初始化项目，由ModelHub XC社区提供模型
Model: RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16 Source: Original Platform
This commit is contained in:
ModelHub XC
262
README.md
Normal file
262
README.md
Normal file
@@ -0,0 +1,262 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
license: llama2
|
||||
---
|
||||
|
||||
# Phi-3-mini-128k-instruct-quantized.w4a16
|
||||
|
||||
## Model Overview
|
||||
- **Model Architecture:** Phi-3
|
||||
- **Input:** Text
|
||||
- **Output:** Text
|
||||
- **Model Optimizations:**
|
||||
- **Weight quantization:** INT4
|
||||
- **Intended Use Cases:** Intended for commercial and research use in English. Similarly to [Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-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)**: [MIT](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/LICENSE)
|
||||
- **Model Developers:** Neural Magic
|
||||
|
||||
Quantized version of [Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
|
||||
It achieves an average score of 67.39 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 69.17.
|
||||
|
||||
### Model Optimizations
|
||||
|
||||
This model was obtained by quantizing the weights of [Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-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.
|
||||
The [GPTQ](https://arxiv.org/abs/2210.17323) algorithm is applied for quantization, as implemented in the [llm-compressor](https://github.com/vllm-project/llm-compressor) library. Quantization is performed with 1% 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/Phi-3-mini-128k-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? Please respond in pirate speak."},
|
||||
]
|
||||
|
||||
prompts = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
|
||||
llm = LLM(model=model_id, tensor_parallel_size=2)
|
||||
|
||||
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
|
||||
|
||||
The following example contemplates how the model can be deployed in Transformers using the `generate()` function.
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
model_id = "neuralmagic/Phi-3-mini-128k-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? Please respond in pirate speak"},
|
||||
]
|
||||
|
||||
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 using the [llm-compressor](https://github.com/vllm-project/llm-compressor) library as presented in the code snipet below.
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer
|
||||
from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot
|
||||
from llmcompressor.modifiers.quantization import GPTQModifier
|
||||
from datasets import load_dataset
|
||||
import random
|
||||
|
||||
model_id = "microsoft/Phi-3-mini-4k-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
|
||||
]
|
||||
|
||||
recipe = GPTQModifier(
|
||||
targets="Linear",
|
||||
scheme="W4A16",
|
||||
ignore=["lm_head"],
|
||||
dampening_frac=0.1,
|
||||
)
|
||||
|
||||
model = SparseAutoModelForCausalLM.from_pretrained(
|
||||
model_id,
|
||||
device_map="auto",
|
||||
trust_remote_code=True,
|
||||
)
|
||||
|
||||
oneshot(
|
||||
model=model,
|
||||
dataset=ds,
|
||||
recipe=recipe,
|
||||
max_seq_length=max_seq_len,
|
||||
num_calibration_samples=num_samples,
|
||||
)
|
||||
|
||||
model.save_pretrained("Phi-3-mini-128k-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/Phi-3-mini-128k-instruct-quantized.w4a16",dtype=auto,tensor_parallel_size=2,gpu_memory_utilization=0.4,add_bos_token=True,max_model_len=4096,trust_remote_code=True \
|
||||
--tasks openllm \
|
||||
--batch_size auto
|
||||
```
|
||||
|
||||
### Accuracy
|
||||
|
||||
#### Open LLM Leaderboard evaluation scores
|
||||
<table>
|
||||
<tr>
|
||||
<td><strong>Benchmark</strong>
|
||||
</td>
|
||||
<td><strong>Phi-3-mini-4k-instruct </strong>
|
||||
</td>
|
||||
<td><strong>Phi-3-mini-128k-instruct-quantized.w4a16(this model)</strong>
|
||||
</td>
|
||||
<td><strong>Recovery</strong>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MMLU (5-shot)
|
||||
</td>
|
||||
<td>68.10
|
||||
</td>
|
||||
<td>66.50
|
||||
</td>
|
||||
<td>97.65%
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ARC Challenge (25-shot)
|
||||
</td>
|
||||
<td>63.90
|
||||
</td>
|
||||
<td>61.51
|
||||
</td>
|
||||
<td>96.26%
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>GSM-8K (5-shot, strict-match)
|
||||
</td>
|
||||
<td>75.58
|
||||
</td>
|
||||
<td>73.84
|
||||
</td>
|
||||
<td>97.69%
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Hellaswag (10-shot)
|
||||
</td>
|
||||
<td>79.81
|
||||
</td>
|
||||
<td>77.63
|
||||
</td>
|
||||
<td>97.27%
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Winogrande (5-shot)
|
||||
</td>
|
||||
<td>73.71
|
||||
</td>
|
||||
<td>71.90
|
||||
</td>
|
||||
<td>97.54%
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>TruthfulQA (0-shot)
|
||||
</td>
|
||||
<td>53.93
|
||||
</td>
|
||||
<td>56.12
|
||||
</td>
|
||||
<td>104.06%
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><strong>Average</strong>
|
||||
</td>
|
||||
<td><strong>69.17</strong>
|
||||
</td>
|
||||
<td><strong>67.91</strong>
|
||||
</td>
|
||||
<td><strong>98.18%</strong>
|
||||
</td>
|
||||
</tr>
|
||||
</table>
|
||||
Reference in New Issue
Block a user