Update README.md

README.md

@@ -1,199 +1,393 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- torchao
+- code
+- math
+- chat
+- conversational
+language:
+- multilingual
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE
+pipeline_tag: text-generation
+base_model:
+- Qwen/Qwen3-8B
 ---
 
-# Model Card for Model ID
+[Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) fine-tuned with [unsloth](https://github.com/unslothai/unsloth) using quantization-aware training (QAT) from [torchao](https://huggingface.co/docs/transformers/main/en/quantization/torchao), and quantized with int4 weight only quantization, by PyTorch team.
+Use it directly or serve using [vLLM](https://docs.vllm.ai/en/latest/) for 62% VRAM reduction (6.24 GB needed) and 1.45x speedup on H100 GPUs.
+
+# Inference with vLLM
+Install vllm nightly and torchao nightly to get some recent changes:
+```
+pip install --pre vllm --extra-index-url https://wheels.vllm.ai/nightly
+pip install --pre torchao torch --index-url https://download.pytorch.org/whl/nightly/cu128
+```
+
+## Serving
+Then we can serve with the following command:
+```Shell
+# Server
+export MODEL=pytorch/Qwen3-8B-QAT-INT4
+VLLM_DISABLE_COMPILE_CACHE=1 vllm serve $MODEL --tokenizer $MODEL -O3
+```
+
+```Shell
+# Client
+curl http://localhost:8000/v1/chat/completions -H "Content-Type: application/json" -d '{
+  "model": "pytorch/Qwen3-8B-QAT-INT4",
+  "messages": [
+    {"role": "user", "content": "Give me a short introduction to large language models."}
+  ],
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "top_k": 20,
+  "max_tokens": 32768
+}'
+```
+
+Note: please use `VLLM_DISABLE_COMPILE_CACHE=1` to disable compile cache when running this code, e.g. `VLLM_DISABLE_COMPILE_CACHE=1 python example.py`, since there are some issues with the composability of compile in vLLM and torchao,
+this is expected be resolved in pytorch 2.8.
+
+# Inference with Transformers
+
+Install the required packages:
+```Shell
+pip install git+https://github.com/huggingface/transformers@main
+pip install --pre torchao torch --index-url https://download.pytorch.org/whl/nightly/cu128
+pip install accelerate
+```
+
+Example:
+```Py
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "pytorch/Qwen3-8B-QAT-INT4"
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+# prepare the model input
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# conduct text completion
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=32768
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
+
+# parsing thinking content
+try:
+    # rindex finding 151668 (</think>)
+    index = len(output_ids) - output_ids[::-1].index(151668)
+except ValueError:
+    index = 0
+
+thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
+content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
+
+print("thinking content:", thinking_content)
+print("content:", content)
+```
+
+# Quantization Recipe
+
+Install the required packages:
+```Shell
+pip install git+https://github.com/huggingface/transformers@main
+pip install --pre torchao torch --index-url https://download.pytorch.org/whl/nightly/cu128
+pip install unsloth
+pip install accelerate
+```
+
+Use the following code to fine-tune the model:
+
+```Py
+# Modeled after https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen3_(14B)-Reasoning-Conversational.ipynb
+
+from unsloth import FastLanguageModel
+from unsloth.chat_templates import (
+    get_chat_template,
+    standardize_data_formats,
+    standardize_sharegpt,
+    train_on_responses_only,
+)
+from datasets import load_dataset
+from trl import SFTConfig, SFTTrainer
+import torch
+
+
+max_seq_length = 2048
+dtype = torch.bfloat16
+
+
+# ==============
+#  Model setup |
+# ==============
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "unsloth/Qwen3-8B",
+    max_seq_length = max_seq_length,
+    dtype = dtype,
+    load_in_4bit = False,
+    full_finetuning = False,
+)
+
+model = FastLanguageModel.get_peft_model(
+    model,
+    r = 16,
+    target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
+                      "gate_proj", "up_proj", "down_proj",],
+    lora_alpha = 16,
+    lora_dropout = 0,
+    qat_scheme = "int4",
+)
+tokenizer = get_chat_template(tokenizer, chat_template="qwen3")
+
+
+# =============
+#  Data setup |
+# =============
