Text Generation
Transformers
Safetensors
English
qwen2
code
code-generation
full-stack
react
nextjs
typescript
tailwindcss
prisma
zustand
qwen2.5-coder
vibe-coding
conversational
text-generation-inference
Instructions to use shawaz03/vibe-coder-7b-max with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shawaz03/vibe-coder-7b-max with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="shawaz03/vibe-coder-7b-max") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("shawaz03/vibe-coder-7b-max") model = AutoModelForCausalLM.from_pretrained("shawaz03/vibe-coder-7b-max", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use shawaz03/vibe-coder-7b-max with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "shawaz03/vibe-coder-7b-max" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "shawaz03/vibe-coder-7b-max", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/shawaz03/vibe-coder-7b-max
- SGLang
How to use shawaz03/vibe-coder-7b-max with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "shawaz03/vibe-coder-7b-max" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "shawaz03/vibe-coder-7b-max", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "shawaz03/vibe-coder-7b-max" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "shawaz03/vibe-coder-7b-max", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use shawaz03/vibe-coder-7b-max with Docker Model Runner:
docker model run hf.co/shawaz03/vibe-coder-7b-max
Update quickstart notebook with dynamic form field
Browse files- vibe_coder_quickstart.ipynb +46 -23
vibe_coder_quickstart.ipynb
CHANGED
|
@@ -4,14 +4,14 @@
|
|
| 4 |
"cell_type": "markdown",
|
| 5 |
"metadata": {},
|
| 6 |
"source": [
|
| 7 |
-
"# ๐ VIBE CODER v2.0 MAX โ Official Google Colab
|
| 8 |
"\n",
|
| 9 |
-
"[](https://colab.research.google.com/github/shawaz03/
|
| 10 |
"\n",
|
| 11 |
-
"
|
| 12 |
"\n",
|
| 13 |
-
"- **Model**: [`shawaz03/vibe-coder-7b-max`](https://huggingface.co/shawaz03/vibe-coder-7b-max)\n",
|
| 14 |
-
"- **Specialization**: Full-Stack React, Next.js 15, TypeScript, Tailwind CSS, Prisma,
|
| 15 |
]
|
| 16 |
},
|
| 17 |
{
|
|
@@ -27,7 +27,6 @@
|
|
| 27 |
"metadata": {},
|
| 28 |
"outputs": [],
|
| 29 |
"source": [
|
| 30 |
-
"# Install required libraries\n",
|
| 31 |
"!pip install -q transformers torch accelerate bitsandbytes huggingface_hub"
|
| 32 |
]
|
| 33 |
},
|
|
@@ -48,10 +47,8 @@
|
|
| 48 |
"from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextStreamer\n",
|
| 49 |
"\n",
|
| 50 |
"MODEL_ID = \"shawaz03/vibe-coder-7b-max\"\n",
|
|
|
|
| 51 |
"\n",
|
| 52 |
-
"print(f\"๐ Loading {MODEL_ID} in 4-bit NF4 for Google Colab...\")\n",
|
| 53 |
-
"\n",
|
| 54 |
-
"# 4-bit configuration (Fits smoothly in 5.2 GB VRAM on Colab T4)\n",
|
| 55 |
"bnb_config = BitsAndBytesConfig(\n",
|
| 56 |
" load_in_4bit=True,\n",
|
| 57 |
" bnb_4bit_quant_type=\"nf4\",\n",
|
|
@@ -69,14 +66,14 @@
|
|
| 69 |
"model.eval()\n",
|
| 70 |
"streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)\n",
|
| 71 |
"\n",
|
| 72 |
-
"print(\"\\nโ
VIBE CODER IS READY
|
| 73 |
]
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"cell_type": "markdown",
|
| 77 |
"metadata": {},
|
| 78 |
"source": [
|
| 79 |
-
"### 3.
|
| 80 |
]
|
| 81 |
},
|
| 82 |
{
|
|
@@ -85,14 +82,19 @@
|
|
| 85 |
"metadata": {},
|
| 86 |
"outputs": [],
|
| 87 |
"source": [
|
| 88 |
-
"# Vibe Coder System Prompt\n",
|
| 89 |
"VIBE_CODER_SYSTEM_PROMPT = \"\"\"You are Vibe Coder, a world-class principal full-stack software engineer and UI/UX designer.\n",
|
| 90 |
-
"ENGINEERING DIRECTIVES:\n",
|
| 91 |
-
"1.
|
| 92 |
-
"2.
|
| 93 |
-
"3.
