449 lines
12 KiB
Markdown
449 lines
12 KiB
Markdown
---
|
||
language:
|
||
- zh
|
||
- en
|
||
- fr
|
||
- es
|
||
- pt
|
||
- de
|
||
- it
|
||
- ru
|
||
- ja
|
||
- ko
|
||
- vi
|
||
- th
|
||
- ar
|
||
- id
|
||
- tr
|
||
- fa
|
||
- nl
|
||
- pl
|
||
- cs
|
||
- he
|
||
- sv
|
||
- fi
|
||
- da
|
||
- no
|
||
- el
|
||
- bg
|
||
- uk
|
||
- ur
|
||
- sr
|
||
- ms
|
||
- zsm
|
||
- nld
|
||
base_model:
|
||
- Qwen/Qwen2.5-7B-Instruct
|
||
pipeline_tag: text-generation
|
||
tags:
|
||
- qwen
|
||
- qwen2_5
|
||
- qwen2_5_instruct
|
||
- w8a8
|
||
- int8
|
||
- vllm
|
||
- conversational
|
||
- text-generation-inference
|
||
- compressed-tensors
|
||
license: apache-2.0
|
||
license_name: apache-2.0
|
||
name: RedHatAI/Qwen2.5-7B-Instruct-quantized.w8a8
|
||
description: This model was obtained by quantizing the weights and activations of Qwen2.5-7B-Instruct to INT8 data type.
|
||
readme: https://huggingface.co/RedHatAI/Qwen2.5-7B-Instruct-quantized.w8a8/main/README.md
|
||
tasks:
|
||
- text-to-text
|
||
provider: Alibaba Cloud
|
||
license_link: https://www.apache.org/licenses/LICENSE-2.0
|
||
validated_on:
|
||
- RHOAI 2.20
|
||
- RHAIIS 3.0
|
||
- RHELAI 1.5
|
||
- vLLM 0.8.4
|
||
---
|
||
|
||
<h1 style="display: flex; align-items: center; gap: 10px; margin: 0;">
|
||
Qwen2.5-7B-Instruct-quantized.w8a8
|
||
<img src="https://www.redhat.com/rhdc/managed-files/Catalog-Validated_model_0.png" alt="Model Icon" width="40" style="margin: 0; padding: 0;" />
|
||
</h1>
|
||
|
||
<a href="https://www.redhat.com/en/products/ai/validated-models" target="_blank" style="margin: 0; padding: 0;">
|
||
<img src="https://www.redhat.com/rhdc/managed-files/Validated_badge-Dark.png" alt="Validated Badge" width="250" style="margin: 0; padding: 0;" />
|
||
</a>
|
||
|
||
## Model Overview
|
||
- **Model Architecture:** Qwen2
|
||
- **Input:** Text
|
||
- **Output:** Text
|
||
- **Model Optimizations:**
|
||
- **Activation quantization:** INT8
|
||
- **Weight quantization:** INT8
|
||
- **Intended Use Cases:** Intended for commercial and research use multiple languages. Similarly to [Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B), 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).
|
||
- **Release Date:** 10/09/2024
|
||
- **Version:** 1.0
|
||
- **Validated on:** RHOAI 2.20, RHAIIS 3.0, RHELAI 1.5
|
||
- **License(s):** [apache-2.0](https://huggingface.co/Qwen/Qwen2.5-7B/blob/main/LICENSE)
|
||
- **Model Developers:** Neural Magic
|
||
|
||
### Model Optimizations
|
||
|
||
This model was obtained by quantizing activations and weights of [Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) to INT8 data type.
|
||
This optimization reduces the number of bits used to represent weights and activations from 16 to 8, reducing GPU memory requirements (by approximately 50%) and increasing matrix-multiply compute throughput (by approximately 2x).
|
||
Weight quantization also reduces disk size requirements by approximately 50%.
|
||
|
||
Only weights and activations of the linear operators within transformers blocks are quantized.
|
||
Weights are quantized with a symmetric static per-channel scheme, whereas activations are quantized with a symmetric dynamic per-token scheme.
|
||
A combination of the [SmoothQuant](https://arxiv.org/abs/2211.10438) and [GPTQ](https://arxiv.org/abs/2210.17323) algorithms is applied for quantization, as implemented in the [llm-compressor](https://github.com/vllm-project/llm-compressor) library.
