lamm-mit
/

Cephalo-Phi-3-MoE-vision-128k-3x4b-beta

Model card Files Files and versions Community

mjbuehler commited on Jun 1

Commit

1e0f2e3

•

1 Parent(s): 3b747f6

Update README.md

Files changed (1) hide show

README.md +5 -3

README.md CHANGED Viewed

@@ -116,6 +116,7 @@ from Phi_3V_MoE.moe_phi3_v import Phi3VForCausalLMMoE, Phi3VForCausalLMMoEConfig
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model_name_1 = f"lamm-mit/Cephalo-Phi-3-vision-128k-4b-beta"
 model_1 = AutoModelForCausalLM.from_pretrained(
     model_name_1,
@@ -123,6 +124,7 @@ model_1 = AutoModelForCausalLM.from_pretrained(
 ).to(device)
 model_name_2 = f"microsoft/Phi-3-vision-128k-instruct"
 model_2 = AutoModelForCausalLM.from_pretrained(
     model_name_2,
@@ -130,15 +132,15 @@ model_2 = AutoModelForCausalLM.from_pretrained(
 ).to(device)
-model_name_3 = f"lamm-mit/Cephalo-Phi-3-vision-128k-4b-alpha"
 model_3 = AutoModelForCausalLM.from_pretrained(
     model_name_3,
     trust_remote_code=True,  torch_dtype=torch.bfloat16,
 ).to(device)
-dtype = torch.bfloat16  # Desired dtype for new layers
 # Initialize the models
 base_model = copy.deepcopy(model_2)  # Your base model

 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+#Model specialized in bio-inspired/mechanics and materials
 model_name_1 = f"lamm-mit/Cephalo-Phi-3-vision-128k-4b-beta"
 model_1 = AutoModelForCausalLM.from_pretrained(
     model_name_1,
 ).to(device)
+#Original model
 model_name_2 = f"microsoft/Phi-3-vision-128k-instruct"
 model_2 = AutoModelForCausalLM.from_pretrained(
     model_name_2,
 ).to(device)
+#Model trained on conversion of images to LaTeX formulas
+model_name_3 = f"lamm-mit/Cephalo-LaTeX-Phi-3-vision-128k-4b-alpha"
 model_3 = AutoModelForCausalLM.from_pretrained(
     model_name_3,
     trust_remote_code=True,  torch_dtype=torch.bfloat16,
 ).to(device)
+dtype = torch.bfloat16  # Desired dtype for new layers in MoE model
 # Initialize the models
 base_model = copy.deepcopy(model_2)  # Your base model