rahul7star/Qwen3.5-0.8B-Coder-Calude-Full

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.