prithivMLmods/Raptor-X3

Raptor X3

Raptor X3 is based on the Qwen 2.5 14B modality architecture, designed to enhance the reasoning capabilities of 14B-parameter models. This model is optimized for advanced coding reasoning and UI coding. It excels in contextual understanding, logical deduction, and multi-step problem-solving. Raptor X3 has been fine-tuned using a long chain-of-thought reasoning model and specialized datasets to improve comprehension, structured responses, and conversational intelligence.

Key improvements include:

1. Enhanced Coding Reasoning: Provides in-depth explanations and optimizations for complex coding problems, making it useful for developers and engineers.
2. Advanced UI Coding Support: Excels in generating and refining front-end code for web and mobile applications.
3. General-Purpose Coding: Capable of generating, debugging, and optimizing code across multiple programming languages, supporting software development and automation.
4. Long-Context Support: Supports up to 128K tokens for input context and can generate up to 8K tokens in a single output, making it ideal for detailed responses.
5. Multilingual Proficiency: Supports over 29 languages, including English, Chinese, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.

Prompt Style :

Make a dark-themed minimalist dashboard for an oil rig.

[HTML, CSS, and more if required].

Quickstart with transformers

Here is a code snippet with apply_chat_template to show you how to load the tokenizer and model and generate content:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "prithivMLmods/Raptor-X3"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How do I optimize React performance?"
messages = [
    {"role": "system", "content": "You are a helpful assistant capable of answering a wide range of questions."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

Intended Use

1. Coding Reasoning:
   Designed for providing explanations, optimizations, and best practices for coding problems.
2. UI Coding and Development:
   Excels in front-end development, including React, Vue, and other UI frameworks.
3. Programming and Software Development:
   Capable of generating, analyzing, and optimizing code in multiple programming languages.
4. Educational Assistance:
   Helps developers by providing coding tutorials, debugging assistance, and structured learning material.
5. Multilingual Applications:
   Supports global communication, translations, and multilingual content generation.
6. Long-Form Content Generation:
   Can generate extended responses, including documentation, technical reports, and coding guides.

Limitations

1. Hardware Requirements:
   Requires high-memory GPUs or TPUs due to its large parameter size and long-context support.
2. Potential Bias in Responses:
   While designed to be neutral, outputs may still reflect biases present in training data.
3. Complexity in Some Advanced Topics:
   While proficient in general coding, highly specialized fields may require verification.
4. Limited Real-World Awareness:
   Does not have access to real-time events beyond its training cutoff.
5. Error Propagation in Extended Outputs:
   Minor errors in early responses may affect overall coherence in long-form outputs.
6. Prompt Sensitivity:
   The effectiveness of responses may depend on how well the input prompt is structured.