|
|
|
|
|
|
|
| 94 |
"\n",
|
| 95 |
"def ask_vibe_coder(prompt_text, temperature=0.2, max_tokens=1500):\n",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 96 |
" messages = [\n",
|
| 97 |
" {\"role\": \"system\", \"content\": VIBE_CODER_SYSTEM_PROMPT},\n",
|
| 98 |
" {\"role\": \"user\", \"content\": prompt_text}\n",
|
|
@@ -102,7 +104,7 @@
|
|
| 102 |
" inputs = tokenizer(formatted_prompt, return_tensors=\"pt\").to(\"cuda\")\n",
|
| 103 |
" \n",
|
| 104 |
" print(\"=\" * 75)\n",
|
| 105 |
-
" print(f\"
|
| 106 |
" print(\"=\" * 75 + \"\\n\")\n",
|
| 107 |
" \n",
|
| 108 |
" with torch.no_grad():\n",
|
|
@@ -124,17 +126,34 @@
|
|
| 124 |
"cell_type": "markdown",
|
| 125 |
"metadata": {},
|
| 126 |
"source": [
|
| 127 |
-
"### 4.
|
|
|
|
| 128 |
]
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"cell_type": "code",
|
| 132 |
"execution_count": null,
|
| 133 |
-
"metadata": {
|
|
|
|
|
|
|
| 134 |
"outputs": [],
|
| 135 |
"source": [
|
| 136 |
-
"#
|
| 137 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 138 |
]
|
| 139 |
},
|
| 140 |
{
|
|
@@ -143,8 +162,12 @@
|
|
| 143 |
"metadata": {},
|
| 144 |
"outputs": [],
|
| 145 |
"source": [
|
| 146 |
-
"
|
| 147 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 148 |
]
|
| 149 |
}
|
| 150 |
],
|
|
|
|
| 4 |
"cell_type": "markdown",
|
| 5 |
"metadata": {},
|
| 6 |
"source": [
|
| 7 |
+
"# ๐ VIBE CODER v2.0 MAX โ Official Google Colab Studio\n",
|
| 8 |
"\n",
|
| 9 |
+
"[](https://colab.research.google.com/github/shawaz03/LLM/blob/main/vibe_coder_quickstart.ipynb)\n",
|
| 10 |
"\n",
|
| 11 |
+
"Run **Vibe Coder v2.0 MAX (7B)** on a **Free Google Colab T4 GPU** in 4-bit NF4 Quantization (5.2 GB VRAM, 0 memory errors).\n",
|
| 12 |
"\n",
|
| 13 |
+
"- **Hugging Face Model**: [`shawaz03/vibe-coder-7b-max`](https://huggingface.co/shawaz03/vibe-coder-7b-max)\n",
|
| 14 |
+
"- **Specialization**: Autonomous Full-Stack React 19, Next.js 15, TypeScript, Tailwind CSS, Prisma, and Anti-AI Aesthetic Directives."
|
| 15 |
]
|
| 16 |
},
|
| 17 |
{
|
|
|
|
| 27 |
"metadata": {},
|
| 28 |
"outputs": [],
|
| 29 |
"source": [
|
|
|
|
| 30 |
"!pip install -q transformers torch accelerate bitsandbytes huggingface_hub"
|
| 31 |
]
|
| 32 |
},
|
|
|
|
| 47 |
"from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextStreamer\n",
|
| 48 |
"\n",
|
| 49 |
"MODEL_ID = \"shawaz03/vibe-coder-7b-max\"\n",
|
| 50 |
+
"print(f\"๐ Loading {MODEL_ID} in 4-bit NF4...\")\n",
|
| 51 |
"\n",
|
|
|
|
|
|
|
|
|
|
| 52 |
"bnb_config = BitsAndBytesConfig(\n",
|
| 53 |
" load_in_4bit=True,\n",
|
| 54 |
" bnb_4bit_quant_type=\"nf4\",\n",
|
|
|
|
| 66 |
"model.eval()\n",
|
| 67 |
"streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)\n",
|
| 68 |
"\n",
|
| 69 |
+
"print(\"\\nโ
VIBE CODER IS READY!\")"
|
| 70 |
]
|
| 71 |
},
|
| 72 |
{
|
| 73 |
"cell_type": "markdown",
|
| 74 |
"metadata": {},
|
| 75 |
"source": [
|
| 76 |
+
"### 3. Vibe Coder Engine Definition"
|
| 77 |
]
|
| 78 |
},
|
| 79 |
{
|
|
|
|
| 82 |
"metadata": {},
|
| 83 |
"outputs": [],
|
| 84 |
"source": [
|
|
|
|
| 85 |
"VIBE_CODER_SYSTEM_PROMPT = \"\"\"You are Vibe Coder, a world-class principal full-stack software engineer and UI/UX designer.\n",
|
| 86 |
+
"ENGINEERING & CODING DIRECTIVES:\n",
|
| 87 |
+
"1. COMPLETE IMPLEMENTATIONS: Never output '// TODO', '/* implement later */', or incomplete stubs. Every component, hook, and route must be fully written.\n",
