Instructions to use anonym5035/ablation_6_no_global_attn with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anonym5035/ablation_6_no_global_attn with Transformers:

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

pipe = pipeline("text-generation", model="anonym5035/ablation_6_no_global_attn", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("anonym5035/ablation_6_no_global_attn", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use anonym5035/ablation_6_no_global_attn with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anonym5035/ablation_6_no_global_attn"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anonym5035/ablation_6_no_global_attn",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/anonym5035/ablation_6_no_global_attn

SGLang

How to use anonym5035/ablation_6_no_global_attn 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 "anonym5035/ablation_6_no_global_attn" \
    --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": "anonym5035/ablation_6_no_global_attn",
		"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 "anonym5035/ablation_6_no_global_attn" \
        --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": "anonym5035/ablation_6_no_global_attn",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use anonym5035/ablation_6_no_global_attn with Docker Model Runner:
```
docker model run hf.co/anonym5035/ablation_6_no_global_attn
```

XpertGPT (SwiGLU & Sliding Window 64, 16, 8, 4)

XpertGPT is a sparse Mixture of Experts (MoE) language model designed for data-efficient pretraining under the BabyLM 2026 challenge (Strict-Small 10M track). It leverages Parallelized Multi-Scale Information Transmission (MSIT) and Expert Choice Routing to maximize representational capacity within restricted token budgets.

This version implements SwiGLU Feed-Forward Networks across all global and parallel expert blocks, along with corrected LayerNorms, redundant residual removal, and sliding window attention sizes of [64, 16, 8, 4] tokens.

1. SwiGLU Feed-Forward Networks (FFN)

Instead of the standard Feed-Forward sequential structure (Linear -> GELU -> Linear), this model replaces FFN layers with the SwiGLU (Swish Gated Linear Unit) variant to improve model capacity and training stability:

$\text{FFN}_{\text{SwiGLU}}(x) = \left(\text{Swish}(x W) \otimes x V\right) W_2$

Where the Swish function is implemented using SiLU:

Gate Linear projections ($W$, $V$): Projects input dimension dim to hidden_dim.
Out Linear projection ($W_2$): Projects back to dim.
To maintain parameter counts equivalent to standard dim * 4 sequential FFNs, the hidden dimension is scaled to: $$\text{hidden_dim} = \text{round_to_multiple_of_8}\left(\frac{8}{3} \times \text{dim}\right)$$

2. Expert Sliding Window Layout

The four parallel MoE experts are configured with distinct sliding window attention constraints:

Expert 1: Window size 64 tokens
Expert 2: Window size 16 tokens
Expert 3: Window size 8 tokens
Expert 4: Window size 4 tokens

3. Architectural Layout & Changes

This model implements:

Removal of Redundant Residual (res3):
- Removed redundant residual connection around the global dense block. Gated input is now simply $X_2 = X_1$.
Introduction of Post-Block LayerNorm (ln3):
- LayerNorm ln3 is added after the SwiGLU addition inside every MSITBranchBlock.
- Formulation: $X_{\text{out}} = \text{LayerNorm}(X^{(2)})$.
Introduction of Post-MoE LayerNorm (ln_post_moe):
- LayerNorm ln_post_moe is added after the Residual 4 MoE aggregation.
- Formulation: $X_{\text{out}} = \text{LayerNorm}(X_2 + X_{3, \text{full}})$.

4. How to Load and Use Checkpoints (Bypass Retraining)

A. Loading the Final Model (`main` branch)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "SRJ5035/sw_glu_sw_64_16_8_4_xpert_gpt",
    revision="main",
    trust_remote_code=True
).eval()

tokenizer = AutoTokenizer.from_pretrained(
    "SRJ5035/sw_glu_sw_64_16_8_4_xpert_gpt",
    revision="main"
)

B. Loading an Intermediate Milestone (e.g. `chck_5M`)

model_5m = AutoModelForCausalLM.from_pretrained(
    "SRJ5035/sw_glu_sw_64_16_8_4_xpert_gpt",
    revision="chck_5M",
    trust_remote_code=True
).eval()

Downloads last month: -; Downloads are not tracked for this model. How to track