docs update

amaiya · Apr 2, 2023 · 2336cab · 2336cab
1 parent 17ed3fe
commit 2336cab
Show file tree

Hide file tree

Showing 5 changed files with 403 additions and 1 deletion.
diff --git a/docs/text/generative_ai/core.html b/docs/text/generative_ai/core.html
@@ -0,0 +1,325 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1" />
+<meta name="generator" content="pdoc 0.10.0" />
+<title>ktrain.text.generative_ai.core API documentation</title>
+<meta name="description" content="" />
+<link rel="preload stylesheet" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/11.0.1/sanitize.min.css" integrity="sha256-PK9q560IAAa6WVRRh76LtCaI8pjTJ2z11v0miyNNjrs=" crossorigin>
+<link rel="preload stylesheet" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/11.0.1/typography.min.css" integrity="sha256-7l/o7C8jubJiy74VsKTidCy1yBkRtiUGbVkYBylBqUg=" crossorigin>
+<link rel="stylesheet preload" as="style" href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/10.1.1/styles/github.min.css" crossorigin>
+<style>:root{--highlight-color:#fe9}.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:30px;overflow:hidden}#sidebar > *:last-child{margin-bottom:2cm}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:1em 0 .50em 0}h3{font-size:1.4em;margin:25px 0 10px 0}h4{margin:0;font-size:105%}h1:target,h2:target,h3:target,h4:target,h5:target,h6:target{background:var(--highlight-color);padding:.2em 0}a{color:#058;text-decoration:none;transition:color .3s ease-in-out}a:hover{color:#e82}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900}pre code{background:#f8f8f8;font-size:.8em;line-height:1.4em}code{background:#f2f2f1;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{background:#f8f8f8;border:0;border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0;padding:1ex}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{margin-top:.6em;font-weight:bold}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-weight:bold;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}dt:target .name{background:var(--highlight-color)}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}td{padding:0 .5em}.admonition{padding:.1em .5em;margin-bottom:1em}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
+<style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%;height:100vh;overflow:auto;position:sticky;top:0}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.item .name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul{padding-left:1.5em}.toc > ul > li{margin-top:.5em}}</style>
+<style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
+<script defer src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/10.1.1/highlight.min.js" integrity="sha256-Uv3H6lx7dJmRfRvH8TH6kJD1TSK1aFcwgx+mdg3epi8=" crossorigin></script>
+<script>window.addEventListener('DOMContentLoaded', () => hljs.initHighlighting())</script>
+</head>
+<body>
+<main>
+<article id="content">
+<header>
+<h1 class="title">Module <code>ktrain.text.generative_ai.core</code></h1>
+</header>
+<section id="section-intro">
+<details class="source">
+<summary>
+<span>Expand source code</span>
+</summary>
+<pre><code class="python">from transformers import pipeline, GenerationConfig
+import torch
+from ...torch_base import TorchBase
+from typing import Optional
+import warnings
+
+
+class GenerativeAI(TorchBase):
+    &#34;&#34;&#34;
+    interface to Transformer-based generative AI models like GPT*
+    &#34;&#34;&#34;
+
+    def __init__(
+        self,
+        model_name: str = &#34;nlpcloud/instruct-gpt-j-fp16&#34;,
+        device: Optional[str] = None,
+        max_new_tokens: int = 512,
+        do_sample: bool = True,
+        **kwargs
+    ):
+        &#34;&#34;&#34;
+        ```
+        Interface to GenerativeAI models using the transformers library.
+        Extra kwargs are supplied directly to the generate method of the model.
+
+        Args:
+          model_name(str): name of the model.  Currently, only the nlpcloud/instruct-gpt-j-fp16
+          device(str): device to use (&#34;cpu&#34; for CPU, &#34;cuda&#34; for GPU, &#34;cuda:0&#34; for first GPU, &#34;cuda:1&#34; for second GPU ,etc.):
+          max_new_tokens(int):  The maximum numbers of tokens to generate, ignoring the number of tokens in the prompt.
+          do_sample(bool):  If True, use sampling instead of the default greedy decoding.
+        ```
+        &#34;&#34;&#34;
+
+        super().__init__(device=device)
+        self.device_id = self.device_to_id()
+        self.config = GenerationConfig(
+            max_new_tokens=max_new_tokens, do_sample=do_sample, **kwargs
+        )
+        if self.device_id &lt; 0:
+            self.generator = pipeline(
+                model=model_name, device=self.device_id, generation_config=self.config
+            )
+        else:
+            self.generator = pipeline(
+                model=model_name,
+                torch_dtype=torch.float16,
+                device=self.device_id,
+                generation_config=self.config,
+            )
+        self.generator.model.generation_config.pad_token_id = (
+            self.generator.model.generation_config.eos_token_id
+        )
+
+    def execute(self, prompt: str):
+        &#34;&#34;&#34;
+        ```
+        Issue a prompt to the model.  The default model is an instruction-fine-tuned model based on GPT-J.
