Transformers
GGUF
llama
text-generation-inference
TheBloke commited on
Commit
e300879
1 Parent(s): abd867c

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -164,7 +164,7 @@ CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
164
  from ctransformers import AutoModelForCausalLM
165
 
166
  # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
167
- llm = AutoModelForCausalLM.from_pretrained("TheBloke/WizardLM-13B-V1.2-GGML", model_file="wizardlm-13b-v1.2.q4_K_M.gguf", model_type="llama", gpu_layers=50)
168
 
169
  print(llm("AI is going to"))
170
  ```
 
164
  from ctransformers import AutoModelForCausalLM
165
 
166
  # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
167
+ llm = AutoModelForCausalLM.from_pretrained("TheBloke/WizardLM-13B-V1.2-GGUF", model_file="wizardlm-13b-v1.2.q4_K_M.gguf", model_type="llama", gpu_layers=50)
168
 
169
  print(llm("AI is going to"))
170
  ```