smshahbaj/RIFA-FLASH-1.7B
11.3k
RIFA-FLASH
Created / maintained by [SM Shahbaj](https://huggingface.co/smshahbaj)
About
RIFA-FLASH is a higher-capacity fine-tuned model maintained by SM Shahbaj.
Part of the RIFA model family by SM Shahbaj.
Downloads
Recommended: Q5_K_M when available.
Quick start
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "smshahbaj/RIFA-FLASH-1.7B"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, device_map="auto")
messages = [{"role": "user", "content": "Hello"}]
text = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tok(text, return_tensors="pt").to(model.device)
print(tok.decode(model.generate(**inputs, max_new_tokens=64)[0], skip_special_tokens=True))Creator
SM Shahbaj — huggingface.co/smshahbaj
License: Apache 2.0
RIFA Model Family — SM Shahbaj
<!-- RIFA-DOCS-START -->
Documentation
- Series hub (GitHub): https://github.com/smshahbaj/RIFA-Text-Series
- Model page: RIFA-FLASH docs
- HF collection: https://huggingface.co/collections/smshahbaj/rifa-text-series <!-- RIFA-DOCS-END -->