Instructions to use bbkdevops/FABER-Genesis-A100-Max with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bbkdevops/FABER-Genesis-A100-Max with Transformers:

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

pipe = pipeline("text-generation", model="bbkdevops/FABER-Genesis-A100-Max", 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("bbkdevops/FABER-Genesis-A100-Max", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bbkdevops/FABER-Genesis-A100-Max with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bbkdevops/FABER-Genesis-A100-Max"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bbkdevops/FABER-Genesis-A100-Max",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bbkdevops/FABER-Genesis-A100-Max

SGLang

How to use bbkdevops/FABER-Genesis-A100-Max 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 "bbkdevops/FABER-Genesis-A100-Max" \
    --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": "bbkdevops/FABER-Genesis-A100-Max",
		"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 "bbkdevops/FABER-Genesis-A100-Max" \
        --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": "bbkdevops/FABER-Genesis-A100-Max",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bbkdevops/FABER-Genesis-A100-Max with Docker Model Runner:
```
docker model run hf.co/bbkdevops/FABER-Genesis-A100-Max
```

FABER-Genesis-A100-Max / README.md

bbkdevops

FABER-Genesis-A100-Max 13.86B architecture: config + HF modeling + profiles + benchmark harness

2ffbf1f verified 28 days ago

preview code

Raw History Blame Contribute Delete

2.27 kB

---
language: [en, th]
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
tags: [faber-genesis, gqa, rope, swiglu, weight-sharing, cass, bf16, a100, th]
---
# FABER-Genesis-A100-Max (13.86B architecture)

Decoder-only transformer with weight sharing + CASS state/value/halt heads.

- hidden 6144, heads 48, KV 8, head-dim 128, SwiGLU FFN 16384
- vocab 32768, tied embeddings, RMSNorm, RoPE, GQA
- 35 physical blocks -> 42 logical transformations + 1 recurrent pass
- total params: **13.860526082B** (backbone + CASS)
- training recipe: BF16, AdamW8bit, activation checkpointing, microbatch=1, ctx=512

## Profiles

| profile | physical | params | status |
|---|---|---:|---|
| production-13.08B | 33 | 13.0804B | default for long runs (~73.55 GiB) |
| safe-13.47B | 34 | 13.4704B | squeeze with safety (~75.75 GiB) |
| max-13.86B | 35 | 13.8605B | capacity experiments (~77.94 GiB) |
| oom-14.25B | 36 | 14.2506B | OOM on single A100 AdamW8bit |

## What this repo contains

`config.json` (max profile), `modeling_faber_genesis.py` (self-contained HF
model code), `genesis_profiles.json`, `tokenizer_config.json` (placeholder
config, vocab 32768 — train a real tokenizer before pretraining),
`benchmark_genesis_a100.py`, `EVIDENCE_GENESIS_A100_MAX.md`.

No trained weights are included in this upload. `config.json` defines a
random-init architecture. To materialize weights:

```python
from modeling_faber_genesis import FaberGenesisConfig, FaberGenesisForCausalLM
cfg = FaberGenesisConfig()  # max-13.86B
model = FaberGenesisForCausalLM(cfg)  # random init, BF16 training recipe applies on A100
```

## Ceiling benchmark (run on A100 80GB)

```bash
pip install "torch==2.6.0" bitsandbytes transformers
python benchmark_genesis_a100.py --profile max-13.86B --steps 1
python benchmark_genesis_a100.py --sweep --n-list 25,29,32,33,34,35,36,37 --steps 1
```

Pass = fwd+bwd+optim step completes; n=36/37 must OOM. VRAM estimates in
`EVIDENCE_GENESIS_A100_MAX.md` are analytic, not a substitute for this run.

## Limitations

Random-init step-pass says nothing about Thai/code/reasoning quality.
Quality requires pretraining curriculum + CASS + verifier + agent training
and SWE/APEX evals. 14.25B+ is not a single-A100 resident AdamW8bit config.

	---
	language: [en, th]
	library_name: transformers
	license: apache-2.0
	pipeline_tag: text-generation
	tags: [faber-genesis, gqa, rope, swiglu, weight-sharing, cass, bf16, a100, th]
	---

	# FABER-Genesis-A100-Max (13.86B architecture)

	Decoder-only transformer with weight sharing + CASS state/value/halt heads.

	- hidden 6144, heads 48, KV 8, head-dim 128, SwiGLU FFN 16384
	- vocab 32768, tied embeddings, RMSNorm, RoPE, GQA
	- 35 physical blocks -> 42 logical transformations + 1 recurrent pass
	- total params: 13.860526082B (backbone + CASS)
	- training recipe: BF16, AdamW8bit, activation checkpointing, microbatch=1, ctx=512

	## Profiles

	\| profile \| physical \| params \| status \|
	\|---\|---\|---:\|---\|
	\| production-13.08B \| 33 \| 13.0804B \| default for long runs (~73.55 GiB) \|
	\| safe-13.47B \| 34 \| 13.4704B \| squeeze with safety (~75.75 GiB) \|
	\| max-13.86B \| 35 \| 13.8605B \| capacity experiments (~77.94 GiB) \|
	\| oom-14.25B \| 36 \| 14.2506B \| OOM on single A100 AdamW8bit \|

	## What this repo contains

	`config.json` (max profile), `modeling_faber_genesis.py` (self-contained HF
	model code), `genesis_profiles.json`, `tokenizer_config.json` (placeholder
	config, vocab 32768 — train a real tokenizer before pretraining),
	`benchmark_genesis_a100.py`, `EVIDENCE_GENESIS_A100_MAX.md`.

	No trained weights are included in this upload. `config.json` defines a
	random-init architecture. To materialize weights:

	```python
	from modeling_faber_genesis import FaberGenesisConfig, FaberGenesisForCausalLM
	cfg = FaberGenesisConfig() # max-13.86B
	model = FaberGenesisForCausalLM(cfg) # random init, BF16 training recipe applies on A100
	```

	## Ceiling benchmark (run on A100 80GB)

	```bash
	pip install "torch==2.6.0" bitsandbytes transformers
	python benchmark_genesis_a100.py --profile max-13.86B --steps 1
	python benchmark_genesis_a100.py --sweep --n-list 25,29,32,33,34,35,36,37 --steps 1
	```

	Pass = fwd+bwd+optim step completes; n=36/37 must OOM. VRAM estimates in
	`EVIDENCE_GENESIS_A100_MAX.md` are analytic, not a substitute for this run.

	## Limitations

	Random-init step-pass says nothing about Thai/code/reasoning quality.
	Quality requires pretraining curriculum + CASS + verifier + agent training
	and SWE/APEX evals. 14.25B+ is not a single-A100 resident AdamW8bit config.