Upload folder using huggingface_hub
Browse files- README.md +6 -6
- config.json +5 -6
- mergekit_config.yml +3 -3
- model-00001-of-00001.safetensors +1 -1
- special_tokens_map.json +8 -1
- tokenizer_config.json +2 -2
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
2 |
base_model:
|
3 |
-
- vilm/Quyen-SE-v0.1
|
4 |
- Qwen/Qwen1.5-0.5B
|
|
|
5 |
library_name: transformers
|
6 |
tags:
|
7 |
- mergekit
|
@@ -15,12 +15,12 @@ This is a merge of pre-trained language models created using [mergekit](https://
|
|
15 |
## Merge Details
|
16 |
### Merge Method
|
17 |
|
18 |
-
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [
|
19 |
|
20 |
### Models Merged
|
21 |
|
22 |
The following models were included in the merge:
|
23 |
-
* [
|
24 |
|
25 |
### Configuration
|
26 |
|
@@ -28,14 +28,14 @@ The following YAML configuration was used to produce this model:
|
|
28 |
|
29 |
```yaml
|
30 |
models:
|
31 |
-
- model: Qwen/Qwen1.5-0.5B
|
32 |
-
# no parameters necessary for base model
|
33 |
- model: vilm/Quyen-SE-v0.1
|
|
|
|
|
34 |
parameters:
|
35 |
density: 0.5
|
36 |
weight: 0.5
|
37 |
merge_method: ties
|
38 |
-
base_model:
|
39 |
parameters:
|
40 |
normalize: true
|
41 |
dtype: float16
|
|
|
1 |
---
|
2 |
base_model:
|
|
|
3 |
- Qwen/Qwen1.5-0.5B
|
4 |
+
- vilm/Quyen-SE-v0.1
|
5 |
library_name: transformers
|
6 |
tags:
|
7 |
- mergekit
|
|
|
15 |
## Merge Details
|
16 |
### Merge Method
|
17 |
|
18 |
+
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [vilm/Quyen-SE-v0.1](https://huggingface.co/vilm/Quyen-SE-v0.1) as a base.
|
19 |
|
20 |
### Models Merged
|
21 |
|
22 |
The following models were included in the merge:
|
23 |
+
* [Qwen/Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B)
|
24 |
|
25 |
### Configuration
|
26 |
|
|
|
28 |
|
29 |
```yaml
|
30 |
models:
|
|
|
|
|
31 |
- model: vilm/Quyen-SE-v0.1
|
32 |
+
# no parameters necessary for base model
|
33 |
+
- model: Qwen/Qwen1.5-0.5B
|
34 |
parameters:
|
35 |
density: 0.5
|
36 |
weight: 0.5
|
37 |
merge_method: ties
|
38 |
+
base_model: vilm/Quyen-SE-v0.1
|
39 |
parameters:
|
40 |
normalize: true
|
41 |
dtype: float16
|
config.json
CHANGED
@@ -1,11 +1,10 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"Qwen2ForCausalLM"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
7 |
-
"
|
8 |
-
"eos_token_id": 151643,
|
9 |
"hidden_act": "silu",
|
10 |
"hidden_size": 1024,
|
11 |
"initializer_range": 0.02,
|
@@ -18,11 +17,11 @@
|
|
18 |
"num_key_value_heads": 16,
|
19 |
"rms_norm_eps": 1e-06,
|
20 |
"rope_theta": 1000000.0,
|
21 |
-
"sliding_window":
|
22 |
-
"tie_word_embeddings":
|
23 |
"torch_dtype": "float16",
|
24 |
"transformers_version": "4.38.2",
|
25 |
-
"use_cache":
|
26 |
"use_sliding_window": false,
|
27 |
"vocab_size": 151936
|
28 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "vilm/Quyen-SE-v0.1",
|
3 |
"architectures": [
|
4 |
"Qwen2ForCausalLM"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
7 |
+
"eos_token_id": 151645,
|
|
|
8 |
"hidden_act": "silu",
|
9 |
"hidden_size": 1024,
|
10 |
"initializer_range": 0.02,
|
|
|
17 |
"num_key_value_heads": 16,
|
18 |
"rms_norm_eps": 1e-06,
|
19 |
"rope_theta": 1000000.0,
|
20 |
+
"sliding_window": 4096,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "float16",
|
23 |
"transformers_version": "4.38.2",
|
24 |
+
"use_cache": false,
|
25 |
"use_sliding_window": false,
|
26 |
"vocab_size": 151936
|
27 |
}
|
mergekit_config.yml
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
models:
|
2 |
-
- model: Qwen/Qwen1.5-0.5B
|
3 |
-
# no parameters necessary for base model
|
4 |
- model: vilm/Quyen-SE-v0.1
|
|
|
|
|
5 |
parameters:
|
6 |
density: 0.5
|
7 |
weight: 0.5
|
8 |
merge_method: ties
|
9 |
-
base_model:
|
10 |
parameters:
|
11 |
normalize: true
|
12 |
dtype: float16
|
|
|
1 |
models:
|
|
|
|
|
2 |
- model: vilm/Quyen-SE-v0.1
|
3 |
+
# no parameters necessary for base model
|
4 |
+
- model: Qwen/Qwen1.5-0.5B
|
5 |
parameters:
|
6 |
density: 0.5
|
7 |
weight: 0.5
|
8 |
merge_method: ties
|
9 |
+
base_model: vilm/Quyen-SE-v0.1
|
10 |
parameters:
|
11 |
normalize: true
|
12 |
dtype: float16
|
model-00001-of-00001.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1239173056
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ad093d3b407f5b332793839693c351df5a6655019ea85d3db221c3233a005c4
|
3 |
size 1239173056
|
special_tokens_map.json
CHANGED
@@ -3,8 +3,15 @@
|
|
3 |
"<|im_start|>",
|
4 |
"<|im_end|>"
|
5 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
"eos_token": {
|
7 |
-
"content": "<|
|
8 |
"lstrip": false,
|
9 |
"normalized": false,
|
10 |
"rstrip": false,
|
|
|
3 |
"<|im_start|>",
|
4 |
"<|im_end|>"
|
5 |
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<|im_end|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
"eos_token": {
|
14 |
+
"content": "<|im_end|>",
|
15 |
"lstrip": false,
|
16 |
"normalized": false,
|
17 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
@@ -30,10 +30,10 @@
|
|
30 |
"<|im_start|>",
|
31 |
"<|im_end|>"
|
32 |
],
|
33 |
-
"bos_token":
|
34 |
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
35 |
"clean_up_tokenization_spaces": false,
|
36 |
-
"eos_token": "<|
|
37 |
"errors": "replace",
|
38 |
"model_max_length": 32768,
|
39 |
"pad_token": "<|endoftext|>",
|
|
|
30 |
"<|im_start|>",
|
31 |
"<|im_end|>"
|
32 |
],
|
33 |
+
"bos_token": "<|im_end|>",
|
34 |
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
35 |
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|im_end|>",
|
37 |
"errors": "replace",
|
38 |
"model_max_length": 32768,
|
39 |
"pad_token": "<|endoftext|>",
|