ShenLab/MentalChat16K
Viewer • Updated • 16.1k • 1.15k • 56
How to use zhenikk/LFM2.5-350M-MentalChat16K with Transformers.js:
// npm i @huggingface/transformers
import { pipeline } from '@huggingface/transformers';
// Allocate pipeline
const pipe = await pipeline('text-generation', 'zhenikk/LFM2.5-350M-MentalChat16K');How to use zhenikk/LFM2.5-350M-MentalChat16K with Unsloth Studio:
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for zhenikk/LFM2.5-350M-MentalChat16K to start chatting
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for zhenikk/LFM2.5-350M-MentalChat16K to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for zhenikk/LFM2.5-350M-MentalChat16K to start chatting
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="zhenikk/LFM2.5-350M-MentalChat16K",
max_seq_length=2048,
)This repository contains an ONNX Q4 export of a fine-tuned version of LiquidAI/LFM2.5-350M.
The model was fine-tuned on ShenLab/MentalChat16K for supportive mental-health-style dialogue.
This repository is intended for experimentation with browser-side and ONNX-based inference.
The repository contains the unpacked ONNX export, not a ZIP archive.
Expected structure:
config.json
generation_config.json
tokenizer.json
tokenizer_config.json
chat_template.jinja
onnx/model_q4.onnx
onnx/model_q4.onnx_data