Update constants.py

Moving MODEL_ID & MODEL_BASENAME to constant.py

constants.py

@@ -40,3 +40,39 @@
 # You can also choose a smaller model, don't forget to change HuggingFaceInstructEmbeddings
 # to HuggingFaceEmbeddings in both ingest.py and run_localGPT.py
 # EMBEDDING_MODEL_NAME = "all-MiniLM-L6-v2"
+
+# Select the Model ID and model_basename
+# load the LLM for generating Natural Language responses
+
+MODEL_ID = "TheBloke/vicuna-13B-v1.5-16K-GGML"
+MODEL_BASENAME = "vicuna-13b-v1.5-16k.ggmlv3.q4_0.bin"
+
+# for HF models
+# model_id = "TheBloke/vicuna-7B-1.1-HF"
+# model_basename = None
+# model_id = "TheBloke/Wizard-Vicuna-7B-Uncensored-HF"
+# model_id = "TheBloke/guanaco-7B-HF"
+# model_id = 'NousResearch/Nous-Hermes-13b' # Requires ~ 23GB VRAM. Using STransformers
+# alongside will 100% create OOM on 24GB cards.
+# llm = load_model(device_type, model_id=model_id)
+
+# for GPTQ (quantized) models
+# model_id = "TheBloke/Nous-Hermes-13B-GPTQ"
+# model_basename = "nous-hermes-13b-GPTQ-4bit-128g.no-act.order"
+# model_id = "TheBloke/WizardLM-30B-Uncensored-GPTQ"
+# model_basename = "WizardLM-30B-Uncensored-GPTQ-4bit.act-order.safetensors" # Requires
+# ~21GB VRAM. Using STransformers alongside can potentially create OOM on 24GB cards.
+# model_id = "TheBloke/wizardLM-7B-GPTQ"
+# model_basename = "wizardLM-7B-GPTQ-4bit.compat.no-act-order.safetensors"
+# model_id = "TheBloke/WizardLM-7B-uncensored-GPTQ"
+# model_basename = "WizardLM-7B-uncensored-GPTQ-4bit-128g.compat.no-act-order.safetensors"
+
+# for GGML (quantized cpu+gpu+mps) models - check if they support llama.cpp
+# model_id = "TheBloke/wizard-vicuna-13B-GGML"
+# model_basename = "wizard-vicuna-13B.ggmlv3.q4_0.bin"
+# model_basename = "wizard-vicuna-13B.ggmlv3.q6_K.bin"
+# model_basename = "wizard-vicuna-13B.ggmlv3.q2_K.bin"
+# model_id = "TheBloke/orca_mini_3B-GGML"
+# model_basename = "orca-mini-3b.ggmlv3.q4_0.bin"
+
+