QED-B1-Instruction-v1-300M

Model Description

QED-B1-Instruction-v1-300M is an instruction-tuned version of QED-Base-v1, a decoder-only Transformer language model trained entirely from scratch.

The underlying foundation model was pretrained using original model weights and an independently created dataset. QED-B1-Instruction-v1 further trains the base model on an original instruction-following dataset to improve its ability to understand prompts, follow instructions, answer questions, write text, generate code, and perform general assistant-style tasks.

No external pretrained model weights were used at any stage of development.


Model Details

Property Value
Model Name QED-B1-Instruction-v1-300M
Base Model Qarvexium/QED-Base-v1
Model Type Decoder-only Transformer
Parameters 299.82M
Hidden Dimension 1024
Layers 12
Attention Heads 16
Activation Function SwiGLU
Normalization RMSNorm
Position Encoding RoPE
Vocabulary Size 96,000
Tokenizer SentencePiece
Training Method Instruction Tuning

Architecture

QED-B1-Instruction-v1 retains the same architecture as QED-Base-v1, including:

  • Rotary Positional Embeddings (RoPE)
  • RMSNorm
  • SwiGLU feed-forward networks
  • Multi-head causal self-attention
  • Weight-tied token embeddings
  • Decoder-only Transformer architecture

Instruction tuning updates the model weights while preserving the original architecture.


Training Data

QED-B1-Instruction-v1 was instruction-tuned using a fully original dataset created specifically for this project.

The dataset was independently authored and includes a diverse collection of instruction-response pairs covering:

  • General knowledge
  • Reasoning
  • Coding
  • Mathematics
  • Writing
  • Summarization
  • Text transformation
  • Question answering
  • Conversation
  • Creative generation

The data creation process included:

  • Original prompt creation
  • Original responses
  • Custom formatting
  • Custom preprocessing
  • SentencePiece tokenization

No public instruction datasets or existing assistant conversations were used.


Intended Use

QED-B1-Instruction-v1 is intended for:

  • General-purpose AI assistants
  • Instruction following
  • Text generation
  • Code generation
  • Research
  • Fine-tuning
  • Educational projects
  • Experimentation

Limitations

Although instruction-tuned, QED-B1-Instruction-v1 has limitations:

  • It can still produce incorrect or fabricated information.
  • Responses may vary in quality depending on prompt complexity.
  • It has not undergone reinforcement learning from human feedback (RLHF).
  • It should not be relied upon for high-risk applications without human verification.

License

MIT License.

Downloads last month
109
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Qarvexium/QED-B1-Instruction-v1

Finetuned
(1)
this model
Finetunes
1 model