Instructions to use LLM-OS-Models/Fabliq-8B-Agent-FromBase with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLM-OS-Models/Fabliq-8B-Agent-FromBase with Transformers:

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

pipe = pipeline("text-generation", model="LLM-OS-Models/Fabliq-8B-Agent-FromBase")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LLM-OS-Models/Fabliq-8B-Agent-FromBase")
model = AutoModelForCausalLM.from_pretrained("LLM-OS-Models/Fabliq-8B-Agent-FromBase")
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 LLM-OS-Models/Fabliq-8B-Agent-FromBase with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LLM-OS-Models/Fabliq-8B-Agent-FromBase"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLM-OS-Models/Fabliq-8B-Agent-FromBase",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LLM-OS-Models/Fabliq-8B-Agent-FromBase

SGLang

How to use LLM-OS-Models/Fabliq-8B-Agent-FromBase 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 "LLM-OS-Models/Fabliq-8B-Agent-FromBase" \
    --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": "LLM-OS-Models/Fabliq-8B-Agent-FromBase",
		"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 "LLM-OS-Models/Fabliq-8B-Agent-FromBase" \
        --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": "LLM-OS-Models/Fabliq-8B-Agent-FromBase",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LLM-OS-Models/Fabliq-8B-Agent-FromBase with Docker Model Runner:
```
docker model run hf.co/LLM-OS-Models/Fabliq-8B-Agent-FromBase
```

Fabliq-8B-Agent-FromBase / README.md

gyung

Upload README.md with huggingface_hub

f1e2b4d verified 12 days ago

preview code

Raw

History Blame Contribute Delete

2.54 kB

	---
	library_name: transformers
	license: apache-2.0
	base_model: LiquidAI/LFM2.5-8B-A1B
	base_model_relation: finetune
	tags:
	- lfm
	- liquid-ai
	- moe
	- agentic
	- terminal
	- fable-5
	- distillation
	- sft
	- ablation
	language:
	- en
	pipeline_tag: text-generation
	---

	# Fabliq-8B-Agent-FromBase 🌊🔬

	> Ablation variant of [Fabliq-8B-Agent](https://huggingface.co/LLM-OS-Models/Fabliq-8B-Agent) — fine-tuned directly from raw [`LiquidAI/LFM2.5-8B-A1B`](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B), skipping the ToolBench foundation. Used to isolate the effect of the ToolBench intermediate stage.

	## 🔬 Why this variant?

	[Fabliq-8B-Agent](https://huggingface.co/LLM-OS-Models/Fabliq-8B-Agent) is trained as: `LiquidAI/LFM2.5-8B-A1B` → `ToolBench-Full-SFT-1Epoch` → `Fable-5`.

	This model skips the middle step: `LiquidAI/LFM2.5-8B-A1B` → `Fable-5` (direct).

	Comparing the two answers the question: does ToolBench foundation actually help, or does Fable-5 alone give you the same agent?

	## 🧪 Model details

	\| \| \|
	\| --- \| --- \|
	\| Architecture \| Lfm2MoeForCausalLM (24 layers, 32 experts, 4 experts/token) \|
	\| Parameters \| ~8B total / ~1B active (MoE) \|
	\| Context \| 8,192 trained · 128K native \|
	\| Precision \| bfloat16 \|
	\| Fine-tune type \| Full-parameter SFT (direct from base, no ToolBench) \|
	\| License \| Apache 2.0 \|

	## 📚 Training data

	Same as Phase-1: [Fable-5-traces](https://huggingface.co/datasets/Glint-Research/Fable-5-traces), 4,047 rows × 3 epoch.

	## 🔧 Training procedure

	\| Hyperparameter \| Value \|
	\| --- \| --- \|
	\| Schedule \| 3 epochs, constant LR \|
	\| Max sequence length \| 8,192 \|
	\| Per-device batch size \| 2 \|
	\| Gradient accumulation \| 4 \|
	\| GPUs \| 8× H200 (effective batch 64) \|
	\| Learning rate \| 1e-6 (higher than Phase-1's 5e-7, since starting from base) \|
	\| Precision \| bf16 \|
	\| Final train_loss \| logged in run_config.json \|
	\| Train runtime \| ~14 min \|

	## 🌳 Model tree

	```
	LiquidAI/LFM2.5-8B-A1B
	├─ LLM-OS-Models/LFM2.5-8B-A1B-Terminal-ToolBench-Full-SFT-1Epoch
	│ └─ LLM-OS-Models/Fabliq-8B-Agent ← Phase-1 (ToolBench → Fable-5)
	└─ LLM-OS-Models/Fabliq-8B-Agent-FromBase ← this model (base → Fable-5, direct)
	└─ LLM-OS-Models/Fabliq-8B-Agent-FromBase-Reasoning ← + reasoning expansion
	```

	## 🚀 Usage

	See [Fabliq-8B-Agent](https://huggingface.co/LLM-OS-Models/Fabliq-8B-Agent) — same system prompt, same tool-call format, same inference code.

	## 📜 License

	Apache 2.0.