ZhangRC commited on
Commit
1733e53
·
verified ·
1 Parent(s): ce348d1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -3
README.md CHANGED
@@ -1,5 +1,14 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
 
 
 
3
  ---
4
 
5
  # rwkv7-168m-pile
@@ -36,7 +45,7 @@ This is RWKV-7 model under flash-linear attention format.
36
  <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
37
  Install flash-linear-attention before using this model:
38
 
39
- ```
40
  git clone https://github.com/fla-org/flash-linear-attention
41
  cd flash-linear-attention
42
  pip install -e .
@@ -46,7 +55,7 @@ pip install -e .
46
 
47
  <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
48
  You can use this model just as any other HuggingFace models:
49
- ```
50
  from transformers import AutoModelForCausalLM, AutoTokenizer
51
  model = AutoModelForCausalLM.from_pretrained('fla-hub/rwkv7-168m-pile', trust_remote_code=True)
52
  tokenizer = AutoTokenizer.from_pretrained('fla-hub/rwkv7-168m-pile', trust_remote_code=True)
@@ -67,4 +76,4 @@ This model is trained on the Pile with a total of 332 billion tokens.
67
  #### Metrics
68
 
69
  `lambada_openai`: ppl 14.2 acc 45.6%
70
- `piqa`: acc 65.5%
 
1
  ---
2
  license: apache-2.0
3
+ datasets:
4
+ - EleutherAI/the_pile_deduplicated
5
+ language:
6
+ - en
7
+ metrics:
8
+ - accuracy
9
+ base_model:
10
+ - BlinkDL/rwkv-7-pile
11
+ pipeline_tag: text-generation
12
  ---
13
 
14
  # rwkv7-168m-pile
 
45
  <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
  Install flash-linear-attention before using this model:
47
 
48
+ ```bash
49
  git clone https://github.com/fla-org/flash-linear-attention
50
  cd flash-linear-attention
51
  pip install -e .
 
55
 
56
  <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
57
  You can use this model just as any other HuggingFace models:
58
+ ```python
59
  from transformers import AutoModelForCausalLM, AutoTokenizer
60
  model = AutoModelForCausalLM.from_pretrained('fla-hub/rwkv7-168m-pile', trust_remote_code=True)
61
  tokenizer = AutoTokenizer.from_pretrained('fla-hub/rwkv7-168m-pile', trust_remote_code=True)
 
76
  #### Metrics
77
 
78
  `lambada_openai`: ppl 14.2 acc 45.6%
79
+ `piqa`: acc 65.5%