431 lines
11 KiB
Markdown
431 lines
11 KiB
Markdown
|
---
|
||
|
|
tags:
|
||
|
|
- int8
|
||
|
|
- vllm
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
- de
|
||
|
|
- fr
|
||
|
|
- it
|
||
|
|
- pt
|
||
|
|
- hi
|
||
|
|
- es
|
||
|
|
- th
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
license: llama3.1
|
||
|
|
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
||
|
|
---
|
||
|
|
|
||
|
|
# Meta-Llama-3.1-8B-Instruct-quantized.w8a16
|
||
|
|
|
||
|
|
## Model Overview
|
||
|
|
- **Model Architecture:** Meta-Llama-3
|
||
|
|
- **Input:** Text
|
||
|
|
- **Output:** Text
|
||
|
|
- **Model Optimizations:**
|
||
|
|
- **Weight quantization:** INT8
|
||
|
|
- **Intended Use Cases:** Intended for commercial and research use multiple languages. Similarly to [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-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).
|
||
|
|
- **Release Date:** 7/23/2024
|
||
|
|
- **Version:** 1.0
|
||
|
|
- **License(s):** Llama3.1
|
||
|
|
- **Model Developers:** Neural Magic
|
||
|
|
|
||
|
|
Quantized version of [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct).
|
||
|
|
It achieves scores within 1% of the scores of the unquantized model for MMLU, ARC-Challenge, GSM-8k, Hellaswag, Winogrande and TruthfulQA.
|
||
|
|
|
||
|
|
### Model Optimizations
|
||
|
|
|
||
|
|
This model was obtained by quantizing the weights of [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-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.
|
||
|
|
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. GPTQ used a 1% damping factor and 256 sequences of 8,192 random tokens.
|
||
|
|
|
||
|
|
|
||
|
|
## 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 = "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16"
|
||
|
|
number_gpus = 1
|
||
|
|
max_model_len = 8192
|
||
|
|
|
||
|
|
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, add_generation_prompt=True, 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.
|
||
|
|
|
||
|
|
|
||
|
|
## 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 datasets import Dataset
|
||
|
|
from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot
|
||
|
|
from llmcompressor.modifiers.quantization import GPTQModifier
|
||
|
|
import random
|
||
|
|
|
||
|
|
model_id = "meta-llama/Meta-Llama-3.1-8B-Instruct"
|
||
|
|
|
||
|
|
num_samples = 256
|
||
|
|
max_seq_len = 8192
|
||
|
|
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||
|
|
|
||
|
|
max_token_id = len(tokenizer.get_vocab()) - 1
|
||
|
|
input_ids = [[random.randint(0, max_token_id) for _ in range(max_seq_len)] for _ in range(num_samples)]
|
||
|
|
attention_mask = num_samples * [max_seq_len * [1]]
|
||
|
|
ds = Dataset.from_dict({"input_ids": input_ids, "attention_mask": attention_mask})
|
||
|
|
|
||
|
|
recipe = GPTQModifier(
|
||
|
|
targets="Linear",
|
||
|
|
scheme="W8A16",
|
||
|
|
ignore=["lm_head"],
|
||
|
|
dampening_frac=0.01,
|
||
|
|
)
|
||
|
|
|
||
|
|
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("Meta-Llama-3.1-8B-Instruct-quantized.w8a16")
|
||
|
|
```
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
## Evaluation
|
||
|
|
|
||
|
|
The model was evaluated on MMLU, ARC-Challenge, GSM-8K, Hellaswag, Winogrande and TruthfulQA.
|
||
|
|
Evaluation was conducted using the Neural Magic fork of [lm-evaluation-harness](https://github.com/neuralmagic/lm-evaluation-harness/tree/llama_3.1_instruct) (branch llama_3.1_instruct) and the [vLLM](https://docs.vllm.ai/en/stable/) engine.
|
||
|
|
This version of the lm-evaluation-harness includes versions of MMLU, ARC-Challenge and GSM-8K that match the prompting style of [Meta-Llama-3.1-Instruct-evals](https://huggingface.co/datasets/meta-llama/Meta-Llama-3.1-8B-Instruct-evals).
