Upload README.md with huggingface_hub

README.md

@@ -1,3 +1,242 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+base_model:
+- mistralai/Mistral-Small-3.1-24B-Instruct-2503
+base_model_relation: quantized
+pipeline_tag: text2text-generation
+language:
+- zho
+- eng
+- fra
+- spa
+- por
+- deu
+- ita
+- rus
+- jpn
+- kor
+- vie
+- tha
+- ara
+---
+
+# Elastic model: Mistral-Small-3.1-24B-Instruct-2503. 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.
+
+
+-----
+
+## 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 confugaration as well
+model_name = "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
+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
+* 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 elastic_models[nvidia]\
+ --index-url https://thestage.jfrog.io/artifactory/api/pypi/pypi-thestage-ai-production/simple\
+ --extra-index-url https://pypi.nvidia.com\
+ --extra-index-url https://pypi.org/simple
+
+pip install flash_attn==2.7.3 --no-build-isolation
+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 <YOUR_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 |
+|---------------|---|---|---|----|----------|------------|
+| arc_challenge | 65.30 | 66.30 | 66.70 | 66.80 | 66.80 | 65.30 | - |
+| gsm8k | 87.70 | 87.80 | 88.00 | - | - | 87.70 | - |
+| mmlu | 79.00 | 79.40 | 79.70 | 80.20 | 80.20 | 79.00 | - |
+| piqa | 82.90 | 83.10 | 82.60 | 83.00 | 83.00 | 82.90 | - |
+| winogrande | 78.20 | 79.40 | 79.30 | 79.50 | 79.50 | 78.20 | - |
+
+
+
+* **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 | 90 | -1 | -1 | -1 | -1 | -1 | - |
+| L40S | -1 | -1 | -1 | -1 | -1 | -1 | - |
+
+
+### Performance by Context Size
+
+The tables below show performance (tokens per second) for different input context sizes across different GPU models and batch sizes:
+
+**H100:**
+
+*Batch Size 1:*
+
+| Context | Input Tokens | S | M | L | XL | Original |
+|---------|-------------|---|---|---|----|---------|
+| Small | 93 | 90.3 | - | - | - | - |
+| Medium | 1024 | 89.6 | - | - | - | - |
+| Large | 4096 | 87.5 | - | - | - | - |
+
+*Batch Size 8:*
+
+| Context | Input Tokens | S | M | L | XL | Original |
+|---------|-------------|---|---|---|----|---------|
+| Small | 93 | 87.3 | - | - | - | - |
+| Medium | 1024 | 79.9 | - | - | - | - |
+| Large | 4096 | 63.2 | - | - | - | - |
+
+*Batch Size 16:*
+
+| Context | Input Tokens | S | M | L | XL | Original |
+|---------|-------------|---|---|---|----|---------|
+| Small | 93 | 85.8 | - | - | - | - |
+| Medium | 1024 | 79.0 | - | - | - | - |
+| Large | 4096 | 62.2 | - | - | - | - |
+
+
+**L40S:**
+
+*Batch Size 1:*
+
+| Context | Input Tokens | S | M | L | XL | Original |
+|---------|-------------|---|---|---|----|---------|
+| Small | 93 | - | - | - | - | - |
+| Medium | 1024 | - | - | - | - | - |
+| Large | 4096 | - | - | - | - | - |
+
+*Batch Size 8:*
+
+| Context | Input Tokens | S | M | L | XL | Original |
+|---------|-------------|---|---|---|----|---------|
+| Small | 93 | - | - | - | - | - |
+| Medium | 1024 | - | - | - | - | - |
+| Large | 4096 | - | - | - | - | - |
+
+*Batch Size 16:*
+
+| Context | Input Tokens | S | M | L | XL | Original |
+|---------|-------------|---|---|---|----|---------|
+| Small | 93 | - | - | - | - | - |
+| Medium | 1024 | - | - | - | - | - |
+| Large | 4096 | - | - | - | - | - |
+
+
+
+
+*Note: Results show tokens per second (TPS) for text generation with 100 new tokens output. Performance varies based on GPU model, context size, and batch size.*
+
+
+## Links
+
+* Platform: [app.thestage.ai](https://app.thestage.ai/)
+* __Subscribe for updates__: [TheStageAI X](https://x.com/TheStageAI)
+<!-- * __Elastic models Github__: [app.thestage.ai](app.thestage.ai) -->
+* __Contact email__: [email protected]