lordspline
commited on
Commit
•
5bb1e59
1
Parent(s):
cbbeb31
Upload folder using huggingface_hub
Browse files- added_tokens.json +2 -1
- config.json +4 -4
- generation_config.json +2 -1
- model.safetensors +2 -2
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +21 -1
- tokenizer.json +9 -0
- tokenizer_config.json +11 -3
- trainer_state.json +0 -0
- training_args.bin +3 -0
added_tokens.json
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
{
|
2 |
"<|endoftext|>": 151643,
|
3 |
"<|im_end|>": 151645,
|
4 |
-
"<|im_start|>": 151644
|
|
|
5 |
}
|
|
|
1 |
{
|
2 |
"<|endoftext|>": 151643,
|
3 |
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644,
|
5 |
+
"<|padding|>": 151646
|
6 |
}
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"Qwen2ForCausalLM"
|
5 |
],
|
@@ -20,9 +20,9 @@
|
|
20 |
"rope_theta": 1000000.0,
|
21 |
"sliding_window": 131072,
|
22 |
"tie_word_embeddings": true,
|
23 |
-
"torch_dtype": "
|
24 |
-
"transformers_version": "4.
|
25 |
-
"use_cache":
|
26 |
"use_sliding_window": false,
|
27 |
"vocab_size": 151936
|
28 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "lordspline/qwen-pruned-new",
|
3 |
"architectures": [
|
4 |
"Qwen2ForCausalLM"
|
5 |
],
|
|
|
20 |
"rope_theta": 1000000.0,
|
21 |
"sliding_window": 131072,
|
22 |
"tie_word_embeddings": true,
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.41.1",
|
25 |
+
"use_cache": false,
|
26 |
"use_sliding_window": false,
|
27 |
"vocab_size": 151936
|
28 |
}
|
generation_config.json
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
{
|
2 |
"bos_token_id": 151643,
|
|
|
3 |
"eos_token_id": 151643,
|
4 |
"max_new_tokens": 2048,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
1 |
{
|
2 |
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
"eos_token_id": 151643,
|
5 |
"max_new_tokens": 2048,
|
6 |
+
"transformers_version": "4.41.1"
|
7 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48790dbc82006e9825f5d19e16e232e249c07ad82d9be0fdc9e0a3f0d7328879
|
3 |
+
size 2431151640
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:120ff7a3c6f4030895c34e44045dcf87fe499a5dddb2f2a684ec348fd836d67f
|
3 |
+
size 1969091834
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bba84294f9b1d5b4ded841626d0d4421c07edc29c4c878da271f258915cf2ec
|
3 |
+
size 1064
|
special_tokens_map.json
CHANGED
@@ -3,6 +3,13 @@
|
|
3 |
"<|im_start|>",
|
4 |
"<|im_end|>"
|
5 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
"eos_token": {
|
7 |
"content": "<|endoftext|>",
|
8 |
"lstrip": false,
|
@@ -10,5 +17,18 @@
|
|
10 |
"rstrip": false,
|
11 |
"single_word": false
|
12 |
},
|
13 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
}
|
|
|
3 |
"<|im_start|>",
|
4 |
"<|im_end|>"
|
5 |
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
"eos_token": {
|
14 |
"content": "<|endoftext|>",
|
15 |
"lstrip": false,
|
|
|
17 |
"rstrip": false,
|
18 |
"single_word": false
|
19 |
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<|padding|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"unk_token": {
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
}
|
tokenizer.json
CHANGED
@@ -29,6 +29,15 @@
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
}
|
33 |
],
|
34 |
"normalizer": {
|
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"id": 151646,
|
35 |
+
"content": "<|padding|>",
|
36 |
+
"single_word": false,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"special": true
|
41 |
}
|
42 |
],
|
43 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -24,20 +24,28 @@
|
|
24 |
"rstrip": false,
|
25 |
"single_word": false,
|
26 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
}
|
28 |
},
|
29 |
"additional_special_tokens": [
|
30 |
"<|im_start|>",
|
31 |
"<|im_end|>"
|
32 |
],
|
33 |
-
"bos_token":
|
34 |
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|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": "<|endoftext|>",
|
37 |
"errors": "replace",
|
38 |
"model_max_length": 32768,
|
39 |
-
"pad_token": "<|
|
40 |
"split_special_tokens": false,
|
41 |
"tokenizer_class": "Qwen2Tokenizer",
|
42 |
-
"unk_token":
|
43 |
}
|
|
|
24 |
"rstrip": false,
|
25 |
"single_word": false,
|
26 |
"special": true
|
27 |
+
},
|
28 |
+
"151646": {
|
29 |
+
"content": "<|padding|>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
}
|
36 |
},
|
37 |
"additional_special_tokens": [
|
38 |
"<|im_start|>",
|
39 |
"<|im_end|>"
|
40 |
],
|
41 |
+
"bos_token": "<|endoftext|>",
|
42 |
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
43 |
"clean_up_tokenization_spaces": false,
|
44 |
"eos_token": "<|endoftext|>",
|
45 |
"errors": "replace",
|
46 |
"model_max_length": 32768,
|
47 |
+
"pad_token": "<|padding|>",
|
48 |
"split_special_tokens": false,
|
49 |
"tokenizer_class": "Qwen2Tokenizer",
|
50 |
+
"unk_token": "<|endoftext|>"
|
51 |
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbf86bddd793456f91d989649b997e81a1a3ccfd34bd755f600437c869c3c96a
|
3 |
+
size 5944
|