|
--- |
|
tags: |
|
- fp8 |
|
- vllm |
|
- medical |
|
- med |
|
license: other |
|
license_name: writer-open-model-license |
|
license_link: https://writer.com/legal/open-model-license/ |
|
language: |
|
- en |
|
--- |
|
|
|
# Palmyra-Med-70B-FP8 |
|
This is a quantized version of [Palmyra-Med-70B](https://huggingface.co/Writer/Palmyra-Med-70B), which was developed by Writer. |
|
|
|
The original model performance on biomedical benchmarks is 85.87%. |
|
**This quantized version acheives an average score of 85.62%.** |
|
|
|
## Model Overview: |
|
- **Model:** Llama based model finetuned to form Palmyra-X-004 and then again to form Palmyra-Med-70B. |
|
- **Input:** Text |
|
- **Output:** Text |
|
- **Model Optimizations:** |
|
- **Weight quantization:** FP8 |
|
- **Activation quantization:** FP8 |
|
- **Intended Use Cases:** Palmyra-Medical-70B-FP8 is intended for non-commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks. |
|
- **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. |
|
- **License(s):** [writer-open-model-license](https://writer.com/legal/open-model-license/) |
|
|
|
### Writer Resources and Technical Documentation: |
|
+ [Writer Blog](https://writer.com/blog/palmyra-med-fin-models/) |
|
+ [Writer Developer Website](https://dev.writer.com/home/models) |
|
+ [Writer AI Studio](https://writer.com/product/ai-studio/) |
|
+ [Palmyra Model API](https://dev.writer.com/api-guides/chat-completion) |
|
|
|
### Model Optimizations |
|
|
|
[LLM_Compressor](https://github.com/vllm-project/llm-compressor) library. |
|
Using this optimization, the original FP16 weights and linear activations within the transformer blocks are adjusted to FP8, which decreases the model size and VRAM requirements by 50% overall. |
|
|
|
## Deployment with vLLM |
|
|
|
This model can be deployed using the [vLLM](https://docs.vllm.ai/en/latest/) library, as shown in the example below. |
|
|
|
```python |
|
from vllm import LLM, SamplingParams |
|
from transformers import AutoTokenizer |
|
|
|
model_id = "bprice9/Palmyra-Medical-70B-FP8" |
|
number_gpus = 2 |
|
|
|
sampling_params = SamplingParams(temperature=0.0, top_p=0.9, max_tokens=512, stop_token_ids=[128001, 128009]) |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id) |
|
|
|
messages = [ |
|
{"role": "user", "content": "Give a differential for an intrahepatic lesion with early arterial phase enhancement and rapid washout."}, |
|
] |
|
prompts = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False) |
|
|
|
llm = LLM(model=model_id, tensor_parallel_size=number_gpus) |
|
|
|
outputs = llm.generate(prompts, sampling_params) |
|
|
|
generated_text = outputs[0].outputs[0].text |
|
print(generated_text) |
|
``` |
|
|
|
## Creation |
|
|
|
This model was created by applying [LLM Compressor with calibration samples from UltraChat](https://github.com/vllm-project/llm-compressor/blob/sa/big_model_support/examples/big_model_offloading/big_model_w8a8_calibrate.py), as presented in the code below. |
|
|
|
```python |
|
import torch |
|
from datasets import load_dataset |
|
from transformers import AutoTokenizer |
|
from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot |
|
from llmcompressor.transformers.compression.helpers import ( |
|
calculate_offload_device_map, |
|
custom_offload_device_map, |
|
) |
|
recipe = """ |
|
quant_stage: |
|
quant_modifiers: |
|
QuantizationModifier: |
|
ignore: ["lm_head"] |
|
config_groups: |
|
group_0: |
|
weights: |
|
num_bits: 8 |
|
type: float |
|
strategy: tensor |
|
dynamic: false |
|
symmetric: true |
|
input_activations: |
|
num_bits: 8 |
|
type: float |
|
strategy: tensor |
|
dynamic: false |
|
symmetric: true |
|
targets: ["Linear"] |
|
""" |
|
model_stub = "Writer/Palmyra-Med-70B" |