|
||
|
||
## Deployment
|
||
|
||
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 = "RedHatAI/Qwen2.5-7B-Instruct-quantized.w8a8"
|
||
number_gpus = 1
|
||
max_model_len = 8192
|
||
|
||
sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)
|
||
|
||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||
|
||
messages = [
|
||
{"role": "user", "content": "Give me a short introduction to large language model."},
|
||
]
|
||
|
||
prompts = tokenizer.apply_chat_template(messages, tokenize=False)
|
||
|
||
llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len)
|
||
|
||
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.
|
||
|
||
<details>
|
||
<summary>Deploy on <strong>Red Hat AI Inference Server</strong></summary>
|
||
|
||
```bash
|
||
podman run --rm -it --device nvidia.com/gpu=all -p 8000:8000 \
|
||
--ipc=host \
|
||
--env "HUGGING_FACE_HUB_TOKEN=$HF_TOKEN" \
|
||
--env "HF_HUB_OFFLINE=0" -v ~/.cache/vllm:/home/vllm/.cache \
|
||
--name=vllm \
|
||
registry.access.redhat.com/rhaiis/rh-vllm-cuda \
|
||
vllm serve \
|
||
--tensor-parallel-size 8 \
|
||
--max-model-len 32768 \
|
||
--enforce-eager --model RedHatAI/Qwen2.5-7B-Instruct-quantized.w8a8
|
||
```
|
||
See [Red Hat AI Inference Server documentation](https://docs.redhat.com/en/documentation/red_hat_ai_inference_server/) for more details.
|
||
</details>
|
||
|
||
<details>
|
||
<summary>Deploy on <strong>Red Hat Enterprise Linux AI</strong></summary>
|
||
|
||
```bash
|
||
# Download model from Red Hat Registry via docker
|
||
# Note: This downloads the model to ~/.cache/instructlab/models unless --model-dir is specified.
|
||
ilab model download --repository docker://registry.redhat.io/rhelai1/qwen2-5-7b-instruct-quantized-w8a8:1.5
|
||
```
|
||
|
||
```bash
|
||
# Serve model via ilab
|
||
ilab model serve --model-path ~/.cache/instructlab/models/qwen2-5-7b-instruct-quantized-w8a8
|
||
|
||
# Chat with model
|
||
ilab model chat --model ~/.cache/instructlab/models/qwen2-5-7b-instruct-quantized-w8a8
|
||
```
|
||
See [Red Hat Enterprise Linux AI documentation](https://docs.redhat.com/en/documentation/red_hat_enterprise_linux_ai/1.4) for more details.
|
||
</details>
|
||
|
||
<details>
|
||
<summary>Deploy on <strong>Red Hat Openshift AI</strong></summary>
|
||
|
||
```python
|
||
# Setting up vllm server with ServingRuntime
|
||
# Save as: vllm-servingruntime.yaml
|
||
apiVersion: serving.kserve.io/v1alpha1
|
||
kind: ServingRuntime
|
||
metadata:
|
||
name: vllm-cuda-runtime # OPTIONAL CHANGE: set a unique name
|
||
annotations:
|
||
openshift.io/display-name: vLLM NVIDIA GPU ServingRuntime for KServe
|
||
opendatahub.io/recommended-accelerators: '["nvidia.com/gpu"]'
|
||
labels:
|
||
opendatahub.io/dashboard: 'true'
|
||
spec:
|
||
annotations:
|
||
prometheus.io/port: '8080'
|
||
prometheus.io/path: '/metrics'
|
||
multiModel: false
|
||
supportedModelFormats:
|
||
- autoSelect: true
|
||
name: vLLM
|
||
