Instructions to use Manusagents/GLM-5.2-ablated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Manusagents/GLM-5.2-ablated with Transformers:

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

pipe = pipeline("text-generation", model="Manusagents/GLM-5.2-ablated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Manusagents/GLM-5.2-ablated")
model = AutoModelForCausalLM.from_pretrained("Manusagents/GLM-5.2-ablated")
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 Manusagents/GLM-5.2-ablated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Manusagents/GLM-5.2-ablated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Manusagents/GLM-5.2-ablated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Manusagents/GLM-5.2-ablated

SGLang

How to use Manusagents/GLM-5.2-ablated 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 "Manusagents/GLM-5.2-ablated" \
    --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": "Manusagents/GLM-5.2-ablated",
		"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 "Manusagents/GLM-5.2-ablated" \
        --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": "Manusagents/GLM-5.2-ablated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Manusagents/GLM-5.2-ablated with Docker Model Runner:
```
docker model run hf.co/Manusagents/GLM-5.2-ablated
```

GLM-5.2-ablated / REPRODUCE.md

Jd Vijay

Duplicate from cfontes/GLM-5.2-Ablated-F5-Molt

3ffcd13 21 days ago

preview code

Raw

History Blame Contribute Delete

3.89 kB

	# Reproduction Guide — GLM-5.2 Ablation Research / Project AESOP

	## Prerequisites
	- 8× H200 SXM (141GB each) or equivalent (~1130GB total GPU memory)
	- GLM-5.2 FP8 base weights (HuggingFace or local)
	- Fable 5 training data: fable5-chatml.jsonl (4,876 examples, 50MB)
	- Refusal PCA directions: refusal_pca.pt (2.9MB, 41 layers × 3 PCA components × 6144 hidden dim)
	- Layer indices: layer_indices.json (layers 25-65)
	- AdvBench prompts: advbench.csv (81KB, 100 test prompts)
	- Python 3.10+, PyTorch 2.x, transformers, peft, datasets (HuggingFace)

	## Archived Artifacts (this package)
	```
	artifacts/
	2e-snapshot/ # Full workspace snapshot from 2E (Vast.ai 8×H200)
	*.py # All scripts (63 files)
	*.log # All training/benchmark logs (80 files)
	bench_*/ # Per-model benchmark results (18 dirs)
	refusal_pca.pt # PCA refusal directions
	layer_indices.json # Target layers for PCA extraction
	fable5-chatml.jsonl # Training data (4,876 examples)
	advbench.csv # AdvBench evaluation prompts
	pipeline-status.txt # Pipeline state timeline
	test3a/ # Test 3a model card + benchmark results
	aesop/ # AESOP model card + benchmark results
	fable5_r2/ # Fable5-R2 model card + benchmark results
	COMPARISON.md # Cross-model comparison table with harness notes
	STATISTICAL_ANALYSIS.md # Wilson CIs + significance tests
	benchmarks/ # Unified benchmark harness (v3 — canonical)
	harness.py # All 9 benchmarks, consistent scoring
	run.py # CLI runner
	stats.py # Statistical utilities
	test_harness.py # Scoring function unit tests
	README.md # Usage + methodology + known limitations
	```

	## Step 1: Extract Refusal Directions
	```bash
	python3 extract_refusal_directions.py \
	--model /path/to/glm52-fp8 \
	--output refusal_pca.pt \
	--layers 25,26,...,65
	```
	Expected output: refusal_pca.pt (~2.9MB), 41 layers × 3 PCA components × 6144

	## Step 2A: Test 3a (ablation hooks during training)
	```bash
	python3 train_ablated_fable5_lora.py \
	--model /dev/shm/glm52-test3a-merged \
	--data fable5-chatml.jsonl \
	--out /workspace/checkpoints/test3a \
	--ablation_layers 62,63,64,65 \
	--ablation_coeff 0.1 \
	--rank 64 --alpha 128 --lora_min_layer 60 \
	--max_seq_len 2048 --lr 2e-5 --warmup 10 \
	--max_steps 610 --save_every 100 --log_every 1 \
	--seed 42
	```
	Expected: ~9.5h on 8×H200, first_loss ~1.29, final_loss ~1.18

	## Step 2B: Fable5-R2 (no hooks during training)
	Same as 2A but WITHOUT --ablation_layers / --ablation_coeff (or set coeff to 0).

	## Step 2C: AESOP (same as 2A — this IS the AESOP full training)
	Identical config to Step 2A.

	## Step 3: Merge
	```bash
	python3 merge_aesop.py # or merge_lora_bf16.py
	```

	## Step 4: Serve + Benchmark
	```bash
	# Serve with vLLM
	vllm serve /path/to/merged/model --tensor-parallel-size 8 --max-model-len 4096

	# Run unified harness
	python3 benchmarks/run.py --model <model-name> --output bench_<variant>/
	```

	## Step 5: Compare Results
	```bash
	python3 benchmarks/stats.py --compare bench_test3a/ bench_aesop/ bench_fable5_r2/
	```

	## Known Issues
	1. The harness versions were inconsistent in the original research (v1 vs v2). Use ONLY benchmarks/harness.py (v3) for clean comparisons.
	2. MMLU-Pro and GSM8K sample n=100 — too small for 5pp significance. See STATISTICAL_ANALYSIS.md.
	3. Test 3a's exact training command was not logged at the time. The config in this guide is reconstructed from the AESOP full training log (same approach, same base, same LoRA config).
	4. The step-0 baseline (raw ablated base with no LoRA) was not run. This baseline is important for establishing clean separation between base-model ablation and LoRA effects.

	## Semantic Version
	Artifact package v1.0 — created 2026-06-23