gargamit commited on
Commit
43660c7
1 Parent(s): ba3e2e8

updated headers

Browse files
Files changed (2) hide show
  1. README.md +3 -3
  2. config.json +1 -0
README.md CHANGED
@@ -3,14 +3,14 @@ license: mit
3
  license_link: https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/LICENSE
4
 
5
  language:
6
- - multilingual
7
  pipeline_tag: text-generation
8
  tags:
9
  - nlp
10
  - code
11
  inference:
12
  parameters:
13
- temperature: 0.7
14
  widget:
15
  - messages:
16
  - role: user
@@ -81,7 +81,7 @@ The table below highlights improvements on instruction following, structure outp
81
  | MMLU | 68.8 | 70.9 |
82
  | **Average** | **21.9** | **36.7** |
83
 
84
- Notes: if users would like to check out the previous version, use the git commit id **ff07dc01615f8113924aed013115ab2abd32115b**.
85
 
86
  ## How to Use
87
 
 
3
  license_link: https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/LICENSE
4
 
5
  language:
6
+ - en
7
  pipeline_tag: text-generation
8
  tags:
9
  - nlp
10
  - code
11
  inference:
12
  parameters:
13
+ temperature: 0.0
14
  widget:
15
  - messages:
16
  - role: user
 
81
  | MMLU | 68.8 | 70.9 |
82
  | **Average** | **21.9** | **36.7** |
83
 
84
+ Notes: if users would like to check out the previous version, use the git commit id **ff07dc01615f8113924aed013115ab2abd32115b**. For the model conversion, e.g. GGUF and other formats, we invite the community to experiment with various approaches and share your valuable feedback. Let's innovate together!
85
 
86
  ## How to Use
87
 
config.json CHANGED
@@ -31,5 +31,6 @@
31
  "torch_dtype": "bfloat16",
32
  "transformers_version": "4.40.2",
33
  "use_cache": true,
 
34
  "vocab_size": 32064
35
  }
 
31
  "torch_dtype": "bfloat16",
32
  "transformers_version": "4.40.2",
33
  "use_cache": true,
34
+ "attention_bias": false,
35
  "vocab_size": 32064
36
  }