Update README.md
Browse files
README.md
CHANGED
@@ -256,7 +256,17 @@ output = llm(
|
|
256 |
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
|
257 |
echo=True # Whether to echo the prompt
|
258 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
259 |
|
|
|
260 |
```
|
261 |
|
262 |
## How to use with LangChain
|
|
|
256 |
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
|
257 |
echo=True # Whether to echo the prompt
|
258 |
)
|
259 |
+
```
|
260 |
+
|
261 |
+
#### Simple example code to load one of these GGUF models
|
262 |
+
|
263 |
+
```python
|
264 |
+
from ctransformers import AutoModelForCausalLM
|
265 |
+
|
266 |
+
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
|
267 |
+
llm = AutoModelForCausalLM.from_pretrained("infosys/NT-Java-1.1B-GGUF", model_file="NT-Java-1.1B_Q4_K_M.gguf", model_type="gpt_bigcode", gpu_layers=50)
|
268 |
|
269 |
+
print(llm("AI is going to"))
|
270 |
```
|
271 |
|
272 |
## How to use with LangChain
|