Instructions to use ControlLLM/Llama-3.1-8B-SynE-Concat16-Lerp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ControlLLM/Llama-3.1-8B-SynE-Concat16-Lerp with Transformers:

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

pipe = pipeline("text-generation", model="ControlLLM/Llama-3.1-8B-SynE-Concat16-Lerp")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ControlLLM/Llama-3.1-8B-SynE-Concat16-Lerp", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ControlLLM/Llama-3.1-8B-SynE-Concat16-Lerp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ControlLLM/Llama-3.1-8B-SynE-Concat16-Lerp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ControlLLM/Llama-3.1-8B-SynE-Concat16-Lerp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ControlLLM/Llama-3.1-8B-SynE-Concat16-Lerp

SGLang

How to use ControlLLM/Llama-3.1-8B-SynE-Concat16-Lerp 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 "ControlLLM/Llama-3.1-8B-SynE-Concat16-Lerp" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ControlLLM/Llama-3.1-8B-SynE-Concat16-Lerp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ControlLLM/Llama-3.1-8B-SynE-Concat16-Lerp" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ControlLLM/Llama-3.1-8B-SynE-Concat16-Lerp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ControlLLM/Llama-3.1-8B-SynE-Concat16-Lerp with Docker Model Runner:
```
docker model run hf.co/ControlLLM/Llama-3.1-8B-SynE-Concat16-Lerp
```

Control-LLM-Llama3.1-8B-SynE-Concat16-Lerp

This is a fine-tuned model of Llama-3.1-8B for muliligual-Chinese tasks on SynE dataset by Control LLM-Concat16-Lerp.

Linked Paper

This model is associated with the paper: Control LLM: Controlled Evolution for Intelligence Retention in LLM.

Linked Open Source code - training, eval and benchmark

This model is associated with the github: Control-LLM.

Evaluation Results

Here is an overview of the evaluation results and findings:

Benchmark Results Table

The table below summarizes evaluation results across Chinese tasks and original capabilities.

Model	CEval	CEvalC	CMMLU	CMMLUC	C-Avg	BBH	MLU	MLUP	O-Avg	Overall
Llama3.1-8B	48.3	12.8	51.1	14.1	13.9	65.2	65.4	35.5	45.9	29.9
Llama-3-SynE	57.7	22.3	57.1	22.8	22.8	61.9	64.0	32.6	42.9	32.9
Full Param Tune	59.0	40.2	60.2	44.3	43.8	64.8	64.9	35.0	45.4	44.6
Stack Expansion	56.0	32.7	55.2	33.4	33.3	62.3	65.6	35.3	44.8	39.1
Concat-Lerp	57.1	34.8	57.0	37.4	37.1	64.4	64.6	35.8	45.9	41.5
Hybrid Expansion	58.9	44.7	57.9	44.3	44.4	65.1	65.7	36.9	46.8	45.6
Control LLM*	57.0	44.7	56.0	44.9	44.8	68.2	65.6	37.9	48.5	46.7

Explanation:

CEval: Chinese Evaluation
CEvalC: Chinese Evaluation (CoT - Chain of Thought)
CMMLU: Chinese MMLU
CMMLUC: Chinese MMLU (CoT)
C-Avg: Chinese - Size Weighted Average across CEval, CEvalC, CMMLU, and CMMLUC
BBH: BigBench Hard
MLU: MMLU (Massive Multitask Language Understanding)
MLUP: MMLU Pro
O-Avg: Original Capability - Size Weighted Average across BBH, MLU, and MLUP
Overall: Combined average across all tasks

Downloads last month: 5

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for ControlLLM/Llama-3.1-8B-SynE-Concat16-Lerp

Base model

meta-llama/Llama-3.1-8B

Finetuned

(1788)

this model

Datasets used to train ControlLLM/Llama-3.1-8B-SynE-Concat16-Lerp

Paper for ControlLLM/Llama-3.1-8B-SynE-Concat16-Lerp

Control LLM: Controlled Evolution for Intelligence Retention in LLM

Paper • 2501.10979 • Published Jan 19, 2025 • 6

Evaluation results

exact_match,strict-match (meta_pretrain) on Pretraining Evaluation Dataset
self-reported

0.459
exact_match,strict-match (meta_bbh_3shot_cot_pretrain) on Pretraining Evaluation Dataset
self-reported

0.644
acc,none (meta_mmlu_5shot_pretrain) on Pretraining Evaluation Dataset
self-reported

0.646
exact_match,strict-match (meta_mmlu_pro_5shot_pretrain) on Pretraining Evaluation Dataset
self-reported

0.358
exact_match,strict-match (zh_pretrain_multishot) on Chinese Evaluation Dataset
self-reported

0.371
acc,none (ceval-valid) on Chinese Evaluation Dataset
self-reported

0.571
exact_match,strict-match (ceval-valid-pretrain-cot_zh) on Chinese Evaluation Dataset
self-reported

0.348
acc,none (cmmlu) on Chinese Evaluation Dataset
self-reported

0.569
exact_match,strict-match (cmmlu_pretrain_cot_zh) on Chinese Evaluation Dataset
self-reported

0.374