Instructions to use Soofi-Project/Soofi-S-Instruct-Preview-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Soofi-Project/Soofi-S-Instruct-Preview-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="Soofi-Project/Soofi-S-Instruct-Preview-FP8", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Soofi-Project/Soofi-S-Instruct-Preview-FP8", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Soofi-Project/Soofi-S-Instruct-Preview-FP8", trust_remote_code=True)
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 Soofi-Project/Soofi-S-Instruct-Preview-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Soofi-Project/Soofi-S-Instruct-Preview-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Soofi-Project/Soofi-S-Instruct-Preview-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Soofi-Project/Soofi-S-Instruct-Preview-FP8

SGLang

How to use Soofi-Project/Soofi-S-Instruct-Preview-FP8 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 "Soofi-Project/Soofi-S-Instruct-Preview-FP8" \
    --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": "Soofi-Project/Soofi-S-Instruct-Preview-FP8",
		"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 "Soofi-Project/Soofi-S-Instruct-Preview-FP8" \
        --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": "Soofi-Project/Soofi-S-Instruct-Preview-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Soofi-Project/Soofi-S-Instruct-Preview-FP8 with Docker Model Runner:
```
docker model run hf.co/Soofi-Project/Soofi-S-Instruct-Preview-FP8
```

Soofi-S-Instruct-Preview-FP8 / README.md

danielporta

Update model card

90ed419 verified 6 days ago

preview code

Raw

History Blame Contribute Delete

4.16 kB

metadata

base_model: Soofi-Project/Soofi-S-Instruct-Preview
license: other
language:
  - en
  - de
  - es
  - fr
  - it
library_name: transformers
pipeline_tag: text-generation
tags:
  - fp8
  - compressed-tensors
  - mamba-2
  - moe
  - soofi
  - vllm
  - quantized
  - preview
quantized_by: Soofi-Project

Soofi-S-Instruct-Preview-FP8

⚠️ Preview / internal checkpoint. Weights and metadata may still change.

FP8 (W8A8 dynamic) quantization of Soofi-Project/Soofi-S-Instruct-Preview for space-efficient serving with vLLM.

Quantized from bf16 safetensors with llm-compressor to the compressed-tensors FP8 format, which vLLM loads natively at roughly half the weight memory of the bf16 checkpoint.

Architecture support: SOOFI-S is a custom hybrid Mamba-2/MoE model and ships with its own modeling code (trust_remote_code). FP8 serving requires a vLLM build that understands this architecture — verify against the actual checkpoint before relying on this artifact.

Quantization details

Property	Value
Scheme	FP8_DYNAMIC (W8A8)
Weights	FP8 E4M3, per-channel static scales
Activations	FP8 E4M3, per-token dynamic (quantized at runtime)
Calibration	none (data-free)
Kept in full precision	`lm_head`, Mamba-2 `in_proj`/`out_proj`

Why dynamic / data-free? Dynamic per-token activation scales need no calibration dataset and are robust for MoE, where a single static activation scale across experts is a poor fit. The MoE router is not an nn.Linear, so it stays full precision automatically; the Mamba-2 in_proj/out_proj (the recurrent SSM path) are kept bf16 as the most quantization-sensitive layers.

Size scales with the total 30B parameters (not the 3.5B active), so the FP8 weights are ~half the bf16 size minus the few full-precision tensors above.

Usage with vLLM

# OpenAI-compatible server
vllm serve Soofi-Project/Soofi-S-Instruct-Preview-FP8 --trust-remote-code

# query it
curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "Soofi-Project/Soofi-S-Instruct-Preview-FP8",
       "messages": [{"role": "user", "content": "Explain AI sovereignty in one sentence."}]}'

from vllm import LLM, SamplingParams

llm = LLM(model="Soofi-Project/Soofi-S-Instruct-Preview-FP8", trust_remote_code=True)
out = llm.chat([{"role": "user", "content": "Explain AI sovereignty in one sentence."}],
               SamplingParams(temperature=0.6, top_p=0.95))
print(out[0].outputs[0].text)

--trust-remote-code is required: the custom hybrid Mamba-2/MoE modeling code travels with the checkpoint. FP8 needs a GPU with hardware FP8 support (NVIDIA Hopper/Ada/Blackwell — e.g. H100, L40S, RTX 4090) for the fast path; on older GPUs vLLM falls back to a slower Marlin kernel.

The chat template is applied by vLLM's chat endpoint, so the model's native identity and tool-calling format work out of the box — no manual template.

Architecture note

This is a hybrid Mixture-of-Experts model designed from scratch: 23 Mamba-2/MoE layers + 6 attention layers, 128 routing experts + 1 shared expert per MoE layer, 6 experts active per token (30B total / 3.5B active). FP8 is applied to the Linear layers (attention/MoE expert projections); the SSM (Mamba-2) recurrent parameters and the router stay in higher precision. A recent version of vLLM is recommended.

Related models

Base (bf16): Soofi-Project/Soofi-S-Instruct-Preview
GGUF (llama.cpp/Ollama): Soofi-Project/Soofi-S-Instruct-Preview-GGUF

License & provenance

Released under a custom license ("Other"), following the base model Soofi-Project/Soofi-S-Instruct-Preview. TODO: mirror the full license text once the base model card defines it.