|
||
|
|
|
||
|
|
**Note:** Results have been updated after Meta modified the chat template.
|
||
|
|
|
||
|
|
### Accuracy
|
||
|
|
|
||
|
|
<table>
|
||
|
|
<tr>
|
||
|
|
<td><strong>Category</strong>
|
||
|
|
</td>
|
||
|
|
<td><strong>Benchmark</strong>
|
||
|
|
</td>
|
||
|
|
<td><strong>Meta-Llama-3.1-8B-Instruct </strong>
|
||
|
|
</td>
|
||
|
|
<td><strong>Meta-Llama-3.1-8B-Instruct-quantized.w8a16 (this model)</strong>
|
||
|
|
</td>
|
||
|
|
<td><strong>Recovery</strong>
|
||
|
|
</td>
|
||
|
|
</tr>
|
||
|
|
<tr>
|
||
|
|
<td rowspan="5" ><strong>OpenLLM v1</strong>
|
||
|
|
</td>
|
||
|
|
</tr>
|
||
|
|
<tr>
|
||
|
|
<td>Hellaswag (10-shot)
|
||
|
|
</td>
|
||
|
|
<td>80.47
|
||
|
|
</td>
|
||
|
|
<td>80.48
|
||
|
|
</td>
|
||
|
|
<td>100.0%
|
||
|
|
</td>
|
||
|
|
</tr>
|
||
|
|
<tr>
|
||
|
|
<td>Winogrande (5-shot)
|
||
|
|
</td>
|
||
|
|
<td>78.06
|
||
|
|
</td>
|
||
|
|
<td>77.51
|
||
|
|
</td>
|
||
|
|
<td>99.3%
|
||
|
|
</td>
|
||
|
|
</tr>
|
||
|
|
<tr>
|
||
|
|
<td>TruthfulQA (0-shot, mc2)
|
||
|
|
</td>
|
||
|
|
<td>54.48
|
||
|
|
</td>
|
||
|
|
<td>54.41
|
||
|
|
</td>
|
||
|
|
<td>99.9%
|
||
|
|
</td>
|
||
|
|
</tr>
|
||
|
|
<tr>
|
||
|
|
<td><strong>Average</strong>
|
||
|
|
</td>
|
||
|
|
<td><strong>74.05</strong>
|
||
|
|
</td>
|
||
|
|
<td><strong>74.12</strong>
|
||
|
|
</td>
|
||
|
|
<td><strong>100.1%</strong>
|
||
|
|
</td>
|
||
|
|
</tr>
|
||
|
|
<tr>
|
||
|
|
<td rowspan="9" ><strong>Multilingual</strong>
|
||
|
|
</td>
|
||
|
|
<td>Portuguese MMLU (5-shot)
|
||
|
|
</td>
|
||
|
|
<td>59.96
|
||
|
|
</td>
|
||
|
|
<td>59.79
|
||
|
|
</td>
|
||
|
|
<td>99.8%
|
||
|
|
</td>
|
||
|
|
</tr>
|
||
|
|
<tr>
|
||
|
|
<td>Spanish MMLU (5-shot)
|
||
|
|
</td>
|
||
|
|
<td>60.25
|
||
|
|
</td>
|
||
|
|
<td>59.92
|
||
|
|
</td>
|
||
|
|
<td>99.4%
|
||
|
|
</td>
|
||
|
|
</tr>
|
||
|
|
<tr>
|
||
|
|
<td>Italian MMLU (5-shot)
|
||
|
|
</td>
|
||
|
|
<td>59.23
|
||
|
|
</td>
|
||
|
|
<td>59.25
|
||
|
|
</td>
|
||
|
|
<td>100.0%
|
||
|
|
</td>
|
||
|
|
</tr>
|
||
|
|
<tr>
|
||
|
|
<td>German MMLU (5-shot)
|
||
|
|
</td>
|
||
|
|
<td>58.63
|
||
|
|
</td>
|
||
|
|
<td>58.31
|
||
|
|
</td>
|
||
|
|
<td>99.5%
|
||
|
|
</td>
|
||
|
|
</tr>
|
||
|
|
<tr>
|
||
|
|
<td>French MMLU (5-shot)
|
||
|
|
</td>
|
||
|
|
<td>59.65
|
||
|
|
</td>
|
||
|
|
<td>59.57
|
||
|
|
</td>
|
||
|
|
<td>99.9%
|
||
|
|
</td>
|
||
|
|
</tr>
|
||
|
|
<tr>
|
||
|
|
<td>Hindi MMLU (5-shot)
|
||
|
|
</td>
|
||
|
|
<td>50.10
|
||
|
|
</td>
|
