Text Generation
Transformers
Safetensors
English
llama
conversational
Eval Results
Inference Endpoints
text-generation-inference
Felladrin commited on
Commit
e7f5066
β€’
1 Parent(s): c24ebad

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +55 -98
README.md CHANGED
@@ -12,102 +12,59 @@ datasets:
12
  - databricks/databricks-dolly-15k
13
  - THUDM/webglm-qa
14
  widget:
15
- - text: '<|im_start|>system
16
-
17
- You are a helpful assistant, who answers with empathy.<|im_end|>
18
-
19
- <|im_start|>user
20
-
21
- Got a question for you!<|im_end|>
22
-
23
- <|im_start|>assistant
24
-
25
- Sure! What''s it?<|im_end|>
26
-
27
- <|im_start|>user
28
-
29
- Why do you love cats so much!? 🐈<|im_end|>
30
-
31
- <|im_start|>assistant'
32
- - text: '<|im_start|>system
33
-
34
- You are a helpful assistant who answers user''s questions with empathy.<|im_end|>
35
-
36
- <|im_start|>user
37
-
38
- Who is Mona Lisa?<|im_end|>
39
-
40
- <|im_start|>assistant'
41
- - text: '<|im_start|>system
42
-
43
- You are a helpful assistant who provides concise responses.<|im_end|>
44
-
45
- <|im_start|>user
46
-
47
- Heya!<|im_end|>
48
-
49
- <|im_start|>assistant
50
-
51
- Hi! How may I help you today?<|im_end|>
52
-
53
- <|im_start|>user
54
-
55
- I need to build a simple website. Where should I start learning about web development?<|im_end|>
56
-
57
- <|im_start|>assistant'
58
- - text: '<|im_start|>user
59
-
60
- Invited some friends to come home today. Give me some ideas for games to play
61
- with them!<|im_end|>
62
-
63
- <|im_start|>assistant'
64
- - text: '<|im_start|>system
65
-
66
- You are a helpful assistant who answers user''s questions with details and curiosity.<|im_end|>
67
-
68
- <|im_start|>user
69
-
70
- What are some potential applications for quantum computing?<|im_end|>
71
-
72
- <|im_start|>assistant'
73
- - text: '<|im_start|>system
74
-
75
- You are a helpful assistant who gives creative responses.<|im_end|>
76
-
77
- <|im_start|>user
78
-
79
- Write the specs of a game about mages in a fantasy world.<|im_end|>
80
-
81
- <|im_start|>assistant'
82
- - text: '<|im_start|>system
83
-
84
- You are a helpful assistant who answers user''s questions with details.<|im_end|>
85
-
86
- <|im_start|>user
87
-
88
- Tell me about the pros and cons of social media.<|im_end|>
89
-
90
- <|im_start|>assistant'
91
- - text: '<|im_start|>system
92
-
93
- You are a helpful assistant who answers user''s questions with confidence.<|im_end|>
94
-
95
- <|im_start|>user
96
-
97
- What is a dog?<|im_end|>
98
-
99
- <|im_start|>assistant
100
-
101
- A dog is a four-legged, domesticated animal that is a member of the class Mammalia,
102
- which includes all mammals. Dogs are known for their loyalty, playfulness, and
103
- ability to be trained for various tasks. They are also used for hunting, herding,
104
- and as service animals.<|im_end|>
105
-
106
- <|im_start|>user
107
-
108
- What is the color of an apple?<|im_end|>
109
-
110
- <|im_start|>assistant'
111
  inference:
112
  parameters:
113
  max_new_tokens: 250
@@ -285,7 +242,8 @@ output = generate(
285
  print(output[0]["generated_text"])
286
  ```
287
 
288
- # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
 
289
  Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Felladrin__Llama-160M-Chat-v1)
290
 
291
  | Metric |Value|
@@ -297,4 +255,3 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
297
  |TruthfulQA (0-shot) |44.16|
298
  |Winogrande (5-shot) |51.30|
299
  |GSM8k (5-shot) | 0.00|
300
-
 
12
  - databricks/databricks-dolly-15k
13
  - THUDM/webglm-qa
14
  widget:
15
+ - messages:
16
+ - role: system
17
+ content: You are a helpful assistant, who answers with empathy.
18
+ - role: user
19
+ content: Got a question for you!
20
+ - role: assistant
21
+ content: "Sure! What's it?"
22
+ - role: user
23
+ content: Why do you love cats so much!? 🐈
24
+ - messages:
25
+ - role: system
26
+ content: "You are a helpful assistant who answers user's questions with empathy."
27
+ - role: user
28
+ content: Who is Mona Lisa?
29
+ - messages:
30
+ - role: system
31
+ content: You are a helpful assistant who provides concise responses.
32
+ - role: user
33
+ content: Heya!
34
+ - role: assistant
35
+ content: Hi! How may I help you today?
36
+ - role: user
37
+ content: I need to build a simple website. Where should I start learning about web development?
38
+ - messages:
39
+ - role: user
40
+ content: Invited some friends to come home today. Give me some ideas for games to play with them!
41
+ - messages:
42
+ - role: system
43
+ content: "You are a helpful assistant who answers user's questions with details and curiosity."
44
+ - role: user
45
+ content: What are some potential applications for quantum computing?
46
+ - messages:
47
+ - role: system
48
+ content: You are a helpful assistant who gives creative responses.
49
+ - role: user
50
+ content: Write the specs of a game about mages in a fantasy world.
51
+ - messages:
52
+ - role: system
53
+ content: "You are a helpful assistant who answers user's questions with details."
54
+ - role: user
55
+ content: Tell me about the pros and cons of social media.
56
+ - messages:
57
+ - role: system
58
+ content: "You are a helpful assistant who answers user's questions with confidence."
59
+ - role: user
60
+ content: What is a dog?
61
+ - role: assistant
62
+ content: 'A dog is a four-legged, domesticated animal that is a member of the class Mammalia,
63
+ which includes all mammals. Dogs are known for their loyalty, playfulness, and
64
+ ability to be trained for various tasks. They are also used for hunting, herding,
65
+ and as service animals.'
66
+ - role: user
67
+ content: What is the color of an apple?
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  inference:
69
  parameters:
70
  max_new_tokens: 250
 
242
  print(output[0]["generated_text"])
243
  ```
244
 
245
+ ## [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
246
+
247
  Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Felladrin__Llama-160M-Chat-v1)
248
 
249
  | Metric |Value|
 
255
  |TruthfulQA (0-shot) |44.16|
256
  |Winogrande (5-shot) |51.30|
257
  |GSM8k (5-shot) | 0.00|