+
+def format_into_conversation(example):
+    choices = ["A", "B", "C", "D"]
+    correct_choice = choices[example["answer"]]
+    question = "Choose the correct answer for the following question: "
+    question += f"{example['question']}\n\n"
+    question += "Choices:\n"
+    question += f"A. {example['choices'][0]}\n"
+    question += f"B. {example['choices'][1]}\n"
+    question += f"C. {example['choices'][2]}\n"
+    question += f"D. {example['choices'][3]}"
+    answer = f"The correct answer is {correct_choice}."
+    return {"conversations": [
+        {"from": "human", "value": question},
+        {"from": "gpt", "value": answer},
+    ]}
+
+def formatting_prompts_func(examples):
+    convos = examples["conversations"]
+    texts = [tokenizer.apply_chat_template(convo, tokenize = False, add_generation_prompt = False) for convo in convos]
+    return { "text" : texts, }
+
+dataset = load_dataset("cais/mmlu", "all", split="auxiliary_train")
+dataset = dataset.map(format_into_conversation)
+dataset = dataset.remove_columns(["question", "subject", "choices", "answer"])
+dataset = standardize_data_formats(dataset)
+dataset = dataset.map(formatting_prompts_func, batched = True,)
+
+
+# ========
+#  Train |
+# ========
+
+trainer = SFTTrainer(
+    model = model,
+    tokenizer = tokenizer,
+    train_dataset = dataset,
+    dataset_text_field = "text",
+    max_seq_length = max_seq_length,
+    packing = False,
+    args = SFTConfig(
+        per_device_train_batch_size = 32,
+        gradient_accumulation_steps = 1,
+        warmup_steps = 5,
+        num_train_epochs = 1,
+        max_steps = 300,
+        learning_rate = 2e-5,
+        logging_steps = 1,
+        optim = "adamw_8bit",
+        weight_decay = 0.01,
+        lr_scheduler_type = "linear",
+        seed = 3407,
+        output_dir = "outputs",
+        report_to = "none",
+    ),
+)
+
+trainer = train_on_responses_only(
+    trainer,
+    instruction_part = "<|im_start|>user\n",
+    response_part = "<|im_start|>assistant\n",
+)
+trainer_stats = trainer.train()
+
+model.save_pretrained_torchao("/tmp/finetuned_qat_model")
+```
+
+# Model Quality
+We rely on [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) to evaluate the quality of the quantized model.
+
+| Benchmark                        |                |                                 |
+|----------------------------------|----------------|---------------------------------|
+|                                  | mmlu accuracy  | Normalized accuracy degradation | 
+| **Qwen3/Qwen3-8B**               |                |                                 |
+| bf16                             | 73.02          | -0%                             |
+| int4                             | 69.91          | -100%                           |
+| **Fine-tuned without QAT**       |                |                                 |
+| bf16                             | 74.16          | +137%                           |   
+| int4                             | 69.50          | -113%                           |
+| **Fine-tuned with QAT**          |                |                                 |
+| int4                             | 71.12          | -61.1%                          |
+
+<details>
+<summary> Reproduce Model Quality Results </summary>
+
+Need to install lm-eval from source:
+https://github.com/EleutherAI/lm-evaluation-harness#install
+
+## baseline
+```Shell
+lm_eval --model hf --model_args pretrained=Qwen/Qwen3-8B --tasks mmlu --device cuda:0 --batch_size auto
+```
+
+## int4 weight only quantization with quantization-aware training (QAT-INT4)
+```Shell
+export MODEL=pytorch/Qwen3-8B-QAT-INT4
+# or
+# export MODEL=Qwen/Qwen3-8B
+lm_eval --model hf --model_args pretrained=$MODEL --tasks mmlu --device cuda:0 --batch_size auto
+```
+</details>
+
+
+
+# Peak Memory Usage
+
+## Results
+
+| Benchmark        |                |                                |
+|------------------|----------------|--------------------------------|
+|                  | Qwen3-8B       | Qwen3-8B-QAT-INT4              | 
+| Peak Memory (GB) | 16.47          | 6.24 (62% reduction)           |
+
+
+
+<details>
+<summary> Reproduce Peak Memory Usage Results </summary>
+
+We can use the following code to get a sense of peak memory usage during inference:
 
