Instructions to use consciousengines/CE-flicker-eco with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use consciousengines/CE-flicker-eco with Transformers:

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

pipe = pipeline("text-generation", model="consciousengines/CE-flicker-eco", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("consciousengines/CE-flicker-eco", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use consciousengines/CE-flicker-eco with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/consciousengines/CE-flicker-eco

SGLang

How to use consciousengines/CE-flicker-eco 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 "consciousengines/CE-flicker-eco" \
    --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": "consciousengines/CE-flicker-eco",
		"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 "consciousengines/CE-flicker-eco" \
        --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": "consciousengines/CE-flicker-eco",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use consciousengines/CE-flicker-eco with Docker Model Runner:
```
docker model run hf.co/consciousengines/CE-flicker-eco
```

CE-flicker-eco is an internal, temporary name

Block-diffusion chat with FP8 model weights and learned EccoMoE expert allocation. Completed blocks stream left to right. The current assistant introduces itself as Flicker-Eco; its API model ID is CE-flicker.

Three serving profiles

All use normal BF16 KV, block size 4, confidence threshold 0.95, and up to four denoising steps.

Profile	Model-weight precision	Expert routing	Tested hardware
Stock BF16	BF16	Native top-8	H200
Stock FP8	Blocked FP8	Native top-8	H200 and L40S
EccoMoE FP8 t6	Blocked FP8	Learned expert-count allocator, budget 6	L40S · default selected serving profile

Budget 6 is a compute target; actual expert counts vary by token and layer. The expert allocator is separate from the denoising confidence threshold.

Measured speed, energy and quality

FP8 stock on H200: 26.5% higher measured peak throughput and 21.6% less GPU energy per output token than BF16 stock.
EccoMoE t6 on L40S: 9.17% higher throughput and 10.53% less GPU J/token at eight concurrent requests, with an observed 4.67-point MBPP accuracy cost.

H200: stock BF16 versus stock FP8

Same SDAR checkpoint and lmdeploy backend; 1,024 input + forced 1,024 output tokens, no chat/system prompt. Both peaks occur at concurrency 512 and are three-run medians.

Profile	Peak total output tok/s	Concurrency	GPU J/output token
Stock BF16	6,257	512	0.11027
Stock FP8	7,916	512	0.08640

L40S: stock FP8 versus EccoMoE FP8 t6

Same physical GPU and approved prompt. Throughput/energy use forced 256-token outputs; MBPP is a separate paired, natural-stop quality test.

Profile	1-user output tok/s	Total output tok/s · 8 requests	GPU J/token · 8 requests	Prompted MBPP
Stock FP8	67.55	268.72	0.9859	74.71% · 192/257
EccoMoE FP8 t6	77.82	293.37	0.8821	70.04% · 180/257

Stock speed/energy pool six repeats; t6 has three. Stock single-user speed drifted 5.1% between phases. MBPP uses one deterministic run per profile: 25 tasks pass only with stock, 13 only with t6; neither run timed out or truncated. The tests preceded the identity-only rename to Flicker-Eco. Prompted quality comparison covers MBPP; current-prompt full MATH/IFEval comparisons remain outside this measured pair.

The default selected serving profile is EccoMoE t6, with this observed tradeoff. These are distinct hardware/workloads; GPU energy excludes CPU and wall-socket power. Full methods, load levels and metric records.

Setup and artifacts

The public checkpoint stores BF16 backbone weights. FP8 in these tables is validated model-weight serving precision via lmdeploy runtime conversion; the KV cache remains BF16.

The package includes the 49 backbone shards, the separate trained allocator, routing source, native-kernel compatibility probe, authenticated OpenAI-compatible streaming gateway and approved prompt. Current served configuration: lmdeploy 0.18.0, FP8 weights / BF16 KV, EccoMoE t6, 8,192 total-context tokens and maximum engine batch 8.

Reproduce the selected profile or either stock profile · Allocator integrity check · Source provenance and licenses · Package checksums.

Provenance

The frozen backbone is SDAR-30B-A3B-Chat, pinned to f5add2a159163a2a8f07e9da7dfcbfaadc73d6d4, under Apache 2.0. Upstream authors retain credit for base-model training and the SDAR algorithm; Conscious Engines supplies the trained allocator and serving/routing adaptation. The original backbone files are preserved.

Downloads last month: -

Safetensors

Model size

31B params

Tensor type

BF16

Model tree for consciousengines/CE-flicker-eco

Base model

JetLM/SDAR-30B-A3B-Chat

Finetuned

(1)

this model