containers:
|
||
- name: kserve-container
|
||
image: quay.io/modh/vllm:rhoai-2.20-cuda # CHANGE if needed. If AMD: quay.io/modh/vllm:rhoai-2.20-rocm
|
||
command:
|
||
- python
|
||
- -m
|
||
- vllm.entrypoints.openai.api_server
|
||
args:
|
||
- "--port=8080"
|
||
- "--model=/mnt/models"
|
||
- "--served-model-name={{.Name}}"
|
||
env:
|
||
- name: HF_HOME
|
||
value: /tmp/hf_home
|
||
ports:
|
||
- containerPort: 8080
|
||
protocol: TCP
|
||
```
|
||
|
||
```python
|
||
# Attach model to vllm server. This is an NVIDIA template
|
||
# Save as: inferenceservice.yaml
|
||
apiVersion: serving.kserve.io/v1beta1
|
||
kind: InferenceService
|
||
metadata:
|
||
annotations:
|
||
openshift.io/display-name: Qwen2.5-7B-Instruct-quantized.w8a8 # OPTIONAL CHANGE
|
||
serving.kserve.io/deploymentMode: RawDeployment
|
||
name: Qwen2.5-7B-Instruct-quantized.w8a8 # specify model name. This value will be used to invoke the model in the payload
|
||
labels:
|
||
opendatahub.io/dashboard: 'true'
|
||
spec:
|
||
predictor:
|
||
maxReplicas: 1
|
||
minReplicas: 1
|
||
model:
|
||
modelFormat:
|
||
name: vLLM
|
||
name: ''
|
||
resources:
|
||
limits:
|
||
cpu: '2' # this is model specific
|
||
memory: 8Gi # this is model specific
|
||
nvidia.com/gpu: '1' # this is accelerator specific
|
||
requests: # same comment for this block
|
||
cpu: '1'
|
||
memory: 4Gi
|
||
nvidia.com/gpu: '1'
|
||
runtime: vllm-cuda-runtime # must match the ServingRuntime name above
|
||
storageUri: oci://registry.redhat.io/rhelai1/modelcar-qwen2-5-7b-instruct-quantized-w8a8:1.5
|
||
tolerations:
|
||
- effect: NoSchedule
|
||
key: nvidia.com/gpu
|
||
operator: Exists
|
||
```
|
||
|
||
```bash
|
||
# make sure first to be in the project where you want to deploy the model
|
||
# oc project <project-name>
|
||
# apply both resources to run model
|
||
# Apply the ServingRuntime
|
||
oc apply -f vllm-servingruntime.yaml
|
||
# Apply the InferenceService
|
||
oc apply -f qwen-inferenceservice.yaml
|
||
```
|
||
|
||
```python
|
||
# Replace <inference-service-name> and <cluster-ingress-domain> below:
|
||
# - Run `oc get inferenceservice` to find your URL if unsure.
|
||
# Call the server using curl:
|
||
curl https://<inference-service-name>-predictor-default.<domain>/v1/chat/completions
|
||
-H "Content-Type: application/json" \
|
||
-d '{
|
||
"model": "Qwen2.5-7B-Instruct-quantized.w8a8",
|
||
"stream": true,
|
||
"stream_options": {
|
||
"include_usage": true
|
||
},
|
||
"max_tokens": 1,
|
||
"messages": [
|
||
{
|
||
"role": "user",
|
||
"content": "How can a bee fly when its wings are so small?"
|
||
}
|
||
]
|
||
}'
|
||
```
|
||
|
||
See [Red Hat Openshift AI documentation](https://docs.redhat.com/en/documentation/red_hat_openshift_ai/2025) for more details.
|
||
</details>
|
||
|
||
## Creation
|
||
|
||
<details>
|
||
<summary>Creation details</summary>
|
||
This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below.
