Downloads · 30 days
27
33% of all-time downloads
ChatoyantAI/qwen3.5-9b-roleplay-sft-original50k-epoch1-lora
qwen3.5-9b-roleplay-sft-original50k-epoch1-lora is a text generation model from ChatoyantAI. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
This is the complete first-epoch LoRA checkpoint, step 3063, not standalone or merged model weights. Requires the official post-trained Qwen/Qwen3.5-9B, revision c202236235762e1c871ad0ccb60c8ee5ba337b9a. It is not the…
Downloads · 30 days
27
33% of all-time downloads
All-time downloads
82
Public
Repo size
366 MB
Likes
0
Public
Click a slice to open those files.
.safetensors346 MB · 95%
From the Hugging Face model README
This is the complete first-epoch LoRA checkpoint, step 3063, not standalone
or merged model weights. Requires the official post-trained Qwen/Qwen3.5-9B,
revision c202236235762e1c871ad0ccb60c8ee5ba337b9a. It is not the Base model or the later Lusy v4.0.1 dataset run.
import torch
from transformers import Qwen3_5ForConditionalGeneration, AutoTokenizer
from peft import PeftModel
adapter = "ChatoyantAI/qwen3.5-9b-roleplay-sft-original50k-epoch1-lora"
tokenizer = AutoTokenizer.from_pretrained(adapter)
base = Qwen3_5ForConditionalGeneration.from_pretrained(
"Qwen/Qwen3.5-9B", revision="c202236235762e1c871ad0ccb60c8ee5ba337b9a",
dtype=torch.bfloat16, device_map="auto",
)
model = PeftModel.from_pretrained(base, adapter).eval()
messages = [
{"role": "system", "content": "You are a cafe host."},
{"role": "assistant", "content": "Welcome to the cafe."},
{"role": "user", "content": "A table, please."},
]
text = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True, enable_thinking=False,
)
Use non-thinking mode, matching training; the empty thinking prefix is context, not a supervised reasoning target. Preserve system / Assistant greeting / user / Assistant history order where present. The 64K configured limit is not a guarantee of long-context accuracy. Multimodal behavior after SFT has not been evaluated.
The first-epoch independent archive and every recorded hash were verified. The adapter matches checkpoint-3063; all adapter tensors are finite. Saved optimizer and scheduler positions are 3063. A duplicate archival callback caused the runner to exit after the first successful archive and final validation; the verified first archive is the source of this release. No additional optimizer updates were needed or performed for publication.
The data includes roleplay and mature themes. Outputs can be inaccurate, biased, inappropriate or memorized; review before production use. No independent quality, safety, preference or general-capability improvement is claimed.
Only adapter weights, inference assets, licenses and public provenance are included.
Training examples, optimizer states, RNG states, raw logs and credentials are excluded.
See release-manifest.json, LICENSE, NOTICE, and BASE_MODEL_README.md.