How to use from
Docker Model Runner
docker model run hf.co/prithivMLmods/Q3.5-9B-GLM-5.1-v2.0
Quick Links

1

Q3.5-9B-GLM-5.1-v2.0

Q3.5-9B-GLM-5.1-v2.0 is a reasoning-capable 9B-parameter language model built on top of Qwen/Qwen3.5-9B. The model was trained through a multi-stage training pipeline using approximately 1.5K long-context GLM-5.1 math and science reasoning traces, along with additional high-quality reasoning traces, to improve long-form reasoning, mathematical problem solving, scientific analysis, and instruction-following capabilities.

This model is an experimental release and may generate unexpected behaviors or reasoning artifacts in certain scenarios.

Key Highlights

  • Qwen 3.5 Foundation: Built directly on top of Qwen/Qwen3.5-9B.
  • Multi-Stage Training: Trained through multiple stages to progressively improve reasoning performance.
  • Long-Context Reasoning: Incorporates approximately 1.5K GLM-5.1 long-context reasoning traces covering mathematics, science, and complex 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 9B Deployment: Suitable for local inference and research environments.

Quick Start with Transformers

pip install transformers
pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model = AutoModelForCausalLM.from_pretrained(
    "prithivMLmods/Q3.5-9B-GLM-5.1-v2.0",
    torch_dtype="auto",
    device_map="auto"
)

tokenizer = AutoTokenizer.from_pretrained(
    "prithivMLmods/Q3.5-9B-GLM-5.1-v2.0"
)

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

Setting Value
Base Model Qwen/Qwen3.5-9B
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 Datasets Jackrong/GLM-5.1-Reasoning-1M-Cleaned and additional high-quality reasoning datasets

Model Files

Resource Link
Transformers Model prithivMLmods/Q3.5-9B-GLM-5.1-v2.0
GGUF (llama.cpp Quantizations) https://huggingface.co/prithivMLmods/Q3.5-9B-GLM-5.1-v2.0-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.
  • Instruction Following: Evaluating and improving instruction-following capabilities.
  • Local Deployment: Running efficient 9B 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 datasets used during training.

Acknowledgements

  • Qwen/Qwen3.5-9B: 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.

Downloads last month
33
Safetensors
Model size
9B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for prithivMLmods/Q3.5-9B-GLM-5.1-v2.0

Finetuned
Qwen/Qwen3.5-9B
Finetuned
(1,483)
this model
Quantizations
1 model

Dataset used to train prithivMLmods/Q3.5-9B-GLM-5.1-v2.0

Collection including prithivMLmods/Q3.5-9B-GLM-5.1-v2.0