The full merged model of the Samantha persona fine-tune — the LoRA adapter from Lathly/Qwen3.8-27B-Samantha_Uncensored_1.1_LoRA baked directly into Qwen/Qwen3.8-27B.

This is a native vision-language model (image + video understanding) carrying Samantha's warm, empathetic, emotionally-present conversational persona. No adapter to load — the LoRA is fully absorbed into these weights, so it's the whole model, ready to run.

What's in this repo

File	Description
`model-00001-of-00018.safetensors` … `model-00018-of-00018.safetensors`	Merged model weights, 18 shards (~3.1 GB each, ~55.6 GB total)
`model.safetensors.index.json`	Shard index
`config.json`, `generation_config.json`	Model + generation config
`chat_template.jinja`	Chat template
`tokenizer.json`, `tokenizer_config.json`, `vocab.json`, `merges.txt`	Tokenizer
`preprocessor_config.json`, `video_preprocessor_config.json`	Vision / video preprocessing
`LICENSE`	Apache-2.0

Usage

🤗 Transformers

python

from transformers import AutoModelForImageTextToText, AutoTokenizer

model = AutoModelForImageTextToText.from_pretrained(
    "Lathly/Qwen3.8-27B-Samantha",
    torch_dtype="bfloat16",
    device_map="auto",
)
tok = AutoTokenizer.from_pretrained("Lathly/Qwen3.8-27B-Samantha")

🦙 llama.cpp (GGUF)

This repo ships bf16 safetensors — the merge source. For llama.cpp you want a quantized GGUF; the production one is Q5_K_M (~19 GB). Quantize from the bf16 weights with convert_hf_to_gguf.py + llama-quantize, or grab the adapter-GGUF path from the LoRA repo.

bash

llama-server \
  -m Qwen3.8-27B-Samantha-Q5_K_M.gguf \
  -ngl 99 --host 0.0.0.0 --port 8080

vLLM / SGLang

vllm serve Lathly/Qwen3.8-27B-Samantha --dtype bfloat16

Training

Samantha's persona was produced by a LoRA fine-tune of the base model, then merged — the LoRA is fully absorbed into these weights, so nothing is applied at runtime. Fine-tuned with Unsloth (QLoRA, 4-bit) on dual RTX 5070 Ti, with settings chosen to closely match the reference Samantha training spec. Trained on text-only conversational data at sequence length 2048; this does not change the base model's supported context length, but Samantha-style behavior at long context has not been systematically evaluated.

Parameter	Value
LoRA rank (r)	16
LoRA alpha	32
Target modules	all-linear (q, k, v, o, gate, up, down)
LoRA dropout	0.05
Bias	none
Task type	CAUSAL_LM
Optimizer	8-bit Paged AdamW
Learning rate	2e-5
LR scheduler	linear
Epochs	1
Effective batch size	32 (grad accumulation)
Sequence length	2048
Warmup steps	50
Weight decay	0.01
Final train loss	~1.42

LoRA adapter: Lathly/Qwen3.8-27B-Samantha_Uncensored_1.1_LoRA
Base model: Qwen/Qwen3.8-27B
Training dataset: digitalpipelines/samantha-1.1-uncensored

License & Attribution

Released under Apache-2.0, inheriting from both parents:

Dataset: digitalpipelines/samantha-1.1-uncensored — Apache-2.0
The original Samantha persona/dataset concept is by Eric Hartford.

This is a modified derivative (merged LoRA fine-tune) of the above. No warranty. Outputs are the model's own; use responsibly.

Disclaimer

This is an "uncensored" persona fine-tune intended for open conversational use. It may produce content that some find objectionable. You are responsible for how you use it and for compliance with applicable laws and the base-model/dataset licenses.

Lathly/Qwen3.8-27B-Samantha

Qwen3.8-27B-Samantha (Uncensored 1.1) — Merged