DEMO
https://huggingface.co/spaces/rahul7star/claude-Qwen
Implemenation
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="rahul7star/Qwen3.5-0.8B-Coder-Calude-Full")
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
{"type": "text", "text": "What animal is on the candy?"}
]
},
]
pipe(text=messages)
## CODE ##
write a python code to show llm and pytorch use case
# Example 1: Basic LLM usage
from langchain import chat
# Create a simple chat model
chat_model = chat.ChatModel.from_chain_model("gpt-3.5-turbo")
# Create a conversation
messages = [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Can you calculate the area of a circle with radius 5?"
}
]
# Generate response
response = chat_model(messages)
print(f"Response: {response}")
## another sample
from transformers import pipeline
pipe = pipeline("text-generation", model="rahul7star/Qwen3.5-0.8B-Coder-Calude-Full")
messages = [
{"role": "user", "content": "write a python code for neural network"},
]
pipe(messages)
-------
output----
[{'generated_text': [{'role': 'user',
'content': 'write a python code for neural network'},
{'role': 'assistant',
'content': "Here's a beginner-friendly PyTorch neural network example that builds a simple feedforward neural network with multiple layers.\n\n# Neural Network with PyTorch\n\n```python\nimport torch\nimport torch.nn as nn\nfrom torch.utils.data import DataLoader\nfrom torch.optim.lr_scheduler import StepLR\nfrom torch.utils.data import TensorDataset, Subset\n\n# === Create the Neural Network ===\n\nclass NeuralNetwork(nn.Module):\n def __init__(self, input_size, hidden_sizes, output_size):\n super(NeuralNetwork, self).__init__()\n \n # Input layer\n self.input = nn.Linear(input_size, hidden_sizes)\n \n # Hidden layers\n for i in range(1, hidden_sizes):\n self.hidden_layer_i = nn.Linear(hidden_sizes, hidden_sizes)\n \n # Output layer\n self.output = nn.Linear(hidden_sizes, output_size)\n \n def forward(self, x):\n # Apply all linear layers\n x = self.input(x)\n for i in range(1, len(self.hidden_layer)):\n x = self.hidden_layer_i[i](x)\n x = self.output(x)\n return x\n\n# === Create Training Data ===\n\ndef create"}]}]
Uploaded finetuned model
- Developed by: rahul7star
- License: apache-2.0
- Finetuned from model : Qwen/Qwen3.5-0.8B
This qwen3_5 model was trained 2x faster with Unsloth and Huggingface's TRL library.