zeekay commited on
Commit
d925a4d
Β·
verified Β·
1 Parent(s): 89aba01

Update model card: add zen/zenlm tags, fix branding

Browse files
Files changed (1) hide show
  1. README.md +38 -30
README.md CHANGED
@@ -1,55 +1,63 @@
1
  ---
 
2
  license: apache-2.0
3
- language:
4
- - en
5
  tags:
6
- - zen
7
- - zenlm
8
- - hanzo
 
 
 
 
9
  library_name: transformers
10
  ---
11
 
12
- # zen-coder
13
 
14
- Code generation and analysis models (4B to 480B)
15
 
16
- Part of the Zen LM family of models - democratizing AI while protecting our planet.
17
 
18
- ## Model Description
19
 
20
- Code generation and analysis models (4B to 480B)
21
-
22
- This model is part of the Zen LM ecosystem, providing efficient, private, and environmentally responsible AI.
23
-
24
- ## Why Zen LM?
25
-
26
- πŸš€ **Ultra-Efficient** - Optimized for performance across diverse hardware
27
- πŸ”’ **Truly Private** - 100% local processing, no cloud required
28
- 🌱 **Environmentally Responsible** - 95% less energy than cloud AI
29
- πŸ’š **Free Forever** - Apache 2.0 licensed
30
 
31
  ## Quick Start
32
 
33
  ```python
34
  from transformers import AutoModelForCausalLM, AutoTokenizer
35
 
36
- model = AutoModelForCausalLM.from_pretrained("zenlm/zen-coder")
37
- tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-coder")
 
38
 
39
- inputs = tokenizer("Your prompt here", return_tensors="pt")
40
- outputs = model.generate(**inputs)
41
- print(tokenizer.decode(outputs[0]))
 
 
42
  ```
43
 
44
- ## Organizations
 
 
 
 
 
 
 
45
 
46
- **Hanzo AI Inc** - Techstars Portfolio β€’ Award-winning GenAI lab β€’ https://hanzo.ai
47
- **Zoo Labs Foundation** - 501(c)(3) Non-Profit β€’ Environmental preservation β€’ https://zoolabs.io
48
 
49
- ## Contact
50
 
51
- 🌐 https://zenlm.org β€’ πŸ’¬ https://discord.gg/hanzoai β€’ πŸ“§ hello@zenlm.org
 
 
 
 
 
52
 
53
  ## License
54
 
55
- Models: Apache 2.0 β€’ Privacy: No data collection
 
1
  ---
2
+ language: en
3
  license: apache-2.0
 
 
4
  tags:
5
+ - text-generation
6
+ - zen
7
+ - zenlm
8
+ - hanzo
9
+ - code
10
+ - coding
11
+ pipeline_tag: text-generation
12
  library_name: transformers
13
  ---
14
 
15
+ # Zen Coder
16
 
17
+ Code generation and analysis model family spanning 4B to 480B parameters.
18
 
19
+ ## Overview
20
 
21
+ Built on **Zen MoDE (Mixture of Distilled Experts)** architecture with 4B–480B parameters and 128K context window.
22
 
23
+ Developed by [Hanzo AI](https://hanzo.ai) and the [Zoo Labs Foundation](https://zoo.ngo).
 
 
 
 
 
 
 
 
 
24
 
25
  ## Quick Start
26
 
27
  ```python
28
  from transformers import AutoModelForCausalLM, AutoTokenizer
29
 
30
+ model_id = "zenlm/zen-coder"
31
+ tokenizer = AutoTokenizer.from_pretrained(model_id)
32
+ model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
33
 
34
+ messages = [{"role": "user", "content": "Hello!"}]
35
+ text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
36
+ inputs = tokenizer([text], return_tensors="pt").to(model.device)
37
+ outputs = model.generate(**inputs, max_new_tokens=512)
38
+ print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
39
  ```
40
 
41
+ ## API Access
42
+
43
+ ```bash
44
+ curl https://api.hanzo.ai/v1/chat/completions \
45
+ -H "Authorization: Bearer $HANZO_API_KEY" \
46
+ -H "Content-Type: application/json" \
47
+ -d '{"model": "zen-coder", "messages": [{"role": "user", "content": "Hello"}]}'
48
+ ```
49
 
50
+ Get your API key at [console.hanzo.ai](https://console.hanzo.ai) β€” $5 free credit on signup.
 
51
 
52
+ ## Model Details
53
 
54
+ | Attribute | Value |
55
+ |-----------|-------|
56
+ | Parameters | 4B–480B |
57
+ | Architecture | Zen MoDE |
58
+ | Context | 128K tokens |
59
+ | License | Apache 2.0 |
60
 
61
  ## License
62
 
63
+ Apache 2.0