Add DeepSeek R1 models, Llama 3.3, Aya-expanse, and InternVL2_5

vec_inf/cli/_cli.py

@@ -381,9 +381,12 @@ def list_all(models_df: pl.DataFrame, json_mode: bool) -> None:
 
         for row in models_df.to_dicts():
             panel_color = model_type_colors.get(row["model_type"], "white")
-            styled_text = (
-                f"[magenta]{row['model_family']}[/magenta]-{row['model_variant']}"
-            )
+            if row['model_variant'] == "None":
+                styled_text = (f"[magenta]{row['model_family']}[/magenta]")
+            else:
+                styled_text = (
+                    f"[magenta]{row['model_family']}[/magenta]-{row['model_variant']}"
+                )
             panels.append(Panel(styled_text, expand=True, border_style=panel_color))
         CONSOLE.print(Columns(panels, equal=True))
 

vec_inf/launch_server.sh

@@ -52,9 +52,9 @@ export MODEL_WEIGHTS_PARENT_DIR=$model_weights_parent_dir
 
 if [[ "$model_type" == "LLM" || "$model_type" == "VLM" ]]; then
     export VLLM_TASK="generate"
-elif [[ "$model_type" == "Reward_Modeling" ]]; then
+elif [ "$model_type" == "Reward_Modeling" ]; then
     export VLLM_TASK="reward"
-elif [[ "$model_type" == "Text_Embedding" ]]; then
+elif [ "$model_type" == "Text_Embedding" ]; then
     export VLLM_TASK="embed"
 else
     echo "Error: Unknown model_type: $model_type"
@@ -82,6 +82,10 @@ fi
 # ================================= Set default environment variables ======================================
 # Slurm job configuration
 export JOB_NAME="$MODEL_FAMILY-$MODEL_VARIANT"
+if [ "$JOB_NAME" == "DeepSeek-R1-None" ]; then
+    export JOB_NAME=$MODEL_FAMILY
+fi
+
 if [ "$LOG_DIR" = "default" ]; then
     export LOG_DIR="$HOME/.vec-inf-logs/$MODEL_FAMILY"
 fi

vec_inf/models/models.csv

@@ -73,3 +73,14 @@ Pixtral-12B-2409,Pixtral,12B-2409,VLM,1,1,131072,8192,256,true,false,m2,08:00:00
 e5-mistral-7b-instruct,e5,mistral-7b-instruct,Text Embedding,1,1,32000,4096,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
 bge-base-en-v1.5,bge,base-en-v1.5,Text Embedding,1,1,30522,512,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
 all-MiniLM-L6-v2,all-MiniLM,L6-v2,Text Embedding,1,1,30522,512,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
+Llama-3.3-70B-Instruct,Llama-3.3,70B-Instruct,LLM,4,1,128256,65536,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
+InternVL2_5-26B,InternVL2_5,26B,VLM,2,1,92553,32768,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
+InternVL2_5-38B,InternVL2_5,38B,VLM,4,1,92553,32768,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
+Aya-Expanse-32B,Aya-Expanse,32B,LLM,2,1,256000,8192,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
+DeepSeek-R1,DeepSeek-R1,None,LLM,4,16,129280,32768,256,true,false,m5,01:00:00,a40,auto,singularity,default,/model-weights
+DeepSeek-R1-Distill-Llama-70B,DeepSeek-R1,Distill-Llama-70B ,LLM,4,1,128256,65536,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
+DeepSeek-R1-Distill-Llama-8B,DeepSeek-R1,Distill-Llama-8B ,LLM,1,1,128256,131072,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
+DeepSeek-R1-Distill-Qwen-32B,DeepSeek-R1,Distill-Qwen-32B,LLM,2,1,152064,65536,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
+DeepSeek-R1-Distill-Qwen-14B,DeepSeek-R1,Distill-Qwen-14B,LLM,1,1,152064,65536,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
+DeepSeek-R1-Distill-Qwen-7B,DeepSeek-R1,Distill-Qwen-7B,LLM,1,1,152064,131072,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights
+DeepSeek-R1-Distill-Qwen-1.5B,DeepSeek-R1,Distill-Qwen-1.5B,LLM,1,1,152064,131072,256,true,false,m2,08:00:00,a40,auto,singularity,default,/model-weights