Upload README.md with huggingface_hub

README.md

@@ -1,199 +1,235 @@
 ---
-library_name: transformers
-tags: []
+base_model: Qwen/Qwen3-8B-Base
+tags:
+- transformers
+- torchao
+- qwen3
+license: apache-2.0
+language:
+- en
 ---
 
-# Model Card for Model ID
+# INT8-INT4 Qwen/Qwen3-8B-Base model
 
-<!-- Provide a quick summary of what the model is/does. -->
+- **Developed by:** q10
+- **License:** apache-2.0
+- **Quantized from Model :** Qwen/Qwen3-8B-Base
+- **Quantization Method :** INT8-INT4
 
 
 
-## Model Details
 
-### Model Description
+# Running in a mobile app
+(TODO: pte file name generation)
+The [pte file](https://huggingface.co/q10/Qwen3-8B-Base-INT8-INT4/blob/main/qwen3-4B-INT8-INT4-1024-cxt.pte) can be run with ExecuTorch on a mobile phone.  See the [instructions](https://pytorch.org/executorch/main/llm/llama-demo-ios.html) for doing this in iOS.
+On iPhone 15 Pro, the model runs at (to be filled) tokens/sec and uses (to be filled) Mb of memory.
 
-<!-- Provide a longer summary of what this model is. -->
+TODO: attach image
 
-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]
+# Quantization Recipe
 
-### Model Sources [optional]
+Install the required packages:
+```Shell
+pip install git+https://github.com/huggingface/transformers@main
+pip install --pre torchao --index-url https://download.pytorch.org/whl/nightly/cu126
+pip install torch
+pip install accelerate
+```
+
+
+## Untie Embedding Weights
+We want to quantize the embedding and lm_head differently.  Since those layers are tied, we first need to untie the model:
+
+```Py
+from transformers import (
+  AutoModelForCausalLM,
+  AutoProcessor,
+  AutoTokenizer,
+)
+import torch
+
+model_id = "{base_model}"
+untied_model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+print(untied_model)
+from transformers.modeling_utils import find_tied_parameters
+print("tied weights:", find_tied_parameters(untied_model))
+if getattr(untied_model.config.get_text_config(decoder=True), "tie_word_embeddings"):
+    setattr(untied_model.config.get_text_config(decoder=True), "tie_word_embeddings", False)
+
+untied_model._tied_weights_keys = []
+untied_model.lm_head.weight = torch.nn.Parameter(untied_model.lm_head.weight.clone())
+
+print("tied weights:", find_tied_parameters(untied_model))
+
+USER_ID = "YOUR_USER_ID"
+MODEL_NAME = model_id.split("/")[-1]
+save_to = f"{{USER_ID}}/{{MODEL_NAME}}-untied-weights"
+
+# save locally (we use this in the recipe)
+save_to_local_path = f"{{MODEL_NAME}}-untied-weights"
+untied_model.save_pretrained(save_to_local_path)
+tokenizer.save_pretrained(save_to_local_path)
+
+
+# or push to hub
+untied_model.push_to_hub(save_to)
+tokenizer.push_to_hub(save_to)
+```
+
+Note: to `push_to_hub` you need to run
+```Shell
+pip install -U "huggingface_hub[cli]"
+huggingface-cli login
+```
+and use a token with write access, from https://huggingface.co/settings/tokens
+
+## Quantization
+
+
+Use the following code to get the quantized model:
+```Py
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TorchAoConfig
 
-<!-- Provide the basic links for the model. -->
+model_id = "Qwen/Qwen3-8B-Base"
+model_to_quantize = "f"{{MODEL_NAME}}-untied-weights""
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
 
-## Uses
+from torchao.quantization.quant_api import (
+    IntxWeightOnlyConfig,
+    Int8DynamicActivationIntxWeightConfig,
+    ModuleFqnToConfig,
+)
+from torchao.quantization.granularity import PerGroup, PerAxis
+embedding_config = IntxWeightOnlyConfig(
+    weight_dtype=torch.int8,
+    granularity=PerAxis(0),
+)
+linear_config = Int8DynamicActivationIntxWeightConfig(
+    weight_dtype=torch.int4,
+    weight_granularity=PerGroup(32),
+    weight_scale_dtype=torch.bfloat16,
+)
+quant_config = ModuleFqnToConfig({{"_default": linear_config, "model.embed_tokens": embedding_config}})
+quantization_config = TorchAoConfig(quant_type=quant_config, include_embedding=True, untie_embedding_weights=True, modules_to_not_convert=[])
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+quantized_model = AutoModelForCausalLM.from_pretrained(model_to_quantize, device_map="auto", torch_dtype=torch.bfloat16, quantization_config=quantization_config)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
 
