diff --git a/Git-management.png b/Git-management.png
index ebace6ff..5ce6266c 100644
Binary files a/Git-management.png and b/Git-management.png differ
diff --git a/HowToRun_vLLM_Models.md b/HowToRun_vLLM_Models.md
index fa30371d..8b19c6a5 100644
--- a/HowToRun_vLLM_Models.md
+++ b/HowToRun_vLLM_Models.md
@@ -1,6 +1,10 @@
-# Running Llama3.1-70B and Mock vLLM Models in TT-Studio
+# Running Llama and Mock vLLM Models in TT-Studio
-This guide provides step-by-step instructions on setting up and deploying vLLM Llama3.1-70B and vLLM Mock models using TT-Studio.
+This guide walks you through setting up vLLM Llama models and vLLM Mock models via the TT-Inference-Server, and then deploying them via TT-Studio.
+
+## Supported Models
+
+For the complete and up-to-date list of models supported by TT-Studio via TT-Inference-Server, please refer to [TT-Inference-Server GitHub README](https://github.com/tenstorrent/tt-inference-server/blob/main/README.md).
---
@@ -8,9 +12,8 @@ This guide provides step-by-step instructions on setting up and deploying vLLM L
1. **Docker**: Make sure Docker is installed on your system. Follow the [Docker installation guide](https://docs.docker.com/engine/install/).
-2. **Hugging Face Token**: Both models require authentication to Hugging Face repositories. To obtain a token, go to [Hugging Face Account](https://huggingface.co/settings/tokens) and generate a token. Additionally; make sure to accept the terms and conditions on Hugging Face for the Llama3.1 models by visiting [Hugging Face Meta-Llama Page](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct).
+2. **Hugging Face Token**: Both models require authentication to Hugging Face repositories. To obtain a token, go to [Hugging Face Account](https://huggingface.co/settings/tokens) and generate a token. Additionally; make sure to accept the terms and conditions on Hugging Face for the the desired model(s).
-3. **Model Access Weight**: To access specific models like Llama3.1, you may need to register with Meta to obtain download links for model weights. Visit [Llama Downloads](https://www.llama.com/llama-downloads/) for more information.
---
## Instructions Overview
@@ -19,15 +22,14 @@ This guide provides step-by-step instructions on setting up and deploying vLLM L
1. [Clone repositories](#1-clone-required-repositories)
2. [Pull the mock model Docker image](#2-pull-the-desired-model-docker-images-using-docker-github-registry)
3. [Set up the Hugging Face (HF) token](#3-set-up-environment-variables-and-hugging-face-token)
-4. [Run the mock vLLM model via the GUI](#7-deploy-and-run-the-model)
+4. [Deploy and run inference for the model via the GUI](#5-deploy-and-run-the-model)
-### **For vLLM Llama3.1-70B Model:**
-1. [Clone repositories](#1-clone-required-repositories)
-2. [Pull the model Docker image](#2-pull-the-desired-model-docker-images-using-docker-github-registry)
-3. [Set up the Hugging Face (HF) token in the TT-Studio `.env` file](#3-set-up-environment-variables-and-hugging-face-token)
-4. [Run the model setup script](#4-run-the-setup-script-vllm-llama31-70b-only)
-5. [Update the vLLM Environment Variable in Environment File](#6-add-the-vllm-environment-variable-in-environment-file--copy-the-file-over-to-tt-studio-persistent-volume)
-6. [Deploy and run inference for the Llama3.1-70B model via the GUI](#7-deploy-and-run-the-model)
+
+### **For vLLM Llama Model(s):**
+1. [Clone repositories](#1-clone-required-repositories)
+2. [Pull the model Docker image](#2-pull-the-desired-model-docker-images-using-docker-github-registry)
+3. [Run the model setup script](#4-run-the-setup-script)
+4. [Deploy and run inference for the model via the GUI](#6-deploy-and-run-the-model)
---
@@ -55,128 +57,106 @@ git clone https://github.com/tenstorrent/tt-inference-server
1. **Navigate to the Docker Images:**
- Visit [TT-Inference-Server GitHub Packages](https://github.com/orgs/tenstorrent/packages?repo_name=tt-inference-server).