|
||
|
||
|
||
```python
|
||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||
from llmcompressor.modifiers.quantization import GPTQModifier
|
||
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
|
||
from llmcompressor.transformers import oneshot
|
||
from datasets import load_dataset
|
||
|
||
# Load model
|
||
model_stub = "Qwen/Qwen2.5-7B-Instruct"
|
||
model_name = model_stub.split("/")[-1]
|
||
|
||
num_samples = 512
|
||
max_seq_len = 8192
|
||
|
||
tokenizer = AutoTokenizer.from_pretrained(model_stub)
|
||
|
||
model = AutoModelForCausalLM.from_pretrained(
|
||
model_stub,
|
||
device_map="auto",
|
||
torch_dtype="auto",
|
||
)
|
||
|
||
def preprocess_fn(example):
|
||
return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
|
||
|
||
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
|
||
ds = ds.map(preprocess_fn)
|
||
|
||
# Configure the quantization algorithm and scheme
|
||
recipe = [
|
||
SmoothQuantModifier(
|
||
smoothing_strength=0.8,
|
||
mappings=[
|
||
[["re:.*q_proj", "re:.*k_proj", "re:.*v_proj"], "re:.*input_layernorm"],
|
||
[["re:.*gate_proj", "re:.*up_proj"], "re:.*post_attention_layernorm"],
|
||
[["re:.*down_proj"], "re:.*up_proj"],
|
||
],
|
||
),
|
||
GPTQModifier(
|
||
ignore=["lm_head"],
|
||
sequential_targets=["Qwen2DecoderLayer"],
|
||
dampening_frac=0.01,
|
||
targets="Linear",
|
||
scheme="W8A8",
|
||
),
|
||
]
|
||
|
||
# Apply quantization
|
||
oneshot(
|
||
model=model,
|
||
dataset=ds,
|
||
recipe=recipe,
|
||
max_seq_length=max_seq_len,
|
||
num_calibration_samples=num_samples,
|
||
)
|
||
|
||
# Save to disk in compressed-tensors format
|
||
save_path = model_name + "-quantized.w8a8"
|
||
model.save_pretrained(save_path)
|
||
tokenizer.save_pretrained(save_path)
|
||
print(f"Model and tokenizer saved to: {save_path}")
|
||
```
|
||
</details>
|
||
|
||
## 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/387Bbd54bc621086e05aa1b030d8d4d5635b25e6) (commit 387Bbd54bc621086e05aa1b030d8d4d5635b25e6) and the [vLLM](https://docs.vllm.ai/en/stable/) engine, using the following command:
|
||
```
|
||
lm_eval \
|
||
--model vllm \
|
||
--model_args pretrained="neuralmagic/Qwen2.5-7B-Instruct-quantized.w8a8",dtype=auto,gpu_memory_utilization=0.5,max_model_len=4096,add_bos_token=True,enable_chunk_prefill=True,tensor_parallel_size=1 \
|
||
--tasks openllm \
|
||
--batch_size auto
|
||
```
|
||
|
||
### Accuracy
|
||
|
||
#### Open LLM Leaderboard evaluation scores
|
||
<table>
|
||
<tr>
|
||
<th>Benchmark
|
||
</th>
|
||
<th>Qwen2.5-7B-Instruct
|
||
</th>
|
||
<th>Qwen2.5-7B-Instruct-quantized.w8a8<br>(this model)
|
||
</th>
|
||
<th>Recovery
|
||
</th>
|
||
</tr>
|
||
<tr>
|
||
<td>MMLU (5-shot)
|
||
</td>
|
||
<td>74.24
|
||
</td>
|
||
<td>73.87
|
||
</td>
|
||
<td>99.5%
|
||
</td>
|
||
</tr>
|
||
<tr>
|
||
<td>ARC Challenge (25-shot)
|
||
</td>
|
||
<td>63.40
|
||
</td>
|
||
<td>63.23
|
||
</td>
|
||
<td>99.7%
|
||
</td>
|
||
</tr>
|
||
<tr>
|
||
<td>GSM-8K (5-shot, strict-match)
|
||
</td>
|
||
<td>80.36
|
||
</td>
|
||
<td>80.74
|
||
</td>
|
||
<td>100.5%
|
||
</td>
|
||
</tr>
|
||
<tr>
|
||
<td>Hellaswag (10-shot)
|
||
</td>
|
||
<td>81.52
|
||
</td>
|
||
<td>81.06
|
||
</td>
|
||
<td>99.4%
|
||
</td>
|
||
</tr>
|
||
<tr>
|
||
<td>Winogrande (5-shot)
|
||
</td>
|
||
<td>74.66
|
||
</td>
|
||
<td>74.82
|
||
</td>
|
||
<td>100.2%
|
||
</td>
|
||
</tr>
|
||
<tr>
|
||
<td>TruthfulQA (0-shot, mc2)
|
||
</td>
|
||
<td>64.76
|
||
</td>
|
||
<td>64.58
|
||
</td>
|
||
<td>99.7%
|
||
</td>
|
||
</tr>
|
||
<tr>
|
||
<td><strong>Average</strong>
|
||
</td>
|
||
<td><strong>73.16</strong>
|
||
</td>
|
||
<td><strong>73.05</strong>
|
||
</td>
|
||
<td><strong>99.4%</strong>
|
||
</td>
|
||
</tr>
|
||
</table>
|
||
|