Downloads · 30 days
9
9% of all-time downloads
mistral-3b-sft-prompt-hack-merged
ozashu/mistral-3b-sft-prompt-hack-merged
mistral-3b-sft-prompt-hack-merged is a text generation model from ozashu. Use it when you need the model to write or continue text. It is set up for transformers.
Merged model (base + LoRA) from hackathon fine-tuning.
All-time downloads
98
Public
Parameters
3.8B
7.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.7 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- mistral3
- Access
- Public
- Created
- Mar 1, 2026
- Updated
- Mar 1, 2026
- SHA
- bf02fd1a
Try a prompt
Base models
Model card
From the Hugging Face model README
mistral-3b-sft-prompt-hack-merged
Merged model (base + LoRA) from hackathon fine-tuning.
Usage (Transformers)
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
repo = "ozashu/mistral-3b-sft-prompt-hack-merged"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype=torch.bfloat16, device_map="auto")
prompt = "こんにちは。自己紹介してください。"
inputs = tok(prompt, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=128)
print(tok.decode(out[0], skip_special_tokens=True))
- Task
- Text Generation
- Library
- transformers
- Type
- mistral3
- Created
- Mar 1, 2026
- Updated
- Mar 1, 2026