|
| 88 |
+
"2. NO ARTIFACT STRINGS: Never output template tags, variant numbers (e.g. 'Build Variant #...'), or internal directive texts.\n",
|
| 89 |
+
"3. FULL STATE & INTERACTION: Include real mock data arrays, working toggle logic, and complete TypeScript types.\n",
|
| 90 |
+
"4. MODERN DESIGN SYSTEM: Use Tailwind CSS with dark neutral palettes (bg-neutral-900, border-neutral-800), clean accents (cyan, emerald, violet), and Lucide React icons.\n",
|
| 91 |
+
"5. CLEAN OUTPUT: Output standard, clean TypeScript/React code with 'use client' when state is used.\"\"\"\n",
|
| 92 |
"\n",
|
| 93 |
"def ask_vibe_coder(prompt_text, temperature=0.2, max_tokens=1500):\n",
|
| 94 |
+
" if not prompt_text.strip():\n",
|
| 95 |
+
" print(\"โ ๏ธ Please enter a prompt in the box below.\")\n",
|
| 96 |
+
" return\n",
|
| 97 |
+
"\n",
|
| 98 |
" messages = [\n",
|
| 99 |
" {\"role\": \"system\", \"content\": VIBE_CODER_SYSTEM_PROMPT},\n",
|
| 100 |
" {\"role\": \"user\", \"content\": prompt_text}\n",
|
|
|
|
| 104 |
" inputs = tokenizer(formatted_prompt, return_tensors=\"pt\").to(\"cuda\")\n",
|
| 105 |
" \n",
|
| 106 |
" print(\"=\" * 75)\n",
|
| 107 |
+
" print(f\"๐ฌ USER PROMPT: {prompt_text}\")\n",
|
| 108 |
" print(\"=\" * 75 + \"\\n\")\n",
|
| 109 |
" \n",
|
| 110 |
" with torch.no_grad():\n",
|
|
|
|
| 126 |
"cell_type": "markdown",
|
| 127 |
"metadata": {},
|
| 128 |
"source": [
|
| 129 |
+
"### 4. ๐ฎ Dynamic Prompt Studio (Interactive Form Box)\n",
|
| 130 |
+
"Type your custom prompt into the box below and click the **Play (Run)** button:"
|
| 131 |
]
|
| 132 |
},
|
| 133 |
{
|
| 134 |
"cell_type": "code",
|
| 135 |
"execution_count": null,
|
| 136 |
+
"metadata": {
|
| 137 |
+
"cellView": "form"
|
| 138 |
+
},
|
| 139 |
"outputs": [],
|
| 140 |
"source": [
|
| 141 |
+
"# @title ๐ Vibe Coder Interactive Code Generator { vertical-output: true }\n",
|
| 142 |
+
"# @markdown Enter your custom prompt and configure generation settings:\n",
|
| 143 |
+
"\n",
|
| 144 |
+
"prompt = \"Build an interactive pricing matrix in React with Tailwind CSS, supporting monthly/annual billing toggle, 5 feature bullet checkmarks, and popular badge with zero placeholders.\" # @param {type:\"string\"}\n",
|
| 145 |
+
"temperature = 0.2 # @param {type:\"slider\", min:0.05, max:1.0, step:0.05}\n",
|
| 146 |
+
"max_tokens = 1500 # @param {type:\"slider\", min:256, max:3072, step:128}\n",
|
| 147 |
+
"\n",
|
| 148 |
+
"ask_vibe_coder(prompt, temperature=temperature, max_tokens=max_tokens)"
|
| 149 |
+
]
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"cell_type": "markdown",
|
| 153 |
+
"metadata": {},
|
| 154 |
+
"source": [
|
| 155 |
+
"### 5. ๐ฌ Continuous Live Chat Loop\n",
|
| 156 |
+
"Run this cell to chat and prompt continuously in real-time:"
|
| 157 |
]
|
| 158 |
},
|
| 159 |
{
|
|
|
|
| 162 |
"metadata": {},
|
| 163 |
"outputs": [],
|
| 164 |
"source": [
|
| 165 |
+
"while True:\n",
|
| 166 |
+
" user_query = input(\"\\n๐ Type any prompt (or 'exit' to quit): \")\n",
|
| 167 |
+
" if not user_query.strip() or user_query.lower() in [\"exit\", \"quit\"]:\n",
|
| 168 |
+
" print(\"Session stopped.\")\n",
|
| 169 |
+
" break\n",
|
| 170 |
+
" ask_vibe_coder(user_query, temperature=0.2)"
|
| 171 |
]
|
| 172 |
}
|
| 173 |
],
|