Instructions to use Davd-b01/qwen-3.8-next-40b-exp-moe-healed-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Davd-b01/qwen-3.8-next-40b-exp-moe-healed-bf16 with Transformers:

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

pipe = pipeline("text-generation", model="Davd-b01/qwen-3.8-next-40b-exp-moe-healed-bf16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Davd-b01/qwen-3.8-next-40b-exp-moe-healed-bf16")
model = AutoModelForCausalLM.from_pretrained("Davd-b01/qwen-3.8-next-40b-exp-moe-healed-bf16", 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 Davd-b01/qwen-3.8-next-40b-exp-moe-healed-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Davd-b01/qwen-3.8-next-40b-exp-moe-healed-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Davd-b01/qwen-3.8-next-40b-exp-moe-healed-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Davd-b01/qwen-3.8-next-40b-exp-moe-healed-bf16

SGLang

How to use Davd-b01/qwen-3.8-next-40b-exp-moe-healed-bf16 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 "Davd-b01/qwen-3.8-next-40b-exp-moe-healed-bf16" \
    --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": "Davd-b01/qwen-3.8-next-40b-exp-moe-healed-bf16",
		"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 "Davd-b01/qwen-3.8-next-40b-exp-moe-healed-bf16" \
        --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": "Davd-b01/qwen-3.8-next-40b-exp-moe-healed-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Davd-b01/qwen-3.8-next-40b-exp-moe-healed-bf16 with Docker Model Runner:
```
docker model run hf.co/Davd-b01/qwen-3.8-next-40b-exp-moe-healed-bf16
```

⚠️ EXPERIMENTAL WEIGHTS — NOT A FINAL RELEASE ⚠️

THESE ARE EXPERIMENTAL RESEARCH WEIGHTS. THIS IS NOT A FINISHED OR PRODUCTION MODEL.

Every qwen-3.8-next-40b-exp-* repository is an intermediate checkpoint of an ongoing weight-surgery research line — not a release, not a final version, not a validated product.

Not validated for end-user deployment, standalone inference, or any downstream product.

No safety, alignment, or quality guarantees. Behaviour can change or regress between checkpoints.

Non-standard architecture (qwen4_exp): requires an inference stack that explicitly supports it.

Published only for reproducibility of MoE pruning, router-healing, PLE-calibration and distillation experiments.

If you are looking for a model to actually use, use the upstream Qwen release instead.

Qwen-3.8-Next-40B-MoE-Healed (BF16)

Full BFloat16 weights of the experimental hybrid model Qwen-3.8-Next-40B after memory-pruning surgery and a routing-stabilization run (router healing) over the 48 MoE gates $W_{\text{gate}}$, with the PLE associative memory table pruned to 2.0M entries.

1. Diagnosis of the pruned base

The pruned base checkpoint showed expert starvation and routing collapse:

Routing imbalance — the 48 $W_{\text{gate}}$ routers still carried logits initialized for a much larger expert space, leaving ~38% of experts fully inactive or below 0.2% traffic.
Syntactic collapse into loops — critical layers (layer 3, Gini 0.728; layer 44, Gini 0.706) concentrated up to 8.8% of all traffic in a single monopolist expert, inducing infinite lexical repetition in open-ended generation.
PLE hypertrophy — factual-memory injection ran at $\rho = |\Delta h_{\text{PLE}}| / |h_{\text{residual}}| = 0.658$, roughly double the stable range ($0.20 \sim 0.35$).

2. Router-healing SFT (150 steps)

A closed-loop protocol with triple balancing pressure:

ST-MoE auxiliary balance loss: $\mathcal{L}{\text{aux}} = N \sum{i=1}^N f_i \cdot P_i$
Logarithmic starvation barrier (KL): asymmetric exponential penalty on experts whose share falls below $\frac{0.5}{N}$.
Inter-expert load variance: $\mathcal{L}_{\text{var}} = \text{Var}(f)$.
Parametric surgery: 99.96% of the model frozen. Only the 48 $W_{\text{gate}}$ routers (15.73M trainable parameters) were optimized with AdamW, warmup and cosine decay ($LR_{\max} = 3 \times 10^{-4}$).

