Uploaded model

  • Developed by: Kanompung
  • License: apache-2.0
  • Finetuned from model : Tsunami-th/Tsunami-1.0-14B-Instruct

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

from transformers import AutoTokenizer, AutoModel
import torch

tokenizer = AutoTokenizer.from_pretrained("Kanompung/Tsunami_llm_embed")
model     = AutoModel.from_pretrained("Kanompung/Tsunami_llm_embed")

texts = ["สวัสดีครับ", "วันนี้อากาศดี"]
enc = tokenizer(texts, padding=True, truncation=True, return_tensors="pt")
with torch.no_grad():
    out = model(**enc)

embeds = out.last_hidden_state.mean(dim=1)
print(embeds.shape)
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Kanompung/tsuname_llm_embed

Base model

Qwen/Qwen2.5-14B
Finetuned
(6)
this model