Instructions to use BananaMind/normal-model-ablation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BananaMind/normal-model-ablation with Transformers:

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

pipe = pipeline("text-generation", model="BananaMind/normal-model-ablation", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("BananaMind/normal-model-ablation", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BananaMind/normal-model-ablation with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BananaMind/normal-model-ablation"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BananaMind/normal-model-ablation",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BananaMind/normal-model-ablation

SGLang

How to use BananaMind/normal-model-ablation 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 "BananaMind/normal-model-ablation" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BananaMind/normal-model-ablation",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "BananaMind/normal-model-ablation" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BananaMind/normal-model-ablation",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BananaMind/normal-model-ablation with Docker Model Runner:
```
docker model run hf.co/BananaMind/normal-model-ablation
```

Standard attention ablation model (1.50M params, 3072 context)

Part of a controlled ablation: BananaMind/dsa-model-ablation (DSA) vs BananaMind/normal-model-ablation (standard attention). Same seed, data order, tokenizer, architecture and hyper-parameters. Only the attention differs.

Attention: Standard dense causal multi-head attention.
Architecture: 5 layers, hidden 128, 4 heads, SwiGLU 336, RoPE, RMSNorm, tied embeddings, vocab 4096 (custom BPE)
Context length: 3072
Params: 1,498,496
Data: HuggingFaceFW/fineweb-edu (sample-10BT), 2000M tokens, 1 epoch, seed 1337
Optimiser: AdamW lr 0.002 (cosine), batch 16x3072 tokens, bf16 autocast

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "BananaMind/normal-model-ablation"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, trust_remote_code=True)

(No KV cache is implemented; generate recomputes the full sequence each step.)

Benchmarks (0-shot, lm-evaluation-harness; acc / acc_norm where available)

Model	Params	Val loss	Val ppl	piqa	hellaswag	arc_easy	arc_challenge
DSA	1,530,496	3.4150	30.42	54.90 / 53.05	26.84 / 26.72	30.18 / 31.02	16.98 / 20.73
Standard	1,498,496	3.4248	30.72	53.81 / 53.75	26.86 / 26.75	30.68 / 31.44	17.83 / 20.99

Per-model raw results: benchmarks/results.json. Comparison with the other model: benchmarks/comparison.md (other repo: BananaMind/dsa-model-ablation). Training curve: train_log.json.

Note: at this size models are close to chance on these benchmarks, and the benchmark prompts are shorter than the top-k (512), where DSA selects every token and behaves identically to dense attention at inference, so differences mostly reflect how training differed.

Downloads last month: 328

Safetensors

Model size

1.5M params

Tensor type

F32