+        This means that you should always construct your prompt in the form of an instruction.
+
+
+        Example:
+
+        model = GenerativeAI()
+        prompt = &#34;Tell me whether the following sentence is positive,  negative, or neutral in sentiment.\\nThe reactivity of  your team has been amazing, thanks!\\n&#34;
+        model.prompt(prompt)
+
+
+        Args:
+          prompt(str): prompt to supply to model
+        Returns:
+          str: generated text
+        ```
+        &#34;&#34;&#34;
+        prompt = prompt.strip() + &#34;\n&#34;
+        result = self.generator(prompt)
+        result = result[0][&#34;generated_text&#34;]
+        if result.startswith(prompt):
+            result = result.replace(prompt, &#34;&#34;)
+        if not result:
+            warnings.warn(
+                &#34;No output was generated. The model is sensitive to where you please newlines. Try adding or removing embedded newlines in the prompt. Follow the example notebook for tips.&#34;
+            )
+
+        return result.replace(&#34;\\n&#34;, &#34;\n&#34;)</code></pre>
+</details>
+</section>
+<section>
+</section>
+<section>
+</section>
+<section>
+</section>
+<section>
+<h2 class="section-title" id="header-classes">Classes</h2>
+<dl>
+<dt id="ktrain.text.generative_ai.core.GenerativeAI"><code class="flex name class">
+<span>class <span class="ident">GenerativeAI</span></span>
+<span>(</span><span>model_name: str = 'nlpcloud/instruct-gpt-j-fp16', device: Optional[str] = None, max_new_tokens: int = 512, do_sample: bool = True, **kwargs)</span>
+</code></dt>
+<dd>
+<div class="desc"><p>interface to Transformer-based generative AI models like GPT*</p>
+<pre><code>Interface to GenerativeAI models using the transformers library.
+Extra kwargs are supplied directly to the generate method of the model.
+
+Args:
+  model_name(str): name of the model.  Currently, only the nlpcloud/instruct-gpt-j-fp16
+  device(str): device to use (&quot;cpu&quot; for CPU, &quot;cuda&quot; for GPU, &quot;cuda:0&quot; for first GPU, &quot;cuda:1&quot; for second GPU ,etc.):
+  max_new_tokens(int):  The maximum numbers of tokens to generate, ignoring the number of tokens in the prompt.
+  do_sample(bool):  If True, use sampling instead of the default greedy decoding.
+</code></pre></div>
+<details class="source">
+<summary>
+<span>Expand source code</span>
+</summary>
+<pre><code class="python">class GenerativeAI(TorchBase):
+    &#34;&#34;&#34;
+    interface to Transformer-based generative AI models like GPT*
+    &#34;&#34;&#34;
+
+    def __init__(
+        self,
+        model_name: str = &#34;nlpcloud/instruct-gpt-j-fp16&#34;,
+        device: Optional[str] = None,
+        max_new_tokens: int = 512,
+        do_sample: bool = True,
+        **kwargs
+    ):
+        &#34;&#34;&#34;
+        ```
+        Interface to GenerativeAI models using the transformers library.
+        Extra kwargs are supplied directly to the generate method of the model.
+
+        Args:
+          model_name(str): name of the model.  Currently, only the nlpcloud/instruct-gpt-j-fp16
+          device(str): device to use (&#34;cpu&#34; for CPU, &#34;cuda&#34; for GPU, &#34;cuda:0&#34; for first GPU, &#34;cuda:1&#34; for second GPU ,etc.):
+          max_new_tokens(int):  The maximum numbers of tokens to generate, ignoring the number of tokens in the prompt.
+          do_sample(bool):  If True, use sampling instead of the default greedy decoding.
+        ```
+        &#34;&#34;&#34;
+
+        super().__init__(device=device)
+        self.device_id = self.device_to_id()
+        self.config = GenerationConfig(
+            max_new_tokens=max_new_tokens, do_sample=do_sample, **kwargs
+        )
+        if self.device_id &lt; 0:
+            self.generator = pipeline(
+                model=model_name, device=self.device_id, generation_config=self.config
+            )
+        else:
+            self.generator = pipeline(
+                model=model_name,
+                torch_dtype=torch.float16,
+                device=self.device_id,
+                generation_config=self.config,
+            )
+        self.generator.model.generation_config.pad_token_id = (
+            self.generator.model.generation_config.eos_token_id
+        )
+
+    def execute(self, prompt: str):
+        &#34;&#34;&#34;
+        ```
+        Issue a prompt to the model.  The default model is an instruction-fine-tuned model based on GPT-J.
+        This means that you should always construct your prompt in the form of an instruction.