|
model_name = model_stub.split("/")[-1] |
|
device_map = calculate_offload_device_map( |
|
model_stub, reserve_for_hessians=False, num_gpus=2, torch_dtype=torch.float16 |
|
) |
|
model = SparseAutoModelForCausalLM.from_pretrained( |
|
model_stub, torch_dtype=torch.float16, device_map=device_map |
|
) |
|
tokenizer = AutoTokenizer.from_pretrained(model_stub) |
|
output_dir = f"./{model_name}-FP8" |
|
DATASET_ID = "HuggingFaceH4/ultrachat_200k" |
|
DATASET_SPLIT = "train_sft" |
|
NUM_CALIBRATION_SAMPLES = 128 |
|
MAX_SEQUENCE_LENGTH = 4096 |
|
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT) |
|
ds = ds.shuffle(seed=42).select(range(NUM_CALIBRATION_SAMPLES)) |
|
def preprocess(example): |
|
return { |
|
"text": tokenizer.apply_chat_template( |
|
example["messages"], |
|
tokenize=False, |
|
) |
|
} |
|
ds = ds.map(preprocess) |
|
def tokenize(sample): |
|
return tokenizer( |
|
sample["text"], |
|
padding=False, |
|
max_length=MAX_SEQUENCE_LENGTH, |
|
truncation=True, |
|
add_special_tokens=False, |
|
) |
|
ds = ds.map(tokenize, remove_columns=ds.column_names) |
|
oneshot( |
|
model=model, |
|
output_dir=output_dir, |
|
dataset=ds, |
|
recipe=recipe, |
|
max_seq_length=MAX_SEQUENCE_LENGTH, |
|
num_calibration_samples=NUM_CALIBRATION_SAMPLES, |
|
save_compressed=True, |
|
) |
|
``` |
|
|
|
## Evaluation |
|
|
|
<table> |
|
<tr> |
|
<td style="width: 20%;"><strong>Biomedical Benchmark</strong> |
|
</td> |
|
<td style="width: 20%;"><strong>Med-PaLM-2 (5-shot)</strong> |
|
</td> |
|
<td style="width: 20%;"><strong>GPT-4</strong> |
|
</td> |
|
<td style="width: 20%;"><strong>Palmyra-Med-70B (Original FP16)</strong> |
|
</td> |
|
<td style="width: 20%;"><strong>Palmyra-Medical-70B-FP8 (This Model)</strong> |
|
</td> |
|
</tr> |
|
<tr> |
|
<td>MMLU Clincal Knowledge |
|
</td> |
|
<td>88.3 |
|
</td> |
|
<td>86.0 |
|
</td> |
|
<td>90.9 |
|
</td> |
|
<td>90.2 |
|
</td> |
|
</tr> |
|
<tr> |
|
<td>MMLU Medical Genetics |
|
</td> |
|
<td>90.0 |
|
</td> |
|
<td>91.0 |
|
</td> |
|
<td>94.0 |
|
</td> |
|
<td>93.0 |
|
</td> |
|
</tr> |
|
<tr> |
|
<td>MMLU Anatomy |
|
</td> |
|
<td>77.8 |
|
</td> |
|
<td>80.0 |
|
</td> |
|
<td>83.7 |
|
</td> |
|
<td>83.7 |
|
</td> |
|
</tr> |
|
<tr> |
|
<td>MMLU Professional Medicine |
|
</td> |
|
<td>95.2 |
|
</td> |
|
<td>93.0 |
|
</td> |
|
<td>92.7 |
|
</td> |
|
<td>92.3 |
|
</td> |
|
</tr> |
|
<tr> |
|
<td>MMLU College Biology |
|
</td> |
|
<td>94.4 |
|
</td> |
|
<td>95.1 |
|
</td> |
|
<td>94.4 |
|
</td> |
|
<td>93.8 |
|
</td> |
|
</tr> |
|
<tr> |
|
<td>MMLU College Medicine |
|
</td> |
|
<td>80.9 |
|
</td> |
|
<td>76.9 |
|
</td> |
|
<td>84.4 |
|
</td> |
|
<td>84.4 |
|
</td> |
|
</tr> |
|
<tr> |
|
<td>MedQA 4-options |
|
</td> |
|
<td>79.9 |
|
</td> |
|
<td>78.9 |
|
</td> |
|
<td>78.6 |
|
</td> |
|
<td>79.5 |
|
</td> |
|
</tr> |
|
<tr> |
|
<td>PubMed QA |
|
</td> |
|
<td>79.2 |
|
</td> |
|
<td>75.2 |
|
</td> |
|
<td>79.6 |
|
</td> |
|
<td>78.0 |
|
</td> |
|
</tr> |
|
<tr> |
|
<tr> |
|
<td>MedMCQA |
|
</td> |
|
<td>71.3 |
|
</td> |
|
<td>69.5 |
|
</td> |
|
<td>74.4 |
|
</td> |
|
<td>75.7 |
|
</td> |
|
</tr> |
|
<tr> |
|
<td><strong>Average</strong> |
|
</td> |
|
<td><strong>84.1</strong> |
|
</td> |
|
<td><strong>82.8</strong> |
|
</td> |
|
<td><strong>85.9</strong> |
|
</td> |
|
<td><strong>85.6</strong> |
|
</td> |
|
</tr> |
|
</table> |
|
|
|
### Citation and Related Information Provided by Writer |
|
|
|
To cite this model: |
|
|
|
``` |
|
@misc{Palmyra-Med-70B, |
|
author = {Writer Engineering team}, |
|
title = {{Palmyra-Med-70b: A powerful LLM designed for healthcare}}, |
|
howpublished = {\url{https://dev.writer.com}}, |
|
year = 2024, |
|
month = June |
|
} |
|
``` |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
