Instructions to use luxopes/Cognix-1-Flash-2.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use luxopes/Cognix-1-Flash-2.6B with Transformers:

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

pipe = pipeline("text-generation", model="luxopes/Cognix-1-Flash-2.6B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("luxopes/Cognix-1-Flash-2.6B")
model = AutoModelForCausalLM.from_pretrained("luxopes/Cognix-1-Flash-2.6B", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use luxopes/Cognix-1-Flash-2.6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "luxopes/Cognix-1-Flash-2.6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "luxopes/Cognix-1-Flash-2.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/luxopes/Cognix-1-Flash-2.6B

SGLang

How to use luxopes/Cognix-1-Flash-2.6B 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 "luxopes/Cognix-1-Flash-2.6B" \
    --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": "luxopes/Cognix-1-Flash-2.6B",
		"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 "luxopes/Cognix-1-Flash-2.6B" \
        --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": "luxopes/Cognix-1-Flash-2.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use luxopes/Cognix-1-Flash-2.6B with Docker Model Runner:
```
docker model run hf.co/luxopes/Cognix-1-Flash-2.6B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Cognix 1 Flash

Created by LuxAI. Code-first SFT of the pinned LFM2.5-2.6B Base, not Instruct. This repository contains the merged BF16 model.

BF16 unquantized frozen base; rank 64, alpha 128. LoRA covers attention linears, convolution input/output projections and FFN linears. Tied embeddings/output head, norms and depthwise convolution remain frozen.

Processed 313,058,111 input tokens and 170,415,279 assistant-loss tokens. Full epoch: True. Stop reason: epoch. Maximum training length 32768; whole overlong examples removed AFTER LFM retokenization. No right truncation. Independent padded batch rows isolate attention AND convolution. Loss only on originally selected assistant turns, including their end-of-turn token. Code FIM examples are presented as chat missing-code tasks.

Use the included unchanged upstream chat_template.jinja and tokenizer. Reasoning uses ...; Pythonic tool calls use <|tool_call_start|>[function_name(argument='value')]<|tool_call_end|>. Tool results use plain content in the native tool role/template. Execute only allowlisted calls; never eval generated Python. No new vocabulary or identity special tokens were added. Identity examples teach Cognix 1 Flash, created by LuxAI.

Short acceptance checks, if completed, are included as separate JSON receipts. No inference benchmark scores or quality guarantees are claimed. Czech performance, tool reliability and long-context behavior still need evaluation after training. No claim that all 32k contexts will be practical on every 8 GB phone.

The included upstream LICENSE (LFM Open License v1.0) applies to the base/derivative; this model is NOT relabeled Apache-2.0. Preserve its terms and attribution. See BASE_MODEL_CARD.md, DATA_ATTRIBUTION.md, DATA_MANIFEST.json and conversion.json. HF visibility follows the owner's explicit authorization, if included; the original learning configuration is retained unchanged for checkpoint provenance. GGUF conversion is a separate CPU step after the GPU pod has stopped.

Chat identity template update

The native chat format now includes the identity Cognix 1 Flash, created by LuxAI and brief general guidance. Caller-provided system instructions are retained after this prefix. Special token IDs and all weight tensors are unchanged. See system_prompt.txt, chat_template.readable.jinja, and chat_template_update.json. Historical acceptance and LuxCore1 results predate this template change; no new score or quality improvement is claimed.

Downloads last month: 109

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for luxopes/Cognix-1-Flash-2.6B

Base model

LiquidAI/LFM2.5-2.6B-Base

Finetuned

(19)

this model

Adapters

1 model

Quantizations

1 model