Hugging Face's logo

Spaces:
tunedtensor
/
README
Running

App Files Community
weijianzhg commited on
Commit
98147fe
路
verified 路
1 Parent(s): 1a34d8f

Use clean semantic organization card markup

Browse files
Files changed (2) hide show
  1. README.md +8 -10
  2. index.html +19 -34
README.md CHANGED
@@ -4,20 +4,20 @@ sdk: static
4
  pinned: false
5
  ---
6
 
7
- # Tuned Tensor
8
 
9
  **Behaviour control infrastructure for open-weight language models.**
10
 
11
- Tuned Tensor helps teams define how a model should behave, fine-tune open-weight models against that behaviour spec, evaluate the result, and feed the findings back into the next run.
12
 
13
- ## Workflow
14
 
15
- 1. **Specify behaviour** with system prompts, guidelines, constraints, examples, and a base model.
16
- 2. **Fine-tune** by compiling training data and tuning supported open-weight models.
17
- 3. **Evaluate** with per-example scores, failure inspection, and regression checks.
18
- 4. **Iterate** by refining the spec and starting the next run.
19
 
20
- ## Get started
21
 
22
  ```bash
23
  npm i -g @tuned-tensor/cli
@@ -25,6 +25,4 @@ tt init
25
  tt runs start <spec-id>
26
  ```
27
 
28
- Every feature is available through the open-source `tt` CLI or the REST API.
29
-
30
  [Website](https://tunedtensor.com/) 路 [Docs](https://tunedtensor.com/docs) 路 [CLI](https://github.com/tunedtensor/tuned-tensor-cli) 路 [Agent skill](https://tunedtensor.com/skill.md)
 
4
  pinned: false
5
  ---
6
 
7
+ ## Tuned Tensor
8
 
9
  **Behaviour control infrastructure for open-weight language models.**
10
 
11
+ Specify behaviour, fine-tune open-weight models, and use evaluation feedback to start the next run.
12
 
13
+ ### Workflow
14
 
15
+ - **Specify behaviour:** capture system prompts, guidelines, constraints, examples, and a base model in a structured spec.
16
+ - **Fine-tune:** compile training data and tune supported open-weight models.
17
+ - **Evaluate:** score outputs, inspect failures, and catch regressions.
18
+ - **Iterate:** use run feedback to refine the spec and start the next tuning pass.
19
 
20
+ ### Get started
21
 
22
  ```bash
23
  npm i -g @tuned-tensor/cli
 
25
  tt runs start <spec-id>
26
  ```
27
 
 
 
28
  [Website](https://tunedtensor.com/) 路 [Docs](https://tunedtensor.com/docs) 路 [CLI](https://github.com/tunedtensor/tuned-tensor-cli) 路 [Agent skill](https://tunedtensor.com/skill.md)
index.html CHANGED
@@ -4,47 +4,32 @@
4
  <meta charset="utf-8">
5
  <meta name="viewport" content="width=device-width, initial-scale=1">
6
  <title>Tuned Tensor</title>
7
- <link rel="stylesheet" href="style.css">
8
  </head>
9
  <body>
10
- <main class="org-card" aria-labelledby="title">
11
- <p class="eyebrow">Behaviour control infrastructure</p>
12
- <h1 id="title">Tuned Tensor</h1>
13
- <p class="lead">Specify behaviour, fine-tune open-weight models, and use evaluation feedback to start the next run.</p>
14
 
15
- <section class="panel" aria-label="Workflow">
16
- <div>
17
- <span>01</span>
18
- <strong>Specify behaviour</strong>
19
- <p>Capture system prompts, guidelines, constraints, examples, and a base model in a structured spec.</p>
20
- </div>
21
- <div>
22
- <span>02</span>
23
- <strong>Fine-tune</strong>
24
- <p>Compile training data and tune supported open-weight models.</p>
25
- </div>
26
- <div>
27
- <span>03</span>
28
- <strong>Evaluate</strong>
29
- <p>Score outputs, inspect failures, and catch regressions.</p>
30
- </div>
31
- <div>
32
- <span>04</span>
33
- <strong>Iterate</strong>
34
- <p>Use run feedback to refine the spec and start the next tuning pass.</p>
35
- </div>
36
- </section>
37
 
38
- <pre aria-label="CLI quickstart"><code>npm i -g @tuned-tensor/cli
 
39
  tt init
40
  tt runs start &lt;spec-id&gt;</code></pre>
41
 
42
- <nav aria-label="Tuned Tensor links">
43
- <a href="https://tunedtensor.com/" target="_blank" rel="noreferrer">Website</a>
44
- <a href="https://tunedtensor.com/docs" target="_blank" rel="noreferrer">Docs</a>
45
- <a href="https://github.com/tunedtensor/tuned-tensor-cli" target="_blank" rel="noreferrer">CLI</a>
46
  <a href="https://tunedtensor.com/skill.md" target="_blank" rel="noreferrer">Agent skill</a>
47
- </nav>
48
- </main>
49
  </body>
50
  </html>
 
4
  <meta charset="utf-8">
5
  <meta name="viewport" content="width=device-width, initial-scale=1">
6
  <title>Tuned Tensor</title>
 
7
  </head>
8
  <body>
9
+ <article>
10
+ <h2>Tuned Tensor</h2>
11
+ <p><strong>Behaviour control infrastructure for open-weight language models.</strong></p>
12
+ <p>Specify behaviour, fine-tune open-weight models, and use evaluation feedback to start the next run.</p>
13
 
14
+ <h3>Workflow</h3>
15
+ <ul>
16
+ <li><strong>Specify behaviour:</strong> capture system prompts, guidelines, constraints, examples, and a base model in a structured spec.</li>
17
+ <li><strong>Fine-tune:</strong> compile training data and tune supported open-weight models.</li>
18
+ <li><strong>Evaluate:</strong> score outputs, inspect failures, and catch regressions.</li>
19
+ <li><strong>Iterate:</strong> use run feedback to refine the spec and start the next tuning pass.</li>
20
+ </ul>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
 
22
+ <h3>Get started</h3>
23
+ <pre><code>npm i -g @tuned-tensor/cli
24
  tt init
25
  tt runs start &lt;spec-id&gt;</code></pre>
26
 
27
+ <p>
28
+ <a href="https://tunedtensor.com/" target="_blank" rel="noreferrer">Website</a> &middot;
29
+ <a href="https://tunedtensor.com/docs" target="_blank" rel="noreferrer">Docs</a> &middot;
30
+ <a href="https://github.com/tunedtensor/tuned-tensor-cli" target="_blank" rel="noreferrer">CLI</a> &middot;
31
  <a href="https://tunedtensor.com/skill.md" target="_blank" rel="noreferrer">Agent skill</a>
32
+ </p>
33
+ </article>
34
  </body>
35
  </html>