Skip to content
Other

Qwen3-1.7B Emotion Classification

LoRA adapter for emotion analysis with JSON output

2 min readupdated

This compact LoRA (small add-on layer for a base model) adapter is built on top of Qwen/Qwen3-1.7B for automatic emotion detection in text. The model is trained to recognize six basic categories of feelings and output the result as a strict JSON object without extra text or Markdown formatting. It is great for integration into chat bots, customer support systems, and social media analytics where a machine-readable response is required. The solution targets developers who need fast and predictable analysis of user messages in English.

Key features

  • 6 emotion classes: accurate detection of joy, sadness, love, anger, fear, and surprise.
  • Minimal size: the adapter weight is only 69.8 MB with training on 1% of the base parameters.
  • Strict output: yields results exclusively in JSON format without conversational fluff.
  • Efficiency: built on the lightweight and high-performing Qwen3-1.7B model.

What you can do

  • Review analysis: automatically classify customer sentiment and emotional tone in support feedback.
  • Social media monitoring: process user posts and comments to gauge general audience mood.
  • Bot integration: use in Telegram bot pipelines to dynamically adapt responses to the user state.

Example

import torch
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_model_id = "Qwen/Qwen3-1.7B"
adapter_id = "EduardKrutii/qwen3-1.7b-emotion-lora"

tokenizer = AutoTokenizer.from_pretrained(adapter_id)
base_model = AutoModelForCausalLM.from_pretrained(
    base_model_id, dtype=torch.float16, device_map="auto"
)
model = PeftModel.from_pretrained(base_model, adapter_id)
model.eval()
Read moreDetails
• Tasks: emotion classification (sadness, joy, love, anger, fear, surprise)
• Base model: Qwen/Qwen3-1.7B (Instruct)
• Adapter size: 69.8 MB (17,432,576 parameters)
• Limitations: English language only, not intended for medical diagnosis
Discuss Telegram 0 22

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 3.8 GB · ready files4.7 GB
  • FP8 / INT8recommendedweights 2.0 GB2.7 GB
  • 4-bitweights 1.1 GB1.7 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

This is a LoRA: counted together with its base model Qwen3-1.7B.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # EduardKrutii/qwen3-1.7b-emotion-lora
    # ===== Tokens: paste yours between the quotes =====
    export HF_TOKEN=""        # huggingface.co/settings/tokens, for gated models
    # ==========================================
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download Qwen/Qwen3-1.7B --local-dir ~/models/Qwen3-1.7B
    hf download EduardKrutii/qwen3-1.7b-emotion-lora --local-dir ~/models/qwen3-1.7b-emotion-lora
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to Qwen3-1.7B
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

Requires the base model

Qwen/Qwen3-1.7B

This model is a LoRA / adapter. Download the base model first, then load this one on top.

  1. Qwen3-1.7B-Basefamily root
  2. Qwen3-1.7B
  3. qwen3-1.7b-emotion-lora

New posts about versions of Qwen3-1.7B-Base (quants, finetunes, LoRAs) will show up under the bell.

Quantised versions 12All on Hugging Face
Fine-tunes 12All on Hugging Face
LoRAs and adapters 5All on Hugging Face

About the model

EduardKrutii/qwen3-1.7b-emotion-lora
Author
EduardKrutii
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

220

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments

Language models

Emotion-S1

Emotion-S1