||
|
|
<td>49.97
|
||
|
|
</td>
|
||
|
|
<td>99.7%
|
||
|
|
</td>
|
||
|
|
</tr>
|
||
|
|
<tr>
|
||
|
|
<td>Thai MMLU (5-shot)
|
||
|
|
</td>
|
||
|
|
<td>49.12
|
||
|
|
</td>
|
||
|
|
<td>49.09
|
||
|
|
</td>
|
||
|
|
<td>99.9%
|
||
|
|
</td>
|
||
|
|
</tr>
|
||
|
|
</table>
|
||
|
|
|
||
|
|
### Reproduction
|
||
|
|
|
||
|
|
The results were obtained using the following commands:
|
||
|
|
|
||
|
|
#### MMLU
|
||
|
|
```
|
||
|
|
lm_eval \
|
||
|
|
--model vllm \
|
||
|
|
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
|
||
|
|
--tasks mmlu_llama_3.1_instruct \
|
||
|
|
--fewshot_as_multiturn \
|
||
|
|
--apply_chat_template \
|
||
|
|
--num_fewshot 5 \
|
||
|
|
--batch_size auto
|
||
|
|
```
|
||
|
|
|
||
|
|
#### MMLU-CoT
|
||
|
|
```
|
||
|
|
lm_eval \
|
||
|
|
--model vllm \
|
||
|
|
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,max_model_len=4064,max_gen_toks=1024,tensor_parallel_size=1 \
|
||
|
|
--tasks mmlu_cot_0shot_llama_3.1_instruct \
|
||
|
|
--apply_chat_template \
|
||
|
|
--num_fewshot 0 \
|
||
|
|
--batch_size auto
|
||
|
|
```
|
||
|
|
|
||
|
|
#### ARC-Challenge
|
||
|
|
```
|
||
|
|
lm_eval \
|
||
|
|
--model vllm \
|
||
|
|
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,max_model_len=3940,max_gen_toks=100,tensor_parallel_size=1 \
|
||
|
|
--tasks arc_challenge_llama_3.1_instruct \
|
||
|
|
--apply_chat_template \
|
||
|
|
--num_fewshot 0 \
|
||
|
|
--batch_size auto
|
||
|
|
```
|
||
|
|
|
||
|
|
#### GSM-8K
|
||
|
|
```
|
||
|
|
lm_eval \
|
||
|
|
--model vllm \
|
||
|
|
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,max_model_len=4096,max_gen_toks=1024,tensor_parallel_size=1 \
|
||
|
|
--tasks gsm8k_cot_llama_3.1_instruct \
|
||
|
|
--fewshot_as_multiturn \
|
||
|
|
--apply_chat_template \
|
||
|
|
--num_fewshot 8 \
|
||
|
|
--batch_size auto
|
||
|
|
```
|
||
|
|
|
||
|
|
#### Hellaswag
|
||
|
|
```
|
||
|
|
lm_eval \
|
||
|
|
--model vllm \
|
||
|
|
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
|
||
|
|
--tasks hellaswag \
|
||
|
|
--num_fewshot 10 \
|
||
|
|
--batch_size auto
|
||
|
|
```
|
||
|
|
|
||
|
|
#### Winogrande
|
||
|
|
```
|
||
|
|
lm_eval \
|
||
|
|
--model vllm \
|
||
|
|
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
|
||
|
|
--tasks winogrande \
|
||
|
|
--num_fewshot 5 \
|
||
|
|
--batch_size auto
|
||
|
|
```
|
||
|
|
|
||
|
|
#### TruthfulQA
|
||
|
|
```
|
||
|
|
lm_eval \
|
||
|
|
--model vllm \
|
||
|
|
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
