|
--- |
|
language: |
|
- en |
|
pipeline_tag: text-generation |
|
license: apache-2.0 |
|
license_link: https://www.apache.org/licenses/LICENSE-2.0 |
|
--- |
|
|
|
# Qwen2-72B-Instruct-quantized.w4a16 |
|
|
|
## Model Overview |
|
- **Model Architecture:** Qwen2 |
|
- **Input:** Text |
|
- **Output:** Text |
|
- **Model Optimizations:** |
|
- **Weight quantization:** INT4 |
|
- **Intended Use Cases:** Intended for commercial and research use in English. Similarly to [Qwen2-72B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct), this models is intended for assistant-like chat. |
|
- **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. |
|
- **Release Date:** 7/11/2024 |
|
- **Version:** 1.0 |
|
- **License(s):** [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) |
|
- **Model Developers:** Neural Magic |
|
|
|
Quantized version of [Qwen2-72B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct). |
|
It achieves an average score of 68.35 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 69.63. |
|
|
|
### Model Optimizations |
|
|
|
This model was obtained by quantizing the weights of [Qwen2-72B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct) to INT4 data type. |
|
This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 25%. |
|
|
|
Only the weights of the linear operators within transformers blocks are quantized. Symmetric group-wise quantization is applied, in which a linear scaling per group maps the INT4 and floating point representations of the quantized weights. |
|
[AutoGPTQ](https://github.com/AutoGPTQ/AutoGPTQ) is used for quantization with 10% damping factor, group-size as 128 and 512 sequences sampled from [Open-Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus). |
|
|
|
|
|
## Deployment |
|
|
|
### Use with vLLM |
|
|
|
This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below. |
|
|
|
```python |
|
from vllm import LLM, SamplingParams |
|
from transformers import AutoTokenizer |
|
|
|
model_id = "neuralmagic/Qwen2-72B-Instruct-quantized.w4a16" |
|
|
|
sampling_params = SamplingParams(temperature=0.6, top_p=0.9, max_tokens=256) |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id) |
|
|
|
messages = [ |
|
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, |
|
{"role": "user", "content": "Who are you?"}, |
|
] |
|
|
|
prompts = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) |
|
|
|
llm = LLM(model=model_id, tensor_parallel_size=1) |
|
|
|
outputs = llm.generate(prompts, sampling_params) |
|
|
|
generated_text = outputs[0].outputs[0].text |
|
print(generated_text) |
|
``` |
|
|
|
vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details. |
|
|
|
### Use with transformers |
|
|
|
This model is supported by Transformers leveraging the integration with the [AutoGPTQ](https://github.com/AutoGPTQ/AutoGPTQ) data format. |
|
The following example contemplates how the model can be used using the `generate()` function. |
|
|
|
```python |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
model_id = "neuralmagic/Qwen2-72B-Instruct-quantized.w4a16" |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id) |
|
model = AutoModelForCausalLM.from_pretrained( |
|
model_id, |
|
torch_dtype="auto", |
|
device_map="auto", |
|
) |
|
|
|
messages = [ |
|
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, |
|
{"role": "user", "content": "Who are you?"}, |
|
] |
|
|
|
input_ids = tokenizer.apply_chat_template( |
|
messages, |
|
add_generation_prompt=True, |
|
return_tensors="pt" |
|
).to(model.device) |
|
|
|
terminators = [ |
|
tokenizer.eos_token_id, |
|
tokenizer.convert_tokens_to_ids("<|eot_id|>") |
|
] |
|
|
|
outputs = model.generate( |
|
input_ids, |
|
max_new_tokens=256, |
|
eos_token_id=terminators, |
|
do_sample=True, |
