Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
---
|
6 |
+
|
7 |
+
## Model Details
|
8 |
+
- *Finetuned+Capable for laptop
|
9 |
+
### Model Description
|
10 |
+
------------
|
11 |
+
Capable for run in Low-end **laptop**
|
12 |
+
|
13 |
+
- **Developed by:** [Tiny-llama]("https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0/tree/main")
|
14 |
+
|
15 |
+
- **Finetuned from model [optional]:** [Tiny-llama]("https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0/tree/main")
|
16 |
+
|
17 |
+
|
18 |
+
|
19 |
+
## Uses
|
20 |
+
```python
|
21 |
+
from llama_cpp import Llama
|
22 |
+
|
23 |
+
llm = Llama(
|
24 |
+
model_path="path/to/llama",
|
25 |
+
# n_gpu_layers=-1, # Uncomment to use GPU acceleration
|
26 |
+
# seed=1337, # Uncomment to set a specific seed
|
27 |
+
# n_ctx=2048, # Uncomment to increase the context window
|
28 |
+
)
|
29 |
+
output = llm(
|
30 |
+
"Q: Name the planets in the solar system? A: ", # Prompt
|
31 |
+
max_tokens=32, # Generate up to 32 tokens, set to None to generate up to the end of the context window
|
32 |
+
stop=["Q:", "\n"], # Stop generating just before the model would generate a new question
|
33 |
+
echo=True # Echo the prompt back in the output
|
34 |
+
) # Generate a completion, can also call create_completion
|
35 |
+
print(output)
|
36 |
+
```
|