Instructions to use CarperAI/diff-codegen-6b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CarperAI/diff-codegen-6b-v2 with Transformers:

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

pipe = pipeline("text-generation", model="CarperAI/diff-codegen-6b-v2")

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

tokenizer = AutoTokenizer.from_pretrained("CarperAI/diff-codegen-6b-v2")
model = AutoModelForCausalLM.from_pretrained("CarperAI/diff-codegen-6b-v2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CarperAI/diff-codegen-6b-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CarperAI/diff-codegen-6b-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CarperAI/diff-codegen-6b-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CarperAI/diff-codegen-6b-v2

SGLang

How to use CarperAI/diff-codegen-6b-v2 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 "CarperAI/diff-codegen-6b-v2" \
    --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": "CarperAI/diff-codegen-6b-v2",
		"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 "CarperAI/diff-codegen-6b-v2" \
        --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": "CarperAI/diff-codegen-6b-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CarperAI/diff-codegen-6b-v2 with Docker Model Runner:
```
docker model run hf.co/CarperAI/diff-codegen-6b-v2
```

diff-codegen-6b-v2

Commit History

Nov 4, 2024

00:05
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
0306196

Jan 28, 2023

18:19
Add colab link

HyperionHF

a73f849

Jan 27, 2023

19:52
Update README.md

HyperionHF

633ea75

Jan 24, 2023

14:08
Update README.md

HyperionHF

e6318bf

Jan 23, 2023

17:08
Upload LICENSE (#14)⁠

HyperionHF

0c40ba3
17:05
Upload pytorch_model.bin (#8)⁠

HyperionHF

54aeea1
17:05
Upload trainer_state.json (#1)⁠

HyperionHF

92d64ca
17:05
Upload README.md (#3)⁠

HyperionHF

7e530b5
17:05
Upload added_tokens.json (#4)⁠

HyperionHF

53363ac
17:05
Upload config.json (#5)⁠

HyperionHF

f0ced0e
17:05
Upload special_tokens_map.json (#7)⁠

HyperionHF

8fbaac8
17:04
Upload tokenizer_config.json (#2)⁠

HyperionHF

11a0f46
17:04
Upload vocab.json (#9)⁠

HyperionHF

7a2d225
17:04
Upload merges.txt (#10)⁠

HyperionHF

971ec2c
17:04
Upload train_results.json (#13)⁠

HyperionHF

1472848
17:04
Upload tokenizer.json (#12)⁠

HyperionHF

e7da2ae
01:08
initial commit

HyperionHF

ed22db2

Commit History

Nov 4, 2024

Adding `safetensors` variant of this model⁠

Jan 28, 2023

Add colab link

Jan 27, 2023

Update README.md

Jan 24, 2023

Update README.md

Jan 23, 2023

Upload LICENSE (#14)⁠

Upload pytorch_model.bin (#8)⁠

Upload trainer_state.json (#1)⁠

Upload README.md (#3)⁠

Upload added_tokens.json (#4)⁠

Upload config.json (#5)⁠

Upload special_tokens_map.json (#7)⁠

Upload tokenizer_config.json (#2)⁠

Upload vocab.json (#9)⁠

Upload merges.txt (#10)⁠

Upload train_results.json (#13)⁠

