Instructions to use SurgeFF/AriaV7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SurgeFF/AriaV7 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SurgeFF/AriaV7")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SurgeFF/AriaV7")
model = AutoModelForCausalLM.from_pretrained("SurgeFF/AriaV7", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SurgeFF/AriaV7 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SurgeFF/AriaV7"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SurgeFF/AriaV7",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SurgeFF/AriaV7

SGLang

How to use SurgeFF/AriaV7 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SurgeFF/AriaV7" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SurgeFF/AriaV7",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SurgeFF/AriaV7" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SurgeFF/AriaV7",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SurgeFF/AriaV7 with Docker Model Runner:
```
docker model run hf.co/SurgeFF/AriaV7
```

AriaV7 / README.md

SurgeFF

Update README.md

294d1a0 verified 17 days ago

preview code

Raw

History Blame Contribute Delete

2.75 kB

metadata

license: cc-by-nc-sa-4.0
base_model: Qwen/Qwen3-14B-Base
tags:
  - aria
  - mnemonicai
  - qwen3
  - text-generation
library_name: transformers
pipeline_tag: text-generation
language:
  - en

Aria V7.1

Aria is a 14B assistant built by Sergio Williams on Qwen3-14B-Base, developed as the core model for MnemonicAI. This repo's main holds V7.1, the current release. (V7.0 weights remain available in this repo's commit history.)

Benchmarks

100 held-out GSM8K-style math + 10 identity probes, identical raw plain-ChatML serving for all three (Intel Arc A770 / ollama):

Model	Math	Identity	Wall time
v5 (previous live)	46/100	0/10	695s
V7.0	69/100	8/10	837s
V7.1	71/100	8/10	514s

Honest read: +2 math over V7.0 is within noise on a 100-question set. The meaningful gains are the 38% latency reduction and a fully clean, verified training corpus. Against the previous live v5: +25 math points and 0→8 identity.

Training

Unsloth QLoRA on Qwen3-14B-Base, ~2.55 epochs, seq 2048, LoRA r32/α32
Target modules include lm_head + embed_tokens (see below), plain ChatML, response-only loss
17,522 verified examples, deduplicated: math 11,183 (answer-checked vs gold) · code 3,309 (execution-verified — every solution ran its own assert tests) · deep/ultra reasoning 1,206 · chat 937 · balancing 379 · multi-turn 250 · identity 205 · max-thinking 53
Teachers: kimi-k2.5/2.6/2.7-code, Claude Opus & Sonnet, Fable 5, deepseek-v4-pro
Dedup removed 501 duplicate prompts and 768 duplicate code solutions

The stop-token fix

Earlier versions rambled and never terminated. Two causes:

Serving with an injected empty <think>\n\n</think> block (enable_thinking=false) triggers non-stop generation.
More fundamentally: Qwen3-Base never emits <|im_end|> during pretraining, and attention/MLP-only LoRA can never surface that token — the output head must be trainable.

V7.1 fixes this structurally by putting lm_head+embed_tokens in the LoRA and leaving terminators unmasked in the loss. Result: a 5/5 clean-stop gate — every probe emits <|im_end|> and terminates.

Serving requirements (important)

Use the plain Qwen3 ChatML template. Never inject an empty <think> block / enable_thinking=false.
Stop tokens: <|im_end|> and <|endoftext|>.

<|im_start|>system
You are Aria, a helpful AI assistant created by Sergio Williams.<|im_end|>
<|im_start|>user
{message}<|im_end|>
<|im_start|>assistant

Known quirks

A rare stray non-English token can appear immediately before the stop token (cosmetic; trim app-side).

Base model licence: Qwen3-14B-Base, Apache-2.0.