-2. **Pull the Docker Image:**
+2. **Pull the Desired Model Docker Image:**
```bash
- docker pull ghcr.io/tenstorrent/tt-inference-server:
+
+);
+
+interface FileViewerDialogProps {
+ file: { url: string; name: string; isImage: boolean } | null;
+ onClose: () => void;
+}
+
+const FileViewerDialog: React.FC
+
+
+
+
+
+ {file.isImage ? (
+ + {file.name} +
+
{chatHistory.length === 0 ? (
@@ -186,71 +287,6 @@ const ChatHistory: React.FC = ({
)}
- {message.text &&
- message.files &&
- message.files.length > 0 && (
- - )} - {message.files && message.files.length > 0 && ( -
-
- )}
- Attached Images: -
-
- {message.files.map(
- (file, index) =>
- isImageFile(file) && (
-
-
- {!minimizedImages.has(
- file.image_url?.url || ""
- ) ? (
- 
- setEnlargedImage(
- file.image_url?.url ||
- "/placeholder.svg"
- )
- }
- />
- ) : (
-
- )}
-
- )
- )}
-
-
- {file.name}
-
-
-
-
+
+
+ {allFiles.map((file, index) => {
+ const fileId = isImageFile(file)
+ ? file.image_url?.url || file.id || index.toString()
+ : file.url || file.id || index.toString();
+ const isMinimized = isImageFile(file)
+ ? minimizedFiles.has(fileId)
+ : true; // Files always start minimized
+
+ if (isImageFile(file)) {
+ return (
+
+
+ {!isMinimized ? (
+
+ );
+ }
+
+ return (
+
+ 
+ onFileClick(file.image_url?.url || "", file.name)
+ }
+ />
+
+
+
+
+
+
+
+
+ ) : (
+ Minimize image
+
+
+ )}
+ toggleMinimizeFile(fileId)}
+ >
+
+
+
+
+
+
+
+
+
+ {file.name}
+
+ Maximize image
+
+
+ );
+ })}
+ onFileClick(file.url || "", file.name)}
+ >
+ {getFileIcon(file)}
+
+
+
+
+ {file.size && (
+
+
+
+
+ {file.name}
+
+
+ {file.size && (
+
+ {formatFileSize(file.size)}
+
+ )}
+
+ + {formatFileSize(file.size)} +
+ )} +
@@ -181,6 +216,7 @@ export default function Header({
+
+
+
+
+ {
+ // if (v === "remove") {
+ // handleAgentSelection(""); // Clear selection if "remove" is chosen
+ // } else {
+ // handleAgentSelection(v); // Set selected AI Agent
+ // }
+ // }}
+ >
+
+
+ Search Agent
+
+
+ {/* Add more AI agents as SelectItems here if needed */}
+ {/*
+ Another AI Agent
+ */}
+
+ {selectedAIAgent && (
+
+
+
+ )}
+
+
+
+
+
+
+
+
+ {selectedAIAgent ? "Change or remove AI agent" : "Select AI Agent"}
+
- {isDragging && (
-
-
- )}
+ useEffect(() => {
+ adjustTextareaHeight();
+ window.addEventListener("resize", adjustTextareaHeight);
+ return () => window.removeEventListener("resize", adjustTextareaHeight);
+ }, [textInput]);
-
-
-
- {/* File preview section */}
- {files.length > 0 && (
- <>
-
- {files.map((file, index) => (
-
-
+
+
+ Replace Existing Image?
+
+ You can only have one image at a time. Do you want to replace the
+ existing image with the new one?
+ {pendingImageFile && (
+
+
+
+
+ Cancel
+
+
+ Replace
+
+
+
+
+
+
- {file.type === "image_url" ? (
-
- ) : (
-
-
- {file.name}
-
-
+ return (
+ <>
+
+ New image: {pendingImageFile.name}
- ))}
+ )}
+
+ {isDragging && (
+
+
)}
- {/* Main text input area */}
-
-
- {/* Control buttons */}
-
+
-
-
+
-
-
-
-
-