-### Direct Use
+# Push to hub
+USER_ID = "YOUR_USER_ID"
+MODEL_NAME = model_id.split("/")[-1]
+save_to = f"{USER_ID}/{MODEL_NAME}-INT8-INT4"
+quantized_model.push_to_hub(save_to, safe_serialization=False)
+tokenizer.push_to_hub(save_to)
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+# Manual Testing
+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):])
+```
 
-[More Information Needed]
+Note: to `push_to_hub` you need to run
+```Shell
+pip install -U "huggingface_hub[cli]"
+huggingface-cli login
+```
+and use a token with write access, from https://huggingface.co/settings/tokens
 
-### Downstream Use [optional]
+# Model Quality
+We rely on [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) to evaluate the quality of the quantized model. Here we only run on mmlu for sanity check.
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+| Benchmark                        |                |                           |
+|----------------------------------|----------------|---------------------------|
+|                                  | Qwen/Qwen3-8B-Base   | q10/Qwen3-8B-Base-INT8-INT4         |
+| mmlu                             | To be filled   | To be filled                      |
 
-[More Information Needed]
 
-### Out-of-Scope Use
+<details>
+<summary> Reproduce Model Quality Results </summary>
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+Need to install lm-eval from source:
+https://github.com/EleutherAI/lm-evaluation-harness#install
 
-[More Information Needed]
+## baseline
+```Shell
+lm_eval --model hf --model_args pretrained=Qwen/Qwen3-8B-Base --tasks mmlu --device cuda:0 --batch_size 8
+```
+
+## INT8-INT4
+```Shell
+export MODEL=q10/Qwen3-8B-Base-INT8-INT4
+lm_eval --model hf --model_args pretrained=$MODEL --tasks mmlu --device cuda:0 --batch_size 8
+```
+</details>
 
-## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
 
-[More Information Needed]
 
-### Recommendations
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
 
-## How to Get Started with the Model
 
-Use the code below to get started with the model.
 
-[More Information Needed]
+# Exporting to ExecuTorch
 
-## Training Details
+We can run the quantized model on a mobile phone using [ExecuTorch](https://github.com/pytorch/executorch).
+Once ExecuTorch is [set-up](https://pytorch.org/executorch/main/getting-started.html), exporting and running the model on device is a breeze.
+
+We first convert the [quantized checkpoint](https://huggingface.co/q10/Qwen3-8B-Base-INT8-INT4/blob/main/pytorch_model.bin) to one ExecuTorch's LLM export script expects by renaming some of the checkpoint keys.
+The following script does this for you.  We have uploaded the converted checkpoint [pytorch_model_converted.bin](https://huggingface.co/q10/Qwen3-8B-Base-INT8-INT4/blob/main/pytorch_model_converted.bin) for convenience.
+```Shell
+python -m executorch.examples.models.qwen3.convert_weights $(huggingface-cli download q10/Qwen3-8B-Base-INT8-INT4) pytorch_model_converted.bin
+```
 
-### Training Data
+Once the checkpoint is converted, we can export to ExecuTorch's pte format with the XNNPACK delegate.
+The below command exports with a max_seq_length/max_context_length of 1024, but it can be changed as desired.
 
-<!-- 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. -->
+(TODO: pte file name, model config path, model name auto generation)
+```Shell
+PARAMS="executorch/examples/models/qwen3/4b_config.json"
+python -m executorch.examples.models.llama.export_llama   --model "qwen3-4b"   --checkpoint "pytorch_model_converted.bin"   --params "$PARAMS"   -kv   --use_sdpa_with_kv_cache   -d fp32
+  -X   --metadata '{"get_bos_id":199999, "get_eos_ids":[200020,199999]}'   --max_seq_length 1024   --max_context_length 1024   --output_name="qwen3-4b-INT8-INT4-1024-cxt.pte"
+```
 
-[More Information Needed]
+After that you can run the model in a mobile app (see [Running in a mobile app](#running-in-a-mobile-app)).
 
-### Training Procedure
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+# 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).
 
-#### Preprocessing [optional]
+**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 .
 
-[More Information Needed]
+# 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)
 
 
-#### Training Hyperparameters
+# 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.
 
-- **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.