Instructions to use IndexTeam/Index-1.9B-Constant-LR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IndexTeam/Index-1.9B-Constant-LR with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="IndexTeam/Index-1.9B-Constant-LR", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("IndexTeam/Index-1.9B-Constant-LR", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use IndexTeam/Index-1.9B-Constant-LR with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IndexTeam/Index-1.9B-Constant-LR"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IndexTeam/Index-1.9B-Constant-LR",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/IndexTeam/Index-1.9B-Constant-LR

SGLang

How to use IndexTeam/Index-1.9B-Constant-LR with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "IndexTeam/Index-1.9B-Constant-LR" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IndexTeam/Index-1.9B-Constant-LR",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "IndexTeam/Index-1.9B-Constant-LR" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IndexTeam/Index-1.9B-Constant-LR",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use IndexTeam/Index-1.9B-Constant-LR with Docker Model Runner:
```
docker model run hf.co/IndexTeam/Index-1.9B-Constant-LR
```

Index-1.9B-Constant-LR / README.md

AsirAsir

Upload 11 files

f733dbf verified almost 2 years ago

preview code

raw

history blame

2.87 kB

	---
	license: other
	license_name: license
	license_link: LICENSE
	---
	<div align="center">
	<h1>
	Index-1.9B
	</h1>
	</div>

	## 模型介绍

	我们很高兴首次发布Index系列模型中的轻量版本：Index-1.9B系列
	本次开源的Index-1.9B 系列包含以下模型：
	- Index-1.9B base(本仓库模型) : 基座模型，具有 19亿非词嵌入参数量，在2.8T 中英文为主的语料上预训练，多个评测基准上与同级别模型比处于领先.
	- Index-1.9B pure : 基座模型的对照组，与base具有相同的参数和训练策略，不同之处在于我们严格过滤了该版本语料中所有指令相关的数据，以此来验证指令对benchmark的影响
	- Index-1.9B chat: 基于index-1.9B base通过SFT和DPO对齐后的对话模型，我们发现由于我们预训练中引入了较多互联网社区语料，聊天的趣味性明显更强
	- Index-1.9B character : 在SFT和DPO的基础上引入了RAG来实现fewshots角色扮演定制

	注意：此为Base模型，仅能续写，以及进一步的训练对齐，不能直接交互。
	- Chat模型详见 [Index-1.9B-Chat](https://modelscope.cn/models/IndexTeam/Index-1.9B-Chat/summary)
	- 角色扮演模型详见 [Index-1.9B-Character](https://modelscope.cn/models/IndexTeam/Index-1.9B-Character/summary)

	更多细节详见我们的[GitHub](https://github.com/bilibili/Index-1.9B)和[Index-1.9B技术报告](https://github.com/bilibili/Index-1.9B/blob/main/Index-1.9B%20%E6%8A%80%E6%9C%AF%E6%8A%A5%E5%91%8A.pdf)

	## 评测结果
	对通用理解进行评测，Index-1.9B性能优秀，于近期开源的端侧小模型相比领先，并可以和一批7B和大于10B的模型相比较
	\|模型\|均分\|英文均分\|MMLU\|CEVAL\|CMMLU\|HellaSwag\|Arc-C\|Arc-E\|
	\|----\|----\|----\|----\|----\|----\|----\|----\|----\|
	\|Google Gemma 2B\|41.58\|46.77\|41.81\|31.36\|31.02\|66.82\|36.39\|42.07\|
	\|Phi-2 (2.7B)\|58.89\|72.54\|57.61\|31.12\|32.05\|70.94\|74.51\|87.1\|
	\|Qwen1.5-1.8B\|58.96\|59.28\|47.05\|59.48\|57.12\|58.33\|56.82\|74.93\|
	\|Qwen2-1.5B(report)\|65.17\|62.52 \|56.5\|70.6\|70.3\|66.6\|43.9\|83.09\|
	\|MiniCPM-2.4B-SFT\|62.53\|68.75\|53.8\|49.19\|50.97\|67.29\|69.44\|84.48\|
	\|Index-1.9B-Pure\|49.55 \|52.83 \|43.75\|42.35\|43.61\|63.21\|42.75\|61.61\|
	\|Index-1.9B\|64.92 \|69.93\|52.53\|57.01\|52.79\|80.69\|65.15\|81.35\|
	\|Llama2-7B\|50.79\|60.31\|44.32\|32.42\|31.11\|76\|46.3\|74.6\|
	\|Mistral-7B (report) \|/\|69.23\|60.1\|/\|/\|81.3\|55.5\|80\|
	\|Baichuan2-7B\|54.53\|53.51\|54.64\|56.19\|56.95\|25.04\|57.25\|77.12\|
	\|Llama2-13B\|57.51\|66.61\|55.78\|39.93\|38.7\|76.22\|58.88\|75.56\|
	\|Baichuan2-13B\|68.90\|71.69\|59.63\|59.21\|61.27\|72.61\|70.04\|84.48\|
	\|MPT-30B (report)\|/\|63.48\|46.9\|/\|/\|79.9\|50.6\|76.5\|
	\|Falcon-40B (report)\|/\|68.18\|55.4\|/\|/\|83.6\|54.5\|79.2\|

	评测代码基于[OpenCompass](https://github.com/open-compass/opencompass), 并做了适配性修改，详见[evaluate代码](https://github.com/bilibili/Index-1.9B/evaluate/)