Support embedding model gte-Qwen1.5-7B-instruct (#2190)

* Support embedding model gte-Qwen1.5-7B-instruct

This is a text embedding model based on Qwen2. They share same
model architecture except the last MLP module. This commit brings in
minimal modification of the old Qwen2 implementation to support both
models.

An example is provided, and had been verified according to the official
PyTorch implementation.

* Avoid doing the 'last-token filtering' based on the absence of attention mask.

---------

Co-authored-by: Laurent <laurent.mazare@gmail.com>

candle-examples/examples/qwen/main.rs

@@ -7,7 +7,7 @@ extern crate accelerate_src;
 use anyhow::{Error as E, Result};
 use clap::Parser;
 
-use candle_transformers::models::qwen2::{Config as ConfigBase, Model as ModelBase};
+use candle_transformers::models::qwen2::{Config as ConfigBase, ModelForCausalLM as ModelBase};
 use candle_transformers::models::qwen2_moe::{Config as ConfigMoe, Model as ModelMoe};
 
 use candle::{DType, Device, Tensor};