fix(readme): body:sub('huggingface\\.co/zenlm/zen-next-80b-instruct')x1;sub('"zenlm/zen-next-80b-instruct"')x2;sub('zenlm/zen-next-80b-instruct')x1
Browse files
README.md
CHANGED
|
@@ -22,12 +22,12 @@ Multilingual generation across 30+ languages: English, Chinese, Japanese, Korean
|
|
| 22 |
|
| 23 |
Strong at cross-lingual reasoning, code-switching, and multilingual instruction following.
|
| 24 |
|
| 25 |
-
Base weights: [zenlm/zen-
|
| 26 |
|
| 27 |
```python
|
| 28 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 29 |
-
model = AutoModelForCausalLM.from_pretrained("zenlm/zen-
|
| 30 |
-
tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-
|
| 31 |
messages = [{"role": "user", "content": "Your domain-specific prompt here"}]
|
| 32 |
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
| 33 |
inputs = tokenizer(text, return_tensors="pt").to(model.device)
|
|
|
|
| 22 |
|
| 23 |
Strong at cross-lingual reasoning, code-switching, and multilingual instruction following.
|
| 24 |
|
| 25 |
+
Base weights: [zenlm/zen-pro](https://huggingface.co/zenlm/zen-pro)
|
| 26 |
|
| 27 |
```python
|
| 28 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 29 |
+
model = AutoModelForCausalLM.from_pretrained("zenlm/zen-pro", torch_dtype="auto")
|
| 30 |
+
tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-pro")
|
| 31 |
messages = [{"role": "user", "content": "Your domain-specific prompt here"}]
|
| 32 |
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
| 33 |
inputs = tokenizer(text, return_tensors="pt").to(model.device)
|