Upload 10 files
Browse files- README.md +70 -0
- added_tokens.json +5 -0
- config.json +25 -0
- generation_config.json +6 -0
- gitattributes +35 -0
- model.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +68 -0
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-generation
|
6 |
+
base_model: Locutusque/TinyMistral-248M
|
7 |
+
datasets:
|
8 |
+
- OpenAssistant/oasst_top1_2023-08-25
|
9 |
+
widget:
|
10 |
+
- text: |-
|
11 |
+
<|im_start|>user
|
12 |
+
Write the specs of a game about trolls and warriors in a fantasy world.<|im_end|>
|
13 |
+
<|im_start|>assistant
|
14 |
+
The game is an adventure game that takes place on a planet, where players must explore their unique abilities to survive. Players can use different strategies such as collecting items or trading them for gold or silver coins, but they also need to learn how to deal with obstacles and find new ways to escape.<|im_end|>
|
15 |
+
<|im_start|>user
|
16 |
+
Could you tell me something curious about the Earth?<|im_end|>
|
17 |
+
<|im_start|>assistant
|
18 |
+
The planet is a large, rocky world with an atmosphere of 10 billion years old and a surface area around 25 million miles (36 million kilometers) wide.<|im_end|>
|
19 |
+
<|im_start|>user
|
20 |
+
What are some potential applications for quantum computing?<|im_end|>
|
21 |
+
<|im_start|>assistant
|
22 |
+
inference:
|
23 |
+
parameters:
|
24 |
+
max_new_tokens: 64
|
25 |
+
repetition_penalty: 1.18
|
26 |
+
---
|
27 |
+
|
28 |
+
# Locutusque's TinyMistral-248M trained on OpenAssistant TOP-1 Conversation Threads
|
29 |
+
|
30 |
+
- Base model: [Locutusque/TinyMistral-248M](https://huggingface.co/Locutusque/TinyMistral-248M/blob/90b89d18fdf27937dc04ab8a9b543c5af2991c7f/README.md)
|
31 |
+
- Dataset: [OpenAssistant/oasst_top1_2023-08-25](https://huggingface.co/datasets/OpenAssistant/oasst_top1_2023-08-25)
|
32 |
+
|
33 |
+
## Recommended Prompt Format
|
34 |
+
|
35 |
+
```
|
36 |
+
<|im_start|>user
|
37 |
+
{message}<|im_end|>
|
38 |
+
<|im_start|>assistant
|
39 |
+
```
|
40 |
+
|
41 |
+
## How it was trained
|
42 |
+
|
43 |
+
```ipython
|
44 |
+
%pip install autotrain-advanced
|
45 |
+
|
46 |
+
!autotrain setup
|
47 |
+
|
48 |
+
!autotrain llm \
|
49 |
+
--train \
|
50 |
+
--trainer "sft" \
|
51 |
+
--model './TinyMistral-248M/' \
|
52 |
+
--model_max_length 4096 \
|
53 |
+
--block-size 1024 \
|
54 |
+
--project-name 'trained-model' \
|
55 |
+
--data-path "OpenAssistant/oasst_top1_2023-08-25" \
|
56 |
+
--train_split "train" \
|
57 |
+
--valid_split "test" \
|
58 |
+
--text-column "text" \
|
59 |
+
--lr 1e-5 \
|
60 |
+
--train_batch_size 2 \
|
61 |
+
--epochs 5 \
|
62 |
+
--evaluation_strategy "steps" \
|
63 |
+
--save-strategy "steps" \
|
64 |
+
--save-total-limit 2 \
|
65 |
+
--warmup-ratio 0.05 \
|
66 |
+
--weight-decay 0.0 \
|
67 |
+
--gradient-accumulation 8 \
|
68 |
+
--logging-steps 10 \
|
69 |
+
--scheduler "constant"
|
70 |
+
```
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|bos|>": 32000,
|
3 |
+
"<|endoftext|>": 32001,
|
4 |
+
"[PAD]": 32002
|
5 |
+
}
|
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./TinyMistral-248M/",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 1024,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 4096,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
+
"model_type": "mistral",
|
14 |
+
"num_attention_heads": 32,
|
15 |
+
"num_hidden_layers": 12,
|
16 |
+
"num_key_value_heads": 8,
|
17 |
+
"rms_norm_eps": 1e-06,
|
18 |
+
"rope_theta": 10000.0,
|
19 |
+
"sliding_window": 32,
|
20 |
+
"tie_word_embeddings": false,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.34.1",
|
23 |
+
"use_cache": false,
|
24 |
+
"vocab_size": 32003
|
25 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.34.1"
|
6 |
+
}
|
gitattributes
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e6a6b3157a6c75fef55eb31e0d8662bff109779e98e56d652c6e38d0f8c7d28
|
3 |
+
size 992092328
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"32000": {
|
28 |
+
"content": "<|bos|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"32001": {
|
36 |
+
"content": "<|endoftext|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"32002": {
|
44 |
+
"content": "[PAD]",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
}
|
51 |
+
},
|
52 |
+
"additional_special_tokens": [],
|
53 |
+
"bos_token": "<s>",
|
54 |
+
"clean_up_tokenization_spaces": false,
|
55 |
+
"eos_token": "</s>",
|
56 |
+
"legacy": true,
|
57 |
+
"max_length": 1536,
|
58 |
+
"model_max_length": 4096,
|
59 |
+
"pad_token": "[PAD]",
|
60 |
+
"sp_model_kwargs": {},
|
61 |
+
"spaces_between_special_tokens": false,
|
62 |
+
"stride": 0,
|
63 |
+
"tokenizer_class": "LlamaTokenizer",
|
64 |
+
"truncation_side": "right",
|
65 |
+
"truncation_strategy": "longest_first",
|
66 |
+
"unk_token": "<unk>",
|
67 |
+
"use_default_system_prompt": true
|
68 |
+
}
|