|
temperature=0.6, |
|
top_p=0.9, |
|
) |
|
response = outputs[0][input_ids.shape[-1]:] |
|
print(tokenizer.decode(response, skip_special_tokens=True)) |
|
``` |
|
|
|
## Creation |
|
|
|
This model was created by applying the [AutoGPTQ](https://github.com/AutoGPTQ/AutoGPTQ) library as presented in the code snipet below. |
|
Although AutoGPTQ was used for this particular model, Neural Magic is transitioning to using [llm-compressor](https://github.com/vllm-project/llm-compressor) which supports several quantization schemes and models not supported by AutoGPTQ. |
|
|
|
```python |
|
from transformers import AutoTokenizer |
|
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig |
|
from datasets import load_dataset |
|
import random |
|
|
|
model_id = "Qwen/Qwen2-72B-Instruct" |
|
|
|
num_samples = 512 |
|
max_seq_len = 4096 |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id) |
|
|
|
preprocess_fn = lambda example: {"text": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n{text}".format_map(example)} |
|
|
|
dataset_name = "neuralmagic/LLM_compression_calibration" |
|
dataset = load_dataset(dataset_name, split="train") |
|
ds = dataset.shuffle().select(range(num_samples)) |
|
ds = ds.map(preprocess_fn) |
|
|
|
examples = [ |
|
tokenizer( |
|
example["text"], padding=False, max_length=max_seq_len, truncation=True, |
|
) for example in ds |
|
] |
|
|
|
quantize_config = BaseQuantizeConfig( |
|
bits=4, |
|
group_size=128, |
|
desc_act=True, |
|
model_file_base_name="model", |
|
damp_percent=0.1, |
|
) |
|
|
|
model = AutoGPTQForCausalLM.from_pretrained( |
|
model_id, |
|
quantize_config, |
|
device_map="auto", |
|
) |
|
|
|
model.quantize(examples) |
|
model.save_pretrained("Qwen2-72B-Instruct-quantized.w4a16") |
|
``` |
|
|
|
|
|
|
|
## Evaluation |
|
|
|
The model was evaluated on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) leaderboard tasks (version 1) with the [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness/tree/383bbd54bc621086e05aa1b030d8d4d5635b25e6) (commit 383bbd54bc621086e05aa1b030d8d4d5635b25e6) and the [vLLM](https://docs.vllm.ai/en/stable/) engine, using the following command: |
|
``` |
|
lm_eval \ |
|
--model vllm \ |
|
--model_args pretrained="neuralmagic/Qwen2-72B-Instruct-quantized.w4a16",dtype=auto,tensor_parallel_size=1,gpu_memory_utilization=0.4,add_bos_token=True,max_model_len=4096 \ |
|
--tasks openllm \ |
|
--batch_size auto |
|
``` |
|
|
|
### Accuracy |
|
|
|
#### Open LLM Leaderboard evaluation scores |
|
<table> |
|
<tr> |
|
<td><strong>Benchmark</strong> |
|
</td> |
|
<td><strong>Qwen2-72B-Instruct </strong> |
|
</td> |
|
<td><strong>Qwen2-72B-Instruct-quantized.w4a16(this model)</strong> |
|
</td> |
|
<td><strong>Recovery</strong> |
|
</td> |
|
</tr> |
|
<tr> |
|
<td>MMLU (5-shot) |
|
</td> |
|
<td>83.96 |
|
</td> |
|
<td>83.41 |
|
</td> |
|
<td>99.35% |
|
</td> |
|
</tr> |
|
<tr> |
|
<td>ARC Challenge (25-shot) |
|
</td> |
|
<td>71.58 |
|
</td> |
|
<td>71.84 |
|
</td> |
|
<td>100.36% |
|
</td> |
|
</tr> |
|
<tr> |
|
<td>GSM-8K (5-shot, strict-match) |
|
</td> |
|
<td>88.24 |
|
</td> |
|
<td>88.93 |
|
</td> |
|
<td>100.78% |
|
</td> |
|
</tr> |
|
<tr> |
|
<td>Hellaswag (10-shot) |
|
</td> |
|
<td>86.94 |
|
</td> |
|
<td>86.31 |
|
</td> |
|
<td>99.28% |
|
</td> |
|
</tr> |
|
<tr> |
|
<td>Winogrande (5-shot) |
|
</td> |
|
<td>82.79 |
|
</td> |
|
<td>83.50 |
|
</td> |
|
<td>100.86% |
|
</td> |
|
</tr> |
|
<tr> |
|
<td>TruthfulQA (0-shot) |
|
</td> |
|
<td>66.98 |
|
</td> |
|
<td>66.21 |
|
</td> |
|
<td>98.85% |
|
</td> |
|
</tr> |
|
<tr> |
|
<td><strong>Average</strong> |
|
</td> |
|
<td><strong>80.08</strong> |
|
</td> |
|
<td><strong>80.03</strong> |
|
</td> |
|
<td><strong>99.94%</strong> |
|
</td> |
|
</tr> |
|
</table> |
