Upload folder using huggingface_hub
Browse files- README.md +35 -0
- config.json +28 -0
- generation_config.json +11 -0
- model.safetensors +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +42 -0
README.md
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
widget:
|
3 |
+
- text: <|user|>tell me about india<|assistant|>
|
4 |
+
example_title: English-1
|
5 |
+
- text: <|user|>मुझे भारत के बारे में बताओ?<|assistant|>
|
6 |
+
example_title: Hindi-1
|
7 |
+
- text: <|user|>আমাকে ভারত সম্পর্কে বলুন<|assistant|>
|
8 |
+
example_title: Bangla-1
|
9 |
+
- text: <|user|>இந்தியாவைப் பற்றி சொல்லுங்கள்<|assistant|>
|
10 |
+
example_title: Tamil-1
|
11 |
+
- text: <|user|>મને ભારત વિશે કહો<|assistant|>
|
12 |
+
example_title: Gujrati-1
|
13 |
+
- text: <|user|>ಭಾರತದ ಬಗ್ಗೆ ಹೇಳಿ<|assistant|>
|
14 |
+
example_title: Kannada-1
|
15 |
+
- text: <|user|>مجھے انڈیا کے بارے میں بتائیں<|assistant|>
|
16 |
+
example_title: Urdu-1
|
17 |
+
- text: <|user|>What is the capital of India?<|assistant|>
|
18 |
+
example_title: English
|
19 |
+
- text: <|user|>भारत की राजधानी क्या है?<|assistant|>
|
20 |
+
example_title: Hindi
|
21 |
+
- text: <|user|>ভারতের রাজধানী কি?<|assistant|>
|
22 |
+
example_title: Bangla
|
23 |
+
- text: <|user|>இந்தியாவின் தலைநகரம் என்ன<|assistant|>
|
24 |
+
example_title: Tamil
|
25 |
+
- text: <|user|>ભારતની રાજધાની શું છે<|assistant|>
|
26 |
+
example_title: Gujrati
|
27 |
+
- text: <|user|>ಭಾರತದ ರಾಜಧಾನಿ ಯಾವುದು<|assistant|>
|
28 |
+
example_title: Kannada
|
29 |
+
- text: <|user|>ہندوستان کا دارالحکومت کیا ہے؟<|assistant|>
|
30 |
+
example_title: Urdu
|
31 |
+
pipeline_tag: text-generation
|
32 |
+
inference:
|
33 |
+
parameters:
|
34 |
+
max_new_tokens: 200
|
35 |
+
---
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 2048,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 5632,
|
14 |
+
"max_position_embeddings": 2048,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 22,
|
18 |
+
"num_key_value_heads": 4,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rms_norm_eps": 1e-05,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float16",
|
25 |
+
"transformers_version": "4.36.2",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 69632
|
28 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 1,
|
3 |
+
"eos_token_id": 2,
|
4 |
+
"max_length": 2048,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.36.2",
|
7 |
+
"do_sample": "True",
|
8 |
+
"top_k": 5,
|
9 |
+
"temperature": 0.3,
|
10 |
+
"max_new_tokens": 512
|
11 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:739d670dc3c678e05562556940b02eb18397461f97b9ea9fdc6bc61035c4737b
|
3 |
+
size 2508404920
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% 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 = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": false,
|
35 |
+
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": null,
|
37 |
+
"padding_side": "right",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|