prithivMLmods

Q3.5-4B-OpusGLM-MAX-0731-ablated

Deploy Dedicated

README

License: apache-2.0

Key Highlights

Qwen 3.5 Foundation: Built directly on top of Qwen/Qwen3.5-4B.
Multi-Stage Training: Trained through multiple stages to progressively improve reasoning performance.
General Purpose Reasoning: Trained using General Purpose GLM and Opus reasoning traces spanning mathematics, science, coding, and analytical tasks.
General Reasoning Enhancement: Further trained on additional high-quality reasoning traces to strengthen instruction following and multi-step reasoning.
Research-Focused Release: Designed for reasoning research, experimentation, and evaluation.
Efficient 4B Deployment: Suitable for local inference and research environments.

Quick Start with Transformers

bash

pip install transformerspip install accelerate

python

from transformers import AutoTokenizer, AutoModelForCausalLMimport torch model = AutoModelForCausalLM.from_pretrained(    "prithivMLmods/Q3.5-4B-OpusGLM-MAX-0731-ablated",    torch_dtype="auto",    device_map="auto") tokenizer = AutoTokenizer.from_pretrained(    "prithivMLmods/Q3.5-4B-OpusGLM-MAX-0731-ablated") messages = [    {        "role": "user",        "content": "Explain how a transformer model processes text."    }] inputs = tokenizer.apply_chat_template(    messages,    tokenize=True,    add_generation_prompt=True,    return_tensors="pt").to(model.device) outputs = model.generate(    inputs,    max_new_tokens=512) print(    tokenizer.decode(        outputs[0][inputs.shape[-1]:],        skip_special_tokens=True    ))

Training Details

Table with columns: Setting, Value
Setting	Value
Base Model	Qwen/Qwen3.5-4B
Training Method	Multi-stage Supervised Fine-Tuning (SFT)
Maximum Sequence Length	32,768 tokens (Long Context)
Training Precision	BF16 (Full Precision)
Training & Alignment Framework	TRL
Training Data	General Purpose GLM reasoning traces, Opus reasoning traces, and additional high-quality reasoning datasets

Model Files

Table with columns: Resource, Link
Resource	Link
Transformers Model	`prithivMLmods/Q3.5-4B-OpusGLM-MAX-0731-ablated`
GGUF (llama.cpp Quantizations)	`prithivMLmods/Q3.5-4B-OpusGLM-MAX-0731-ablated-GGUF`

Intended Use

Reasoning Research: Studying long-context reasoning and multi-stage training techniques.
Mathematical Reasoning: Solving complex mathematical problems with multi-step reasoning.
Scientific Reasoning: Performing structured scientific analysis and problem solving.
Coding Assistance: Assisting with code generation, debugging, and technical reasoning.
Instruction Following: Evaluating and improving instruction-following capabilities.
Local Deployment: Running efficient 4B reasoning models in research and experimentation environments.

Limitations

Experimental Model: Behavior may differ from the base model in certain scenarios.
Reasoning Artifacts: Complex reasoning chains may occasionally produce incorrect intermediate steps or conclusions.
Training Biases: Performance reflects the characteristics and coverage of the reasoning data used during training.

Acknowledgements

Qwen/Qwen3.5-4B: Base model used for this project.
TRL - Transformers Reinforcement Learning: TRL is a full stack library providing tools to train transformer language models with methods including Supervised Fine-Tuning (SFT), Group Relative Policy Optimization (GRPO), Direct Preference Optimization (DPO), Reward Modeling, and more.
Transformers: Transformers provides state-of-the-art machine learning models for text, computer vision, audio, video, and multimodal tasks, supporting both inference and training.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

prithivMLmods

Model Tree

Base

Qwen/Qwen3.5-4B

Fine-tuned

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality