Downloads · 30 days
0
sft-14b-v1
basab1142/sft-14b-v1
sft-14b-v1 is a machine learning model from basab1142. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Persona-conditioned survey response model fine-tuned on SocSci210 via QLoRA. Given a demographic persona (age, gender, education, ideology, etc.) and a survey question, the model outputs a <think chain-of-thought grou…
Access
Public
Updated May 28, 2026
Repo size
3.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.1 GB · 99%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- May 28, 2026
- Updated
- May 28, 2026
- SHA
- 2427d9da
Base models
Model card
From the Hugging Face model README
sft-14b-v1
Persona-conditioned survey response model fine-tuned on SocSci210 via QLoRA.
Given a demographic persona (age, gender, education, ideology, etc.) and a survey question,
the model outputs a <think> chain-of-thought grounded in the persona's attributes,
followed by a structured JSON response.
Output format
<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
| Setting | Value |
|---|---|
| Base model | Qwen/Qwen2.5-14B-Instruct |
| Training data | SocSci210 6k (fixed) |
| Method | QLoRA 4-bit, NF4, double quant |
| LoRA r / alpha | 64 / 128 |
| LoRA targets | q_proj, v_proj, k_proj, o_proj, gate_proj, up_proj, down_proj |
| Effective batch | 64 (8 × 8 grad accum) |
| Epochs | 2 |
| Learning rate | 0.0002 (cosine schedule) |
| Max seq length | 2048 |
| Training time | 1.21 hrs |
| Training cost | $1.69 |
| Resumed from | basab1142/sft-14b-v1 |
Usage
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")
- License
- apache-2.0
- Languages
- en
- Created
- May 28, 2026
- Updated
- May 28, 2026