Commit
•
047baaf
1
Parent(s):
3775a87
Update README.md (#3)
Browse files- Update README.md (1096b2aab0f9833a995211b1531b61eec6009ae3)
Co-authored-by: Ashmal Vayani <Ashmal@users.noreply.huggingface.co>
README.md
CHANGED
@@ -39,7 +39,7 @@ prompt = "What are the psychological effects of urban living on mental health?"
|
|
39 |
|
40 |
input_str = template.format(prompt=prompt)
|
41 |
input_ids = tokenizer(input_str, return_tensors="pt").input_ids
|
42 |
-
outputs = model.generate(input_ids, max_length=1000)
|
43 |
print(tokenizer.batch_decode(outputs[:, input_ids.shape[1]:-1])[0].strip())
|
44 |
```
|
45 |
|
@@ -87,4 +87,6 @@ python3 -m fastchat.serve.cli --model-path MBZUAI/MobiLlama-05B-Chat
|
|
87 |
|
88 |
|
89 |
## Intended Uses
|
90 |
-
Given the nature of the training data, the MobiLlama-05B model is best suited for prompts using the QA format, the chat format, and the code format.
|
|
|
|
|
|
39 |
|
40 |
input_str = template.format(prompt=prompt)
|
41 |
input_ids = tokenizer(input_str, return_tensors="pt").input_ids
|
42 |
+
outputs = model.generate(input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
|
43 |
print(tokenizer.batch_decode(outputs[:, input_ids.shape[1]:-1])[0].strip())
|
44 |
```
|
45 |
|
|
|
87 |
|
88 |
|
89 |
## Intended Uses
|
90 |
+
Given the nature of the training data, the MobiLlama-05B model is best suited for prompts using the QA format, the chat format, and the code format.
|
91 |
+
|
92 |
+
## Citation
|