nm-testing/granite-4.0-h-small-FP8-block

Granite-4.0-h-small

Model Overview

• Model Architecture: GraniteMoeHybridForCausalLM
  • Input: Text
  • Output: Text
• Model Optimizations:
  • Weight quantization: FP8
  • Activation quantization: FP8
• Release Date:
• Version: 1.0
• Model Developers:: Red Hat

Quantized version of ibm-granite/granite-4.0-h-small.

Model Optimizations

This model was obtained by quantizing the weights and activations of ibm-granite/granite-4.0-h-small to FP8 data type. This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%. Only the weights and activations of the linear operators within transformers blocks of the language model are quantized.

Deployment

Use with vLLM

1. Initialize vLLM server:

vllm serve RedHatAI/granite-4.0-h-small-FP8-block --tensor_parallel_size 4

2. Send requests to the server:

from openai import OpenAI

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://<your-server-host>:8000/v1"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

model = "RedHatAI/granite-4.0-h-small-FP8-block"

messages = [
    {"role": "user", "content": "Explain quantum mechanics clearly and concisely."},
]


outputs = client.chat.completions.create(
    model=model,
    messages=messages,
)

generated_text = outputs.choices[0].message.content
print(generated_text)

Evaluation

The model was evaluated on the OpenLLM leaderboard task, using lm-evaluation-harness. vLLM was used for all evaluations.

Evaluation details

Openllm V1

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/granite-4.0-h-small-FP8-block",dtype=auto,add_bos_token=True,max_model_len=16384,tensor_parallel_size=4,gpu_memory_utilization=0.9,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks openllm \
  --write_out \
  --batch_size auto \
  --show_config

Openllm V2

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/granite-4.0-h-small-FP8-block",dtype=auto,add_bos_token=False,max_model_len=16384,tensor_parallel_size=4,gpu_memory_utilization=0.7,disable_log_stats=True,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks leaderboard \
  --apply_chat_template \
  --fewshot_as_multiturn \
  --write_out \
  --batch_size auto \
  --show_config

Coding Benchmarks

evalplus.evaluate --model "RedHatAI/granite-4.0-h-small-FP8-block" \
                  --dataset "humaneval" \
                  --backend vllm \
                  --tp 4 \
                  --greedy

evalplus.evaluate --model "RedHatAI/granite-4.0-h-small-FP8-block" \
                --dataset "mbpp" \
                --backend vllm \
                --tp 4 \
                --greedy

Accuracy

Category	Metric	ibm-granite/granite-4.0-h-small	RedHatAI/granite-4.0-h-small-FP8-block	Recovery (%)
OpenLLM V1	ARC-Challenge (Acc-Norm, 25-shot)	abc	ijk	xyz
	GSM8K (Strict-Match, 5-shot)	abc	ijk	xyz
	HellaSwag (Acc-Norm, 10-shot)	abc	ijk	xyz
	MMLU (Acc, 5-shot)	abc	ijk	xyz
	TruthfulQA (MC2, 0-shot)	abc	ijk	xyz
	Winogrande (Acc, 5-shot)	abc	ijk	xyz
	Average Score	abc	ijk	xyz
OpenLLM V2	IFEval (Inst Level Strict Acc, 0-shot)	abc	ijk	xyz
	BBH (Acc-Norm, 3-shot)	abc	ijk	xyz
	Math-Hard (Exact-Match, 4-shot)	abc	ijk	xyz
	GPQA (Acc-Norm, 0-shot)	abc	ijk	xyz
	MUSR (Acc-Norm, 0-shot)	abc	ijk	xyz
	MMLU-Pro (Acc, 5-shot)	abc	ijk	xyz
	Average Score	abc	ijk	xyz
Coding	HumanEval pass@1	86.60	ijk	xyz
	HumanEval+ pass@1	81.10	ijk	xyz
	MBPP pass@1	82.00	ijk	xyz
	MBPP+ pass@1	69.80	ijk	xyz