Parameter	Original	Tiny
num_hidden_layers	92	8
hidden_size	8192	1024
num_attention_heads	64	8
num_key_value_heads	4	2
head_dim	256	128
num_experts	512	16
num_experts_per_tok	10	2
moe_intermediate_size	2048	1024
shared_expert_intermediate_size	2048	1024
linear_key_head_dim	128	64
linear_num_key_heads	16	4
linear_num_value_heads	128	16
linear_value_head_dim	128	64
mtp_num_hidden_layers	1	0

Checkpoint Structure

Single safetensors file with packed expert format (experts.gate_up_proj, experts.down_proj) matching the original checkpoint structure. Layer types follow the [linear, linear, linear, full] x 2 pattern from the original.

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Qwen3.8-1.0B-A0.6B", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("Qwen3.8-1.0B-A0.6B")

input_ids = tokenizer("According to all known laws", return_tensors="pt").input_ids.to(model.device)
output = model.generate(input_ids, max_new_tokens=20)
print(tokenizer.decode(output[0]))

Creation Process

This model was created using the llm-compressor create-tiny-model claude skill.

Inspected the original 2.4T parameter MoE model configuration
Reduced all dimensions to create a ~1B parameter model while preserving the hybrid linear/full attention architecture
Fine-tuned on a toy dataset to achieve perplexity ~1.0
Converted checkpoint format to match the original (packed experts, correct tensor naming)
Validated model loading and generation

Notes

The model preserves the hybrid attention pattern: 6 linear attention layers and 2 full attention layers in a [linear, linear, linear, full] x 2 pattern
MTP (multi-token prediction) layers are removed (mtp_num_hidden_layers=0) as they are not needed for the tiny model
Expert weights use the packed format (gate_up_proj fused, stacked across experts) matching the original checkpoint

inference-optimization/Qwen3.8-1.0B-A0.6B

Qwen3.8-1.0B-A0.6B

Model Details

Configuration Changes

Checkpoint Structure

Usage

Creation Process

Notes

inference-optimization/
Qwen3.8-1.0B-A0.6B