3. Quantitative results, pre vs post healing

Audited on an NVIDIA RTX PRO 6000 (96 GB VRAM) with a multi-domain battery (concurrent Python, CoT mathematics, legal doctrine, tool calling):

Indicator	Pre-healing	Post-healing	Change
Trigram repetition	Pathological (infinite loops)	0.69%	Loops eliminated
Lexical diversity (Distinct-1)	$<0.30$	0.81	High vocabulary variability
Shannon routing entropy ($H$)	$0.680$	$0.8353$	+22.8%
Inactive experts (0 hits)	$22.6$ / 128 (17.7%)	$16.6$ / 128 (12.9%)	6 dead experts revived per layer
Top-1 expert share	$7.20%$	$6.12%$	-15.0%
Top-3 expert share	$18.90%$	$15.75%$	-16.7%
PLE injection ratio ($\rho$)	$0.658$	$0.600$	Damped toward the stable band

These numbers describe relative improvement over a broken checkpoint, not competitive benchmark results. No standard benchmark (MMLU, GSM8K, HumanEval…) has been run on this checkpoint, and none should be inferred from the table above.

Architecture (`qwen4_exp`)

Property	Value
Total layers	48 hybrid MoE blocks
Hidden size	2,560
Attention	Gated DeltaNet linear attention, 3 linear blocks per 1 full-attention block (`full_attention_interval: 4`)
Hyper-Connections	4 residual streams, rank-320 projections
Routed experts	128 per layer, top-10 active (`num_experts_per_tok: 10`)
Shared expert	1 dense expert (intermediate size 640)
PLE memory	Associative n-gram table, 2,000,000 base entries (`ngram_size: 3`)
Vocabulary	248,320
Native context	262,144 tokens
Precision	BFloat16

Total parameters: 40.22B (1,294 tensors, 80.44 GB BF16)
Activated per token: top-10 routed experts + 1 shared dense expert ($\approx$ 2.6B expert parameters per token, on top of the attention and embedding stack)
Checkpoint class: text-only (Qwen4ExpForCausalLM); the vision tower is not included
PLE memory: n-gram table pruned to 2,000,000 entries

4. Requirements

Non-standard architecture. It needs an inference stack with explicit qwen4_exp support (Gated DeltaNet linear attention + 4-stream Hyper-Connections + PLE associative memory). Standard dense-Transformer loaders will not work.

Shard 1 is ~49.6 GB. Use hf download / snapshot_download with resume rather than a plain browser download.

Experiment line

Repository	Role
`qwen-3.8-next-40b-exp-clean-bf16`	Clean baseline
`qwen-3.8-next-40b-exp-clean-healed-bf16`	Router-healed, text-only
`qwen-3.8-next-40b-exp-moe-pruned-bf16`	512→128 expert pruning
`qwen-3.8-next-40b-exp-moe-healed-bf16`	Pruned + router-healed + PLE 2.0M
`qwen-3.8-next-40b-exp-ple-2m-table`	Routing tables and calibration artifacts
`qwen-3.8-next-40b-exp-cartridge-general`	Delta cartridge testbed
`qwen-3.8-next-40b-exp-profiling-metrics`	Profiling metrics

5. Credits

Based on the architectures and research of David Aylward (logic65), the Qwen team (Alibaba Cloud), and work on adaptive MoE routing.

License

Apache 2.0, inherited from the upstream Qwen base model.

Downloads last month: 271

Safetensors

Model size

40B params

Tensor type

I64

BF16

Model tree for Davd-b01/qwen-3.8-next-40b-exp-moe-healed-bf16

Base model

Davd-b01/qwen-3.8-next-40b-exp-clean-bf16

Finetuned

Davd-b01/qwen-3.8-next-40b-exp-moe-pruned-bf16

Finetuned

(1)

this model

Davd-b01
/

qwen-3.8-next-40b-exp-moe-healed-bf16

⚠️ EXPERIMENTAL WEIGHTS — NOT A FINAL RELEASE ⚠️

THESE ARE EXPERIMENTAL RESEARCH WEIGHTS. THIS IS NOT A FINISHED OR PRODUCTION MODEL.

Qwen-3.8-Next-40B-MoE-Healed (BF16)

1. Diagnosis of the pruned base

2. Router-healing SFT (150 steps)

3. Quantitative results, pre vs post healing

Architecture (`qwen4_exp`)

4. Requirements

Experiment line

5. Credits

License

Model tree for Davd-b01/qwen-3.8-next-40b-exp-moe-healed-bf16

⚠️ EXPERIMENTAL WEIGHTS — NOT A FINAL RELEASE ⚠️

THESE ARE EXPERIMENTAL RESEARCH WEIGHTS. THIS IS NOT A FINISHED OR PRODUCTION MODEL.

Qwen-3.8-Next-40B-MoE-Healed (BF16)

1. Diagnosis of the pruned base

2. Router-healing SFT (150 steps)

3. Quantitative results, pre vs post healing

Architecture (qwen4_exp)

4. Requirements

Experiment line

5. Credits

License

Model tree for Davd-b01/qwen-3.8-next-40b-exp-moe-healed-bf16

Architecture (`qwen4_exp`)