Instructions to use FreedomIntelligence/AceGPT-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FreedomIntelligence/AceGPT-13B with Transformers:

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

pipe = pipeline("text-generation", model="FreedomIntelligence/AceGPT-13B")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FreedomIntelligence/AceGPT-13B")
model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/AceGPT-13B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FreedomIntelligence/AceGPT-13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FreedomIntelligence/AceGPT-13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FreedomIntelligence/AceGPT-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FreedomIntelligence/AceGPT-13B

SGLang

How to use FreedomIntelligence/AceGPT-13B 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 "FreedomIntelligence/AceGPT-13B" \
    --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": "FreedomIntelligence/AceGPT-13B",
		"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 "FreedomIntelligence/AceGPT-13B" \
        --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": "FreedomIntelligence/AceGPT-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FreedomIntelligence/AceGPT-13B with Docker Model Runner:
```
docker model run hf.co/FreedomIntelligence/AceGPT-13B
```

AceGPT-13B

Commit History

Apr 15, 2024

04:14
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
8c2ca64

Dec 1, 2023

23:31
Delete pytorch_model.bin.index.json

jianqing666

4ceb8c9
23:31
Delete pytorch_model-00006-of-00006.bin

jianqing666

0a0a3a0
23:31
Delete pytorch_model-00005-of-00006.bin

jianqing666

8ee6d46
23:31
Delete pytorch_model-00004-of-00006.bin

jianqing666

12c39c3
23:31
Delete pytorch_model-00003-of-00006.bin

jianqing666

ba9d840
23:30
Delete pytorch_model-00002-of-00006.bin

jianqing666

d6f3410
23:30
Delete pytorch_model-00001-of-00006.bin

jianqing666

add9416
18:53
Upload pytorch_model.bin⁠

jianqing666

c9d9032
16:27
Upload 6 files

jianqing666

c6d2cc1

Sep 26, 2023

08:14
Upload LICENSE.txt

hh2017

3b1047a

Sep 22, 2023

07:58
Upload LlamaForCausalLM

sxn6144

6de635f
07:55
Upload tokenizer

sxn6144

7efc2b0
07:53
Delete pytorch_model-00001-of-00006.bin

sxn6144

7694f88
07:53
Delete pytorch_model-00002-of-00006.bin

sxn6144

a4c4053
07:52
Delete pytorch_model-00003-of-00006.bin

sxn6144

642cc48
07:52
Delete pytorch_model-00004-of-00006.bin

sxn6144

46904f9
07:52
Delete pytorch_model-00006-of-00006.bin

sxn6144

2f4c40f
07:52
Delete pytorch_model-00005-of-00006.bin

sxn6144

b26a14d
07:52
Delete config.json

sxn6144

4d50557
07:52
Delete tokenizer_config.json

sxn6144

39ff244
07:52
Delete tokenizer.model

sxn6144

61e983d
07:52
Delete special_tokens_map.json

sxn6144

fe6d50a
07:51
Delete pytorch_model.bin.index.json

sxn6144

7d7346e
06:24
Upload LlamaForCausalLM

sxn6144

aa63af9
06:11
Upload tokenizer

sxn6144

a9b5dad

Sep 21, 2023

12:49
Update README.md

jianqing666

3a88040
08:58
Update README.md

sxn6144

6eb7f4b
08:34
Update README.md

sxn6144

3b19940
08:32
Update README.md

sxn6144

10f160d
08:31
Update README.md

sxn6144

ce15084
08:13
Update README.md

sxn6144

f9498b8
04:14
Update README.md

sxn6144

30cb415
04:13
Update README.md

sxn6144

4159242
04:12
Update README.md

sxn6144

cfe4f59
02:53
Update README.md

sxn6144

64e9021
02:53
Update README.md

sxn6144

98d290e
02:52
Update README.md

sxn6144

a37773c

Sep 17, 2023

08:34
Create README.md

sxn6144

a4c06ad
06:34
Upload tokenizer

sxn6144

f93e790

Sep 15, 2023

09:38
Upload LlamaForSequenceClassification

sxn6144

6b449fe
09:07
initial commit

sxn6144

00f2ae4

Commit History

Apr 15, 2024

Adding `safetensors` variant of this model⁠

Dec 1, 2023

Delete pytorch_model.bin.index.json

Delete pytorch_model-00006-of-00006.bin

Delete pytorch_model-00005-of-00006.bin

Delete pytorch_model-00004-of-00006.bin

Delete pytorch_model-00003-of-00006.bin

Delete pytorch_model-00002-of-00006.bin

Delete pytorch_model-00001-of-00006.bin

Upload pytorch_model.bin⁠

Upload 6 files

Sep 26, 2023

Upload LICENSE.txt

Sep 22, 2023

Upload LlamaForCausalLM

Upload tokenizer

Delete pytorch_model-00001-of-00006.bin

Delete pytorch_model-00002-of-00006.bin

Delete pytorch_model-00003-of-00006.bin

Delete pytorch_model-00004-of-00006.bin

Delete pytorch_model-00006-of-00006.bin

Delete pytorch_model-00005-of-00006.bin

Delete config.json

Delete tokenizer_config.json

Delete tokenizer.model

Delete special_tokens_map.json

Delete pytorch_model.bin.index.json

Upload LlamaForCausalLM

Upload tokenizer

Sep 21, 2023

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Sep 17, 2023

Create README.md

Upload tokenizer

Sep 15, 2023

Upload LlamaForSequenceClassification

initial commit