Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more
Container

Run this model inference with full control and performance in your environment.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

README

License: apache-2.0

Output format

markdown

<think>
[3-5 sentences of persona-grounded reasoning]
</think>
{"choice": "A", "confidence": 0.82, "reasoning": "one sentence"}

choice is always A (Disagree/No), B (Mixed/Neutral), or C (Agree/Yes).

Training details

SettingValue
Base modelQwen/Qwen2.5-14B-Instruct
Training dataSocSci210 6k (fixed)
MethodQLoRA 4-bit, NF4, double quant
LoRA r / alpha64 / 128
LoRA targetsq_proj, v_proj, k_proj, o_proj, gate_proj, up_proj, down_proj
Effective batch64 (8 × 8 grad accum)
Epochs2
Learning rate0.0002 (cosine schedule)
Max seq length2048
Training time1.21 hrs
Training cost$1.69
Resumed frombasab1142/sft-14b-v1

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
from peft import PeftModel
import torch
base = AutoModelForCausalLM.from_pretrained(
"Qwen/Qwen2.5-14B-Instruct",
quantization_config=BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16),
device_map="auto",
)
model = PeftModel.from_pretrained(base, "basab1142/sft-14b-v1")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-14B-Instruct")

Model provider

basab1142

basab1142

Model tree

Base

Qwen/Qwen2.5-14B-Instruct

Adapter

this model

Modalities

Input

Text

Output

Text

Pricing

Dedicated Endpoints

View details

Supported Functionality

Model APIs

Dedicated Endpoints

Container

More information

Explore FriendliAI today