初始化项目，由ModelHub XC社区提供模型
Model: RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a16 Source: Original Platform
This commit is contained in:
ModelHub XC
257
README.md
Normal file
257
README.md
Normal file
@@ -0,0 +1,257 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
license: apache-2.0
|
||||
license_link: https://www.apache.org/licenses/LICENSE-2.0
|
||||
---
|
||||
|
||||
# Qwen2-1.5B-Instruct-quantized.w8a16
|
||||
|
||||
## Model Overview
|
||||
- **Model Architecture:** Qwen2
|
||||
- **Input:** Text
|
||||
- **Output:** Text
|
||||
- **Model Optimizations:**
|
||||
- **Weight quantization:** INT8
|
||||
- **Intended Use Cases:** Intended for commercial and research use in English. Similarly to [Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-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:** 7/2/2024
|
||||
- **Version:** 1.0
|
||||
- **License(s):** [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0)
|
||||
- **Model Developers:** Neural Magic
|
||||
|
||||
Quantized version of [Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct).
|
||||
It achieves an average score of 55.38 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 55.17.
|
||||
|
||||
### Model Optimizations
|
||||
|
||||
This model was obtained by quantizing the weights of [Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct) to INT8 data type.
|
||||
This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%.
|
||||
|
||||
Only the weights of the linear operators within transformers blocks are quantized. Symmetric per-channel quantization is applied, in which a linear scaling per output dimension maps the INT8 and floating point representations of the quantized weights.
|
||||
[AutoGPTQ](https://github.com/AutoGPTQ/AutoGPTQ) is used for quantization with 1% damping factor and 256 sequences of 8,192 random tokens.
|
||||
|
||||
|
||||
## 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/Qwen2-1.5B-Instruct-quantized.w8a16"
|
||||
number_gpus = 1
|
||||
|
||||
sampling_params = SamplingParams(temperature=0.7, top_p=0.8, 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, 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)
|
||||
```
|
||||
|
||||
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/Qwen2-1.5B-Instruct-quantized.w8a16"
|
||||
|
||||
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=0.7,
|
||||
top_p=0.8,
|
||||
)
|
||||
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
|
||||
import random
|
||||
|
||||
model_id = "Qwen/Qwen2-1.5B-Instruct"
|
||||
|
||||
num_samples = 256
|
||||
max_seq_len = 8192
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
|
||||
max_token_id = len(tokenizer.get_vocab()) - 1
|
||||
examples = []
|
||||
for _ in range(num_samples):
|
||||
examples.append(
|
||||
{
|
||||
"input_ids": [random.randint(0, max_token_id) for _ in range(max_seq_len)],
|
||||
"attention_mask": max_seq_len*[1],
|
||||
}
|
||||
)
|
||||
|
||||
quantize_config = BaseQuantizeConfig(
|
||||
bits=8,
|
||||
group_size=-1,
|
||||
desc_act=False,
|
||||
model_file_base_name="model",
|
||||
damp_percent=0.01,
|
||||
)
|
||||
|
||||
model = AutoGPTQForCausalLM.from_pretrained(
|
||||
model_id,
|
||||
quantize_config,
|
||||
device_map="auto",
|
||||
)
|
||||
|
||||
model.quantize(examples)
|
||||
model.save_pretrained("Qwen2-1.5B-Instruct-quantized.w8a16")
|
||||
```
|
||||
|
||||
|
||||
|
||||
## 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/Qwen2-1.5B-Instruct-quantized.w8a16",dtype=auto,gpu_memory_utilization=0.4,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
|
||||
--tasks openllm \
|
||||
--batch_size auto
|
||||
```
|
||||
|
||||
### Accuracy
|
||||
|
||||
#### Open LLM Leaderboard evaluation scores
|
||||
<table>
|
||||
<tr>
|
||||
<td><strong>Benchmark</strong>
|
||||
</td>
|
||||
<td><strong>Qwen2-1.5B-Instruct</strong>
|
||||
</td>
|
||||
<td><strong>Qwen2-1.5B-Instruct-quantized.w8a16 (this model)</strong>
|
||||
</td>
|
||||
<td><strong>Recovery</strong>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MMLU (5-shot)
|
||||
</td>
|
||||
<td>55.65
|
||||
</td>
|
||||
<td>56.08
|
||||
</td>
|
||||
<td>100.8%
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ARC Challenge (25-shot)
|
||||
</td>
|
||||
<td>42.83
|
||||
</td>
|
||||
<td>43.09
|
||||
</td>
|
||||
<td>100.6%
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>GSM-8K (5-shot, strict-match)
|
||||
</td>
|
||||
<td>58.07
|
||||
</td>
|
||||
<td>58.00
|
||||
</td>
|
||||
<td>99.9%
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Hellaswag (10-shot)
|
||||
</td>
|
||||
<td>67.43
|
||||
</td>
|
||||
<td>67.44
|
||||
</td>
|
||||
<td>100.0%
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Winogrande (5-shot)
|
||||
</td>
|
||||
<td>63.69
|
||||
</td>
|
||||
<td>64.33
|
||||
</td>
|
||||
<td>101.0%
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>TruthfulQA (0-shot)
|
||||
</td>
|
||||
<td>43.34
|
||||
</td>
|
||||
<td>43.38
|
||||
</td>
|
||||
<td>100.1%
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><strong>Average</strong>
|
||||
</td>
|
||||
<td><strong>55.17</strong>
|
||||
</td>
|
||||
<td><strong>55.38</strong>
|
||||
</td>
|
||||
<td><strong>100.4%</strong>
|
||||
</td>
|
||||
</tr>
|
||||
</table>
|
||||
Reference in New Issue
Block a user