Added weights
Browse files- README.md +49 -0
- added_tokens.json +4 -0
- config.json +29 -0
- job_new.json +0 -0
- measurement.json +0 -0
- output.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.model +3 -0
- tokenizer_config.json +59 -0
README.md
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
datasets:
|
3 |
+
- teknium/OpenHermes-2.5
|
4 |
+
---
|
5 |
+
This is an EXL2 quantized model in 4bpw of [feeltheAGI/yi-super-9B](https://huggingface.co/feeltheAGI/yi-super-9B) using the default calibration dataset.
|
6 |
+
|
7 |
+
# Original Model card:
|
8 |
+
|
9 |
+
![1702046172090179.jpg](https://cdn-uploads.huggingface.co/production/uploads/65d1f383351255ba48a4f831/EdV6mhHGCv5w2BIC58vCm.jpeg)
|
10 |
+
|
11 |
+
YI-9B-Super
|
12 |
+
|
13 |
+
YI-9B-Super is an YI-9B model that has been further fine-tuned with OpenHermes-2.5 dataset.
|
14 |
+
|
15 |
+
|
16 |
+
Results on some benchmarks :
|
17 |
+
|
18 |
+
| Tasks |Version| Filter |n-shot| Metric | Value | |Stderr|
|
19 |
+
|---------------------------------------|-------|----------------|------|-----------|------:|---|-----:|
|
20 |
+
|truthfulqa |N/A |none | 0|rouge1_max |47.1011|± |0.8016|
|
21 |
+
|hellaswag | 1|none |None |acc | 0.5758|± |0.0049|
|
22 |
+
| | |none |None |acc_norm | 0.7639|± |0.0042|
|
23 |
+
|gsm8k_cot | 3|strict-match |8 |exact_match| 0.5262|± |0.0138|
|
24 |
+
| | |flexible-extract|8 |exact_match| 0.6027|± |0.0135|
|
25 |
+
|gsm8k | 3|strict-match |5 |exact_match| 0.6073|± |0.0135|
|
26 |
+
| | |flexible-extract|5 |exact_match| 0.6126|± |0.0134|
|
27 |
+
|
28 |
+
|
29 |
+
|
30 |
+
| Groups |Version|Filter|n-shot| Metric | Value | |Stderr|
|
31 |
+
|------------------|-------|------|------|-----------|------:|---|-----:|
|
32 |
+
|truthfulqa |N/A |none | 0|rouge1_max |47.1011|± |0.8016|
|
33 |
+
| | |none | 0|bleu_max |21.9476|± |0.7162|
|
34 |
+
| | |none | 0|rouge2_acc | 0.3293|± |0.0165|
|
35 |
+
| | |none | 0|bleu_acc | 0.3635|± |0.0168|
|
36 |
+
| | |none | 0|rouge1_acc | 0.3892|± |0.0171|
|
37 |
+
| | |none | 0|rougeL_acc | 0.3782|± |0.0170|
|
38 |
+
| | |none | 0|bleu_diff |-2.3953|± |0.6292|
|
39 |
+
| | |none | 0|rouge2_diff|-4.6929|± |0.9130|
|
40 |
+
| | |none | 0|rougeL_diff|-4.2677|± |0.8034|
|
41 |
+
| | |none | 0|acc | 0.4040|± |0.0113|
|
42 |
+
| | |none | 0|rouge1_diff|-3.8975|± |0.7966|
|
43 |
+
| | |none | 0|rougeL_max |43.7954|± |0.8145|
|
44 |
+
| | |none | 0|rouge2_max |32.3573|± |0.9094|
|
45 |
+
|mmlu |N/A |none | 0|acc | 0.6726|± |0.0037|
|
46 |
+
| - humanities |N/A |none |None |acc | 0.6043|± |0.0067|
|
47 |
+
| - other |N/A |none |None |acc | 0.7306|± |0.0077|
|
48 |
+
| - social_sciences|N/A |none |None |acc | 0.7741|± |0.0074|
|
49 |
+
| - stem |N/A |none |None |acc | 0.6181|± |0.0083|
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 64001,
|
3 |
+
"<s>": 64000
|
4 |
+
}
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "01-ai/Yi-9B",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 64000,
|
9 |
+
"eos_token_id": 64001,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 11008,
|
14 |
+
"max_position_embeddings": 8192,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 48,
|
18 |
+
"num_key_value_heads": 4,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-06,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 10000,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.38.2",
|
27 |
+
"use_cache": false,
|
28 |
+
"vocab_size": 64002
|
29 |
+
}
|
job_new.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
measurement.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
output.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cff2ce34da0f3acfb45839535691a72d77ad784278e882724eeb14d709ef9fb
|
3 |
+
size 4885584736
|
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": "<unk>",
|
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.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
|
3 |
+
size 1033105
|
tokenizer_config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
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 |
+
"64000": {
|
31 |
+
"content": "<s>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"64001": {
|
39 |
+
"content": "</s>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"bos_token": "<s>",
|
48 |
+
"clean_up_tokenization_spaces": false,
|
49 |
+
"eos_token": "</s>",
|
50 |
+
"legacy": true,
|
51 |
+
"model_max_length": 4096,
|
52 |
+
"pad_token": "<unk>",
|
53 |
+
"sp_model_kwargs": {},
|
54 |
+
"spaces_between_special_tokens": false,
|
55 |
+
"tokenizer_class": "LlamaTokenizer",
|
56 |
+
"unk_token": "<unk>",
|
57 |
+
"use_default_system_prompt": false,
|
58 |
+
"use_fast": true
|
59 |
+
}
|