--- license: apache-2.0 base_model: - meta-llama/Meta-Llama-3.1-8B-Instruct base_model_relation: quantized pipeline_tag: text-generation language: - zho - eng - fra - spa - por - deu - ita - rus - jpn - kor - vie - tha - ara --- # Elastic model: Meta-Llama-3.1-8B-Instruct. Fastest and most flexible models for self-serving. Elastic models are the models produced by TheStage AI ANNA: Automated Neural Networks Accelerator. ANNA allows you to control model size, latency and quality with a simple slider movement. For each model, ANNA produces a series of optimized models: * __XL__: Mathematically equivalent neural network, optimized with our DNN compiler. * __L__: Near lossless model, with less than 1% degradation obtained on corresponding benchmarks. * __M__: Faster model, with accuracy degradation less than 1.5%. * __S__: The fastest model, with accuracy degradation less than 2%. __Goals of elastic models:__ * Provide flexibility in cost vs quality selection for inference * Provide clear quality and latency benchmarks * Provide interface of HF libraries: transformers and diffusers with a single line of code * Provide models supported on a wide range of hardware, which are pre-compiled and require no JIT. * Provide the best models and service for self-hosting. > It's important to note that specific quality degradation can vary from model to model. For instance, with an S model, you can have 0.5% degradation as well. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6799fc8e150f5a4014b030ca/pKc4jGGKTrp7ecawPbZq-.png) ----- ## Inference To infer our models, you just need to replace `transformers` import with `elastic_models.transformers`: ```python import torch from transformers import AutoTokenizer from elastic_models.transformers import AutoModelForCausalLM # Currently we require to have your HF token # as we use original weights for part of layers and # model configuration as well model_name = "meta-llama/Llama-3.1-8B-Instruct" hf_token = '' device = torch.device("cuda") # Create mode tokenizer = AutoTokenizer.from_pretrained( model_name, token=hf_token ) model = AutoModelForCausalLM.from_pretrained( model_name, token=hf_token, torch_dtype=torch.bfloat16, attn_implementation="sdpa", mode='S' ).to(device) model.generation_config.pad_token_id = tokenizer.eos_token_id # Inference simple as transformers library prompt = "Describe basics of DNNs quantization." messages = [ { "role": "system", "content": "You are a search bot, answer on user text queries." }, { "role": "user", "content": prompt } ] chat_prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=False ) inputs = tokenizer(chat_prompt, return_tensors="pt") inputs.to(device) with torch.inference_mode(): generate_ids = model.generate(**inputs, max_length=500) input_len = inputs['input_ids'].shape[1] generate_ids = generate_ids[:, input_len:] output = tokenizer.batch_decode( generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False )[0] # Validate answer print(f"# Q:\n{prompt}\n") print(f"# A:\n{output}\n") ``` __System requirements:__ * GPUs: H100, L40s, 5090, 4090 * CPU: AMD, Intel * Python: 3.10-3.12 To work with our models just run these lines in your terminal: ```shell pip install thestage pip install 'thestage-elastic-models[nvidia]' --extra-index-url https://thestage.jfrog.io/artifactory/api/pypi/pypi-thestage-ai-production/simple pip install flash_attn==2.7.3 --no-build-isolation # or for blackwell support pip install 'thestage-elastic-models[blackwell]' --extra-index-url https://thestage.jfrog.io/artifactory/api/pypi/pypi-thestage-ai-production/simple pip install torch==2.7.0+cu128 torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128 # please download the appropriate version of Wheels for your system from https://github.com/Zarrac/flashattention-blackwell-wheels-whl-ONLY-5090-5080-5070-5060-flash-attention-/releases/tag/FlashAttention mv flash_attn-2.7.4.post1-rtx5090-torch2.7.0cu128cxx11abiTRUE-cp311-linux_x86_64.whl flash_attn-2.7.4.post1-0rtx5090torch270cu128cxx11abiTRUE-cp311-cp311-linux_x86_64.whl pip install flash_attn-2.7.4.post1-0rtx5090torch270cu128cxx11abiTRUE-cp311-cp311-linux_x86_64.whl pip uninstall apex ``` Then go to [app.thestage.ai](https://app.thestage.ai), login and generate API token from your profile page. Set up API token as follows: ```shell thestage config set --api-token ``` Congrats, now you can use accelerated models! ---- ## Benchmarks Benchmarking is one of the most important procedures during model acceleration. We aim to provide clear performance metrics for models using our algorithms. The `W8A8, int8 column` indicates that we applied W8A8 quantization with int8 data type to all linear layers and used the same calibration data as for ANNA. The S model achieves practically identical speed but much higher quality, as ANNA knows how to improve quantization quality on sensitive layers! ### Quality benchmarks | Metric/Model | S | M | L | XL | Original | W8A8, int8 | |---------------|---|---|---|----|----------|------------| | MMLU | 65.8 | 66.8 | 67.5 | 68.2 | 68.2 | 24.3 | | PIQA | 77.6 | 79.3 | 79.8 | 79.8 | 79.8 | 64.6 | | Arc Challenge | 50.7 | 50.3 | 52.3 | 51.7 | 51.7 | 29.6 | | Winogrande | 72.5 | 72 | 73.3 | 73.9 | 73.9 | 62.8 | * **MMLU**:Evaluates general knowledge across 57 subjects including science, humanities, engineering, and more. Shows model's ability to handle diverse academic topics. * **PIQA**: Evaluates physical commonsense reasoning through questions about everyday physical interactions. Shows model's understanding of real-world physics concepts. * **Arc Challenge**: Evaluates grade-school level multiple-choice questions requiring reasoning. Shows model's ability to solve complex reasoning tasks. * **Winogrande**: Evaluates commonsense reasoning through sentence completion tasks. Shows model's capability to understand context and resolve ambiguity. ### Latency benchmarks __100 input/300 output; tok/s:__ | GPU/Model | S | M | L | XL | Original | W8A8, int8 | |-----------|-----|---|---|----|----------|------------| | H100 | 189 | 175 | 159 | 132 | 60 | 191 | | L40s | 73 | 64 | 57 | 45 | 40 | 77 | | 5090 | 145 | - | - | - | - | - | | 4090 | 95 | - | - | - | - | - | ## Links * __Platform__: [app.thestage.ai](app.thestage.ai) * __Subscribe for updates__: [TheStageAI X](https://x.com/TheStageAI) * __Contact email__: contact@thestage.ai