Update README.md
Browse files
README.md
CHANGED
|
@@ -41,42 +41,6 @@ We use state-of-the-art [Language Model Evaluation Harness](https://github.com/E
|
|
| 41 |
|
| 42 |
The above loss curve was generated from the run's private wandb.ai log.
|
| 43 |
|
| 44 |
-
### Example prompts and responses
|
| 45 |
-
|
| 46 |
-
Example 1:
|
| 47 |
-
|
| 48 |
-
**User**:
|
| 49 |
-
> You are a helpful assistant. Write me a numbered list of things to do in New York City.\n
|
| 50 |
-
|
| 51 |
-
**llama-2-7b-instruct-peft**:
|
| 52 |
-
coming
|
| 53 |
-
|
| 54 |
-
<br>
|
| 55 |
-
|
| 56 |
-
Example 2:
|
| 57 |
-
|
| 58 |
-
**User**:
|
| 59 |
-
|
| 60 |
-
> You are a helpful assistant. Write a short email inviting my friends to a dinner party on Friday. Respond succinctly.\n
|
| 61 |
-
|
| 62 |
-
**llama-2-7b-instruct-peft**:
|
| 63 |
-
|
| 64 |
-
coming
|
| 65 |
-
|
| 66 |
-
<br>
|
| 67 |
-
|
| 68 |
-
Example 3:
|
| 69 |
-
|
| 70 |
-
**User**:
|
| 71 |
-
|
| 72 |
-
> You are a helpful assistant. Tell me a recipe for vegan banana bread.\n
|
| 73 |
-
|
| 74 |
-
**llama-2-7b-instruct-peft**:
|
| 75 |
-
|
| 76 |
-
coming
|
| 77 |
-
|
| 78 |
-
<br>
|
| 79 |
-
|
| 80 |
## Limitations and biases
|
| 81 |
|
| 82 |
_The following language is modified from [EleutherAI's GPT-NeoX-20B](https://huggingface.co/EleutherAI/gpt-neox-20b)_
|
|
|
|
| 41 |
|
| 42 |
The above loss curve was generated from the run's private wandb.ai log.
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
## Limitations and biases
|
| 45 |
|
| 46 |
_The following language is modified from [EleutherAI's GPT-NeoX-20B](https://huggingface.co/EleutherAI/gpt-neox-20b)_
|