Instructions to use MaxChess/qwen2.5-7b-nla-affect-ar with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MaxChess/qwen2.5-7b-nla-affect-ar with Transformers:

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

pipe = pipeline("text-generation", model="MaxChess/qwen2.5-7b-nla-affect-ar")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaxChess/qwen2.5-7b-nla-affect-ar")
model = AutoModelForCausalLM.from_pretrained("MaxChess/qwen2.5-7b-nla-affect-ar", 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 MaxChess/qwen2.5-7b-nla-affect-ar with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MaxChess/qwen2.5-7b-nla-affect-ar"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MaxChess/qwen2.5-7b-nla-affect-ar",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MaxChess/qwen2.5-7b-nla-affect-ar

SGLang

How to use MaxChess/qwen2.5-7b-nla-affect-ar 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 "MaxChess/qwen2.5-7b-nla-affect-ar" \
    --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": "MaxChess/qwen2.5-7b-nla-affect-ar",
		"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 "MaxChess/qwen2.5-7b-nla-affect-ar" \
        --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": "MaxChess/qwen2.5-7b-nla-affect-ar",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MaxChess/qwen2.5-7b-nla-affect-ar with Docker Model Runner:
```
docker model run hf.co/MaxChess/qwen2.5-7b-nla-affect-ar
```

MaxChess commited on Aug 1

Commit

045ef73

verified ·

1 Parent(s): a2c0622

Initialize private AR card

Browse files

Files changed (1) hide show

README.md +39 -0

README.md ADDED Viewed

	@@ -0,0 +1,39 @@

+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+datasets:
+- MaxChess/nla-affect-10k
+library_name: transformers
+license: apache-2.0
+tags:
+- natural-language-autoencoder
+- activation-reconstructor
+- interpretability
+- affect
+---
+# Qwen2.5-7B NLA Affect AR
+Experimental activation reconstructor (AR): explanation text to a 3,584-dimensional
+Qwen2.5-7B-Instruct layer-20 activation direction. The backbone is truncated to 21
+transformer blocks and uses a separately saved `value_head.safetensors`.
+## Evaluation on 200 AR-held-out teacher explanations
+- Directional FVE: 0.34277.
+- Bootstrap 95% CI: [0.30129, 0.37560].
+- Mean cosine similarity: 0.76460.
+- Shuffled FVE: -0.77740.
+Targets and predictions are independently L2-normalized. FVE is
+`1 - mean(||h-h_hat||^2) / mean(||h-mean(h)||^2)` on normalized directions.
+## Training
+- 5,000 examples, one epoch, 209 optimizer steps.
+- Direction-only normalized MSE, scale `sqrt(3584)`.
+- Effective global batch: 24 on three V100-32GB GPUs.
+- PyTorch SDPA.
+This AR score measures reconstruction from teacher explanations. The current full
+AV -> AR cycle is substantially weaker (FVE 0.03765), indicating that AV is the main
+bottleneck. See `MaxChess/nla-affect-10k` for exact splits and source code.