+
+
+        Example:
+
+        model = GenerativeAI()
+        prompt = &#34;Tell me whether the following sentence is positive,  negative, or neutral in sentiment.\\nThe reactivity of  your team has been amazing, thanks!\\n&#34;
+        model.prompt(prompt)
+
+
+        Args:
+          prompt(str): prompt to supply to model
+        Returns:
+          str: generated text
+        ```
+        &#34;&#34;&#34;
+        prompt = prompt.strip() + &#34;\n&#34;
+        result = self.generator(prompt)
+        result = result[0][&#34;generated_text&#34;]
+        if result.startswith(prompt):
+            result = result.replace(prompt, &#34;&#34;)
+        if not result:
+            warnings.warn(
+                &#34;No output was generated. The model is sensitive to where you please newlines. Try adding or removing embedded newlines in the prompt. Follow the example notebook for tips.&#34;
+            )
+
+        return result.replace(&#34;\\n&#34;, &#34;\n&#34;)</code></pre>
+</details>
+<h3>Ancestors</h3>
+<ul class="hlist">
+<li><a title="ktrain.torch_base.TorchBase" href="../../torch_base.html#ktrain.torch_base.TorchBase">TorchBase</a></li>
+</ul>
+<h3>Methods</h3>
+<dl>
+<dt id="ktrain.text.generative_ai.core.GenerativeAI.execute"><code class="name flex">
+<span>def <span class="ident">execute</span></span>(<span>self, prompt: str)</span>
+</code></dt>
+<dd>
+<div class="desc"><pre><code>Issue a prompt to the model.  The default model is an instruction-fine-tuned model based on GPT-J.
+This means that you should always construct your prompt in the form of an instruction.
+
+
+Example:
+
+model = GenerativeAI()
+prompt = &quot;Tell me whether the following sentence is positive,  negative, or neutral in sentiment.\nThe reactivity of  your team has been amazing, thanks!\n&quot;
+model.prompt(prompt)
+
+
+Args:
+  prompt(str): prompt to supply to model
+Returns:
+  str: generated text
+</code></pre></div>
+<details class="source">
+<summary>
+<span>Expand source code</span>
+</summary>
+<pre><code class="python">def execute(self, prompt: str):
+    &#34;&#34;&#34;
+    ```
+    Issue a prompt to the model.  The default model is an instruction-fine-tuned model based on GPT-J.
+    This means that you should always construct your prompt in the form of an instruction.
+
+
+    Example:
+
+    model = GenerativeAI()
+    prompt = &#34;Tell me whether the following sentence is positive,  negative, or neutral in sentiment.\\nThe reactivity of  your team has been amazing, thanks!\\n&#34;
+    model.prompt(prompt)
+
+
+    Args:
+      prompt(str): prompt to supply to model
+    Returns:
+      str: generated text
+    ```
+    &#34;&#34;&#34;
+    prompt = prompt.strip() + &#34;\n&#34;
+    result = self.generator(prompt)
+    result = result[0][&#34;generated_text&#34;]
+    if result.startswith(prompt):
+        result = result.replace(prompt, &#34;&#34;)
+    if not result:
+        warnings.warn(
+            &#34;No output was generated. The model is sensitive to where you please newlines. Try adding or removing embedded newlines in the prompt. Follow the example notebook for tips.&#34;
+        )
+
+    return result.replace(&#34;\\n&#34;, &#34;\n&#34;)</code></pre>
+</details>
+</dd>
+</dl>
+<h3>Inherited members</h3>
+<ul class="hlist">
+<li><code><b><a title="ktrain.torch_base.TorchBase" href="../../torch_base.html#ktrain.torch_base.TorchBase">TorchBase</a></b></code>:
+<ul class="hlist">
+<li><code><a title="ktrain.torch_base.TorchBase.quantize_model" href="../../torch_base.html#ktrain.torch_base.TorchBase.quantize_model">quantize_model</a></code></li>
+</ul>
+</li>
+</ul>
+</dd>
+</dl>
+</section>
+</article>
+<nav id="sidebar">
+<h1>Index</h1>
+<div class="toc">
+<ul></ul>
+</div>
+<ul id="index">
+<li><h3>Super-module</h3>
+<ul>
+<li><code><a title="ktrain.text.generative_ai" href="index.html">ktrain.text.generative_ai</a></code></li>
+</ul>
+</li>
+<li><h3><a href="#header-classes">Classes</a></h3>
+<ul>
+<li>
+<h4><code><a title="ktrain.text.generative_ai.core.GenerativeAI" href="#ktrain.text.generative_ai.core.GenerativeAI">GenerativeAI</a></code></h4>
+<ul class="">
+<li><code><a title="ktrain.text.generative_ai.core.GenerativeAI.execute" href="#ktrain.text.generative_ai.core.GenerativeAI.execute">execute</a></code></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</nav>
+</main>
+<footer id="footer">
+<p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.10.0</a>.</p>
+</footer>
+</body>
+</html>