rvk7895 commited on
Commit
83dd665
·
verified ·
1 Parent(s): c37fe02

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -11
README.md CHANGED
@@ -32,7 +32,7 @@ widget:
32
  ---
33
  # pip-code-bandit
34
 
35
- [pipableAi](https://www.pipable.ai/)
36
 
37
  [colab_notebook](https://colab.research.google.com/drive/10av3SxFf0Psx_IkmZbcUhiVznStV5pVS?usp=sharing)
38
 
@@ -51,9 +51,9 @@ widget:
51
 
52
  Given a goal and tools, can AI intelligently use the tools to reach the goal?\
53
  What if it has a meagre 1.3b params/neurons akin to that of an owl? Can it follow instructions and plan to reach a goal?\
54
- Apparently it can!\
55
  Releasing **pip-code-bandit** and **pipflow**\
56
- A `model` and a `library` to manage and run goal oriented agentic system.
57
 
58
 
59
  ## Model attributes
@@ -77,16 +77,16 @@ A `model` and a `library` to manage and run goal oriented agentic system.
77
  ```
78
 
79
 
80
- ## How we built it?
81
 
82
  We used a simulator to simulate environments where the model could play games to achieve goals, given a set of actions available to it.
83
- All the model could do was find the right action and config to incur positive reward.
84
- The reward policy is around the concept of model going to a stable state of zero net sum reward for both good and bad behaviour.
85
- In this set up the model, which was pre trained on code , function documentation and similar OS datasets ,was RL tuned for instruction following and reliability.
86
 
87
  ## License
88
  ```bash
89
- complete open sourced - apache 2.0. License
90
  ```
91
 
92
  ## Usage
@@ -124,15 +124,15 @@ curl -X 'POST' \
124
  -d 'model_name=PipableAI%2Fpip-code-bandit&prompt="YOUR PROMPT"&max_new_tokens=400'
125
  ```
126
 
127
- Alternatively, you can directly access UI endpoint at https://playground.pipable.ai/docs#/default/infer_infer_post.
128
 
129
 
130
 
131
  ### Library Usage
132
 
133
- For directly using the capabilities of model without putting extra efforts on schemas and prompts try to use [pipflow](https://github.com/PipableAI/pipflow).
134
 
135
- For detailed usage refer to the [colab_notebook](https://colab.research.google.com/drive/10av3SxFf0Psx_IkmZbcUhiVznStV5pVS?usp=sharing)
136
 
137
 
138
 
 
32
  ---
33
  # pip-code-bandit
34
 
35
+ [PipableAI](https://www.pipable.ai/)
36
 
37
  [colab_notebook](https://colab.research.google.com/drive/10av3SxFf0Psx_IkmZbcUhiVznStV5pVS?usp=sharing)
38
 
 
51
 
52
  Given a goal and tools, can AI intelligently use the tools to reach the goal?\
53
  What if it has a meagre 1.3b params/neurons akin to that of an owl? Can it follow instructions and plan to reach a goal?\
54
+ It can!\
55
  Releasing **pip-code-bandit** and **pipflow**\
56
+ A `model` and a `library` to manage and run goal-oriented agentic system.
57
 
58
 
59
  ## Model attributes
 
77
  ```
78
 
79
 
80
+ ## How did we build it?
81
 
82
  We used a simulator to simulate environments where the model could play games to achieve goals, given a set of actions available to it.
83
+ All the model could do was find the right action and config to incur a positive reward.
84
+ The reward policy is around the concept of a model going to a stable state of zero net sum reward for both good and bad behaviour.
85
+ In this setup, the model, which was pre-trained on code, function documentation, and similar OS datasets, was RL-tuned for reliability and instruction-following.
86
 
87
  ## License
88
  ```bash
89
+ complete open-sourced - apache 2.0. License
90
  ```
91
 
92
  ## Usage
 
124
  -d 'model_name=PipableAI%2Fpip-code-bandit&prompt="YOUR PROMPT"&max_new_tokens=400'
125
  ```
126
 
127
+ Alternatively, you can directly access the UI endpoint at https://playground.pipable.ai/docs#/default/infer_infer_post.
128
 
129
 
130
 
131
  ### Library Usage
132
 
133
+ To directly use the model's capabilities without putting extra effort into schemas and prompts, try to use [pipflow](https://github.com/PipableAI/pipflow).
134
 
135
+ For detailed usage, refer to the [colab_notebook](https://colab.research.google.com/drive/10av3SxFf0Psx_IkmZbcUhiVznStV5pVS?usp=sharing)
136
 
137
 
138