-<!-- Provide a quick summary of what the model is/does. -->
+```Py
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TorchAoConfig
 
+# use "Qwen/Qwen3-8B" or "pytorch/Qwen3-8B-QAT-INT4"
+model_id = "pytorch/Qwen3-8B-QAT-INT4"
+quantized_model = AutoModelForCausalLM.from_pretrained(model_id, device_map="cuda:0", torch_dtype=torch.bfloat16)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
 
+torch.cuda.reset_peak_memory_stats()
 
-## Model Details
+prompt = "Hey, are you conscious? Can you talk to me?"
+messages = [
+    {
+        "role": "system",
+        "content": "",
+    },
+    {"role": "user", "content": prompt},
+]
+templated_prompt = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+print("Prompt:", prompt)
+print("Templated prompt:", templated_prompt)
+inputs = tokenizer(
+    templated_prompt,
+    return_tensors="pt",
+).to("cuda")
+generated_ids = quantized_model.generate(**inputs, max_new_tokens=128)
+output_text = tokenizer.batch_decode(
+    generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
+)
+print("Response:", output_text[0][len(prompt):])
 
-### Model Description
+mem = torch.cuda.max_memory_reserved() / 1e9
+print(f"Peak Memory Usage: {mem:.02f} GB")
+```
 
-<!-- Provide a longer summary of what this model is. -->
+</details>
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
 
-### Model Sources [optional]
+# Model Performance
 
-<!-- Provide the basic links for the model. -->
+Our INT4 model is only optimized for batch size 1, so expect some slowdown with larger batch sizes, we expect this to be used in local server deployment for single or a few users where the decode tokens per second will matters more than the time to first token.
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+## Results
 
-## Uses
+| Benchmark (Latency)              |                |                          |
+|----------------------------------|----------------|--------------------------|
+|                                  | Qwen3-8B       | Qwen3-8B-QAT-INT4        | 
+| latency (batch_size=1)           | 2.50s          | 1.72s (1.45x speedup)    |
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
 
-### Direct Use
+Int4 weight only is optimized for batch size 1 and short input and output token length, please stay tuned for models optimized for larger batch sizes or longer token length.
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 
-[More Information Needed]
 
-### Downstream Use [optional]
+<details>
+<summary> Reproduce Model Performance Results </summary>
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+## Setup
 
-[More Information Needed]
+Get vllm source code:
+```Shell
+git clone [email protected]:vllm-project/vllm.git
+```
 
-### Out-of-Scope Use
+Install vllm
+```
+VLLM_USE_PRECOMPILED=1 pip install --editable .
+```
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+Run the benchmarks under `vllm` root folder:
 
-[More Information Needed]
+## benchmark_latency
 
-## Bias, Risks, and Limitations
+### baseline
+```Shell
+vllm bench latency --input-len 256 --output-len 256 --model Qwen/Qwen3-8B --batch-size 1
+```
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+### QAT INT4
+```Shell
+VLLM_DISABLE_COMPILE_CACHE=1 vllm bench latency --input-len 256 --output-len 256 --model pytorch/Qwen3-8B-QAT-INT4 --batch-size 1
+```
 
-[More Information Needed]
+</details>
 
-### Recommendations
+# Paper: TorchAO: PyTorch-Native Training-to-Serving Model Optimization
+The model's quantization is powered by **TorchAO**, a framework presented in the paper [TorchAO: PyTorch-Native Training-to-Serving Model Optimization](https://huggingface.co/papers/2507.16099).
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+**Abstract:** We present TorchAO, a PyTorch-native model optimization framework leveraging quantization and sparsity to provide an end-to-end, training-to-serving workflow for AI models. TorchAO supports a variety of popular model optimization techniques, including FP8 quantized training, quantization-aware training (QAT), post-training quantization (PTQ), and 2:4 sparsity, and leverages a novel tensor subclass abstraction to represent a variety of widely-used, backend agnostic low precision data types, including INT4, INT8, FP8, MXFP4, MXFP6, and MXFP8. TorchAO integrates closely with the broader ecosystem at each step of the model optimization pipeline, from pre-training (TorchTitan) to fine-tuning (TorchTune, Axolotl) to serving (HuggingFace, vLLM, SGLang, ExecuTorch), connecting an otherwise fragmented space in a single, unified workflow. TorchAO has enabled recent launches of the quantized Llama 3.2 1B/3B and LlamaGuard3-8B models and is open-source at this https URL .
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+# Resources
+*   **Official TorchAO GitHub Repository:** [https://github.com/pytorch/ao](https://github.com/pytorch/ao)
+*   **TorchAO Documentation:** [https://docs.pytorch.org/ao/stable/index.html](https://docs.pytorch.org/ao/stable/index.html)
 
-## How to Get Started with the Model
 
-Use the code below to get started with the model.
+# Disclaimer
+PyTorch has not performed safety evaluations or red teamed the quantized models. Performance characteristics, outputs, and behaviors may differ from the original models. Users are solely responsible for selecting appropriate use cases, evaluating and mitigating for accuracy, safety, and fairness, ensuring security, and complying with all applicable laws and regulations.
 
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+Nothing contained in this Model Card should be interpreted as or deemed a restriction or modification to the licenses the models are released under, including any limitations of liability or disclaimers of warranties provided therein.