|
||
|
|
--tasks truthfulqa \
|
||
|
|
--num_fewshot 0 \
|
||
|
|
--batch_size auto
|
||
|
|
```
|
||
|
|
|
||
|
|
#### MMLU Portuguese
|
||
|
|
```
|
||
|
|
lm_eval \
|
||
|
|
--model vllm \
|
||
|
|
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
|
||
|
|
--tasks mmlu_pt_llama_3.1_instruct \
|
||
|
|
--fewshot_as_multiturn \
|
||
|
|
--apply_chat_template \
|
||
|
|
--num_fewshot 5 \
|
||
|
|
--batch_size auto
|
||
|
|
```
|
||
|
|
|
||
|
|
#### MMLU Spanish
|
||
|
|
```
|
||
|
|
lm_eval \
|
||
|
|
--model vllm \
|
||
|
|
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
|
||
|
|
--tasks mmlu_es_llama_3.1_instruct \
|
||
|
|
--fewshot_as_multiturn \
|
||
|
|
--apply_chat_template \
|
||
|
|
--num_fewshot 5 \
|
||
|
|
--batch_size auto
|
||
|
|
```
|
||
|
|
|
||
|
|
#### MMLU Italian
|
||
|
|
```
|
||
|
|
lm_eval \
|
||
|
|
--model vllm \
|
||
|
|
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
|
||
|
|
--tasks mmlu_it_llama_3.1_instruct \
|
||
|
|
--fewshot_as_multiturn \
|
||
|
|
--apply_chat_template \
|
||
|
|
--num_fewshot 5 \
|
||
|
|
--batch_size auto
|
||
|
|
```
|
||
|
|
|
||
|
|
#### MMLU German
|
||
|
|
```
|
||
|
|
lm_eval \
|
||
|
|
--model vllm \
|
||
|
|
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
|
||
|
|
--tasks mmlu_de_llama_3.1_instruct \
|
||
|
|
--fewshot_as_multiturn \
|
||
|
|
--apply_chat_template \
|
||
|
|
--num_fewshot 5 \
|
||
|
|
--batch_size auto
|
||
|
|
```
|
||
|
|
|
||
|
|
#### MMLU French
|
||
|
|
```
|
||
|
|
lm_eval \
|
||
|
|
--model vllm \
|
||
|
|
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
|
||
|
|
--tasks mmlu_fr_llama_3.1_instruct \
|
||
|
|
--fewshot_as_multiturn \
|
||
|
|
--apply_chat_template \
|
||
|
|
--num_fewshot 5 \
|
||
|
|
--batch_size auto
|
||
|
|
```
|
||
|
|
|
||
|
|
#### MMLU Hindi
|
||
|
|
```
|
||
|
|
lm_eval \
|
||
|
|
--model vllm \
|
||
|
|
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
|
||
|
|
--tasks mmlu_hi_llama_3.1_instruct \
|
||
|
|
--fewshot_as_multiturn \
|
||
|
|
--apply_chat_template \
|
||
|
|
--num_fewshot 5 \
|
||
|
|
--batch_size auto
|
||
|
|
```
|
||
|
|
|
||
|
|
#### MMLU Thai
|
||
|
|
```
|
||
|
|
lm_eval \
|
||
|
|
--model vllm \
|
||
|
|
--model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
|
||
|
|
--tasks mmlu_th_llama_3.1_instruct \
|
||
|
|
--fewshot_as_multiturn \
|
||
|
|
--apply_chat_template \
|
||
|
|
--num_fewshot 5 \
|
||
|
|
--batch_size auto
|
||
|
|
```
|