Update README.md

README.md

@@ -1,199 +1,109 @@
----
-library_name: transformers
-tags: []
----
-
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-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]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- 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
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## 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]
-
-## 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]
+```
+model: opt-125m
+config: ModuleFqnToConfig
+with Float8DynamicActivationFloat8WeightConfig, Int4WeightOnlyConfig and IntxWeightOnlyConfig
+config version: 1
+torchao version: 0.14.dev
+```
+
+```
+import logging
+
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TorchAoConfig
+
+# Configure logging to see warnings and debug information
+logging.basicConfig(
+    level=logging.INFO, format="%(name)s - %(levelname)s - %(message)s"
+)
+
+# Enable specific loggers that might contain the serialization warnings
+logging.getLogger("transformers").setLevel(logging.INFO)
+logging.getLogger("torchao").setLevel(logging.INFO)
+logging.getLogger("safetensors").setLevel(logging.INFO)
+logging.getLogger("huggingface_hub").setLevel(logging.INFO)
+
+model_id = "facebook/opt-125m"
+
+from torchao.quantization import (
+    Float8DynamicActivationFloat8WeightConfig,
+    Int4WeightOnlyConfig,
+    IntxWeightOnlyConfig,
+    PerRow,
+    PerAxis,
+    ModuleFqnToConfig,
+    Float8Tensor,
+    Int4TilePackedTo4dTensor,
+    IntxUnpackedToInt8Tensor,
+)
+
+float8dyn = Float8DynamicActivationFloat8WeightConfig(granularity=PerRow())
+int4wo = Int4WeightOnlyConfig(int4_packing_format="tile_packed_to_4d")
+intxwo = IntxWeightOnlyConfig(weight_dtype=torch.int8, granularity=PerAxis(0))
+
+qconfig_dict = {
+    # highest priority
+    "model.decoder.layers.3.self_attn.q_proj": int4wo,
+    "model.decoder.layers.*.self_attn.q_proj": float8dyn,
+    "model.decoder.layers.*.self_attn.k_proj": float8dyn,
+    "model.decoder.layers.*.self_attn.v_proj": None,
+    "_default": intxwo,
+}
+quant_config = ModuleFqnToConfig(qconfig_dict)
+quantization_config = TorchAoConfig(quant_type=quant_config)
+quantized_model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="auto",
+    torch_dtype=torch.bfloat16,
+    quantization_config=quantization_config,
+)
+print("quantized model:", quantized_model)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+for i in range(12):
+    if i == 3:
+        print("type:", quantized_model.model.decoder.layers[i].self_attn.q_proj.weight)
+        assert isinstance(quantized_model.model.decoder.layers[i].self_attn.q_proj.weight, Int4TilePackedTo4dTensor)
+    else:
+        assert isinstance(quantized_model.model.decoder.layers[i].self_attn.q_proj.weight, Float8Tensor)
+    assert isinstance(quantized_model.model.decoder.layers[i].self_attn.k_proj.weight, Float8Tensor)
+    assert not isinstance(quantized_model.model.decoder.layers[i].self_attn.v_proj.weight, Float8Tensor)
+    assert isinstance(quantized_model.model.decoder.layers[i].self_attn.out_proj.weight, IntxUnpackedToInt8Tensor)
+
+# Push to hub
+MODEL_NAME = model_id.split("/")[-1]
+save_to = f"torchao-testing/{MODEL_NAME}-ModuleFqnToConfig-v1-regex-0.14.0.dev"
+quantized_model.push_to_hub(save_to, safe_serialization=False)
+tokenizer.push_to_hub(save_to)
+
+# Manual Testing
+prompt = "What are we having for dinner?"
+print("Prompt:", prompt)
+inputs = tokenizer(
+    prompt,
+    return_tensors="pt",
+).to("cuda")
+# setting temperature to 0 to make sure result deterministic
+generated_ids = quantized_model.generate(**inputs, max_new_tokens=128, temperature=0)
+
+correct_output_text = tokenizer.batch_decode(
+    generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
+)
+print("Response:", correct_output_text[0][len(prompt) :])
+
+
+# # # Load model from saved checkpoint
+reloaded_model = AutoModelForCausalLM.from_pretrained(
+    save_to,
+    device_map="cuda:0",
+    torch_dtype=torch.bfloat16,
+    # quantization_config=quantization_config,
+)
+
+generated_ids = reloaded_model.generate(**inputs, max_new_tokens=128, temperature=0)
+output_text = tokenizer.batch_decode(
+    generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
+)
+print("Response:", output_text[0][len(prompt) :])
+
+assert(correct_output_text == output_text)
+```