16 |
+
"mlp_bias": false,
|
17 |
+
"model_type": "llama",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"num_key_value_heads": 16,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"pretraining_tp": 1,
|
23 |
+
"quantization_config": {
|
24 |
+
"bits": 4,
|
25 |
+
"group_size": 64,
|
26 |
+
"modules_to_not_convert": null,
|
27 |
+
"quant_method": "awq",
|
28 |
+
"version": "gemm",
|
29 |
+
"zero_point": true
|
30 |
+
},
|
31 |
+
"rms_norm_eps": 1e-05,
|
32 |
+
"rope_scaling": null,
|
33 |
+
"rope_theta": 10000000,
|
34 |
+
"tie_word_embeddings": false,
|
35 |
+
"torch_dtype": "float16",
|
36 |
+
"transformers_version": "4.45.1",
|
37 |
+
"use_cache": false,
|
38 |
+
"vocab_size": 64064
|
39 |
+
}
|
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": 7,
|
6 |
+
"pad_token_id": 0,
|
7 |
+
"transformers_version": "4.45.1"
|
8 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af6f939a75b6287cfbace8399e019a8ea06c695f5858cadd41858ca69d0ed27c
|
3 |
+
size 1179632368
|
special_tokens_map.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|next_start|>",
|
6 |
+
"<|next_end|>",
|
7 |
+
"<|target_start|>",
|
8 |
+
"<|target_end|>",
|
9 |
+
"<|target|>",
|
10 |
+
"<|search_and_replace|>"
|
11 |
+
],
|
12 |
+
"bos_token": {
|
13 |
+
"content": "<|startoftext|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"eos_token": {
|
20 |
+
"content": "<|im_end|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false
|
25 |
+
},
|
26 |
+
"pad_token": {
|
27 |
+
"content": "<|endoftext|>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": false,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
},
|
33 |
+
"unk_token": {
|
34 |
+
"content": "<unk>",
|
35 |
+
"lstrip": false,
|
36 |
+
"normalized": false,
|
37 |
+
"rstrip": false,
|
38 |
+
"single_word": false
|
39 |
+
}
|
40 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,137 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<|startoftext|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "<|endoftext|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"6": {
|
31 |
+
"content": "<|im_start|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"7": {
|
39 |
+
"content": "<|im_end|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"64000": {
|
47 |
+
"content": "<|next_start|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"64001": {
|
55 |
+
"content": "<|next_end|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"64002": {
|
63 |
+
"content": "<|target_start|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"64003": {
|
71 |
+
"content": "<|target_end|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"64004": {
|
79 |
+
"content": "<|target|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"64005": {
|
87 |
+
"content": "<|search_and_replace|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
}
|
94 |
+
},
|
95 |
+
"additional_special_tokens": [
|
96 |
+
"<|im_start|>",
|
97 |
+
"<|im_end|>",
|
98 |
+
"<|next_start|>",
|
99 |
+
"<|next_end|>",
|
100 |
+
"<|target_start|>",
|
101 |
+
"<|target_end|>",
|
102 |
+
"<|target|>",
|
103 |
+
"<|search_and_replace|>"
|
104 |
+
],
|
105 |
+
"bos_token": "<|startoftext|>",
|
106 |
+
"chat_template": [
|
107 |
+
{
|
108 |
+
"name": "default",
|
109 |
+
"template": "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful programming assistant.<|im_end|>\n' }}{% endif %}{% if not loop.first %}{{ '\n' }}{% endif %}{{ '<|im_start|>' + message['role'] }}{% if 'name' in message %}{{ ' name=' + message['name'] }}{% endif %}{{ '\n' + message['content'] + '<|im_end|>' }}{% if loop.last and add_generation_prompt %}{{ '\n<|im_start|>assistant\n<|next_start|>' }}{% endif %}{% endfor %}"
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"name": "assistant-conversation",
|
113 |
+
"template": "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful programming assistant.<|im_end|>\n' }}{% endif %}{% if not loop.first %}{{ '\n' }}{% endif %}{{ '<|im_start|>' + message['role'] }}{% if 'name' in message %}{{ ' name=' + message['name'] }}{% endif %}{{ '\n' + message['content'] + '<|im_end|>' }}{% if loop.last and add_generation_prompt %}{{ '\n<|im_start|>assistant\n<|next_start|>' }}{% endif %}{% endfor %}"
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"name": "prefix_response",
|
117 |
+
"template": "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful programming assistant.<|im_end|>\n' }}{% endif %}{% if not loop.first %}{{ '\n' }}{% endif %}{{ '<|im_start|>' + message['role'] }}{% if 'name' in message %}{{ ' name=' + message['name'] }}{% endif %}{{ '\n' + message['content'] }}{% if not loop.last %}{{ '<|im_end|>' }}{% endif %}{% endfor %}"
|
118 |
+
}
|
119 |
+
],
|
120 |
+
"clean_up_tokenization_spaces": false,
|
121 |
+
"eos_token": "<|im_end|>",
|
122 |
+
"legacy": true,
|
123 |
+
"max_length": 16384,
|
124 |
+
"model_max_length": 16384,
|
125 |
+
"pad_to_multiple_of": null,
|
126 |
+
"pad_token": "<|endoftext|>",
|
127 |
+
"pad_token_type_id": 0,
|
128 |
+
"padding_side": "left",
|
129 |
+
"sp_model_kwargs": {},
|
130 |
+
"spaces_between_special_tokens": false,
|
131 |
+
"stride": 0,
|
132 |
+
"tokenizer_class": "LlamaTokenizer",
|
133 |
+
"truncation_side": "right",
|
134 |
+
"truncation_strategy": "longest_first",
|
135 |
+
"unk_token": "<unk>",
|
136 |
+
"use_default_system_prompt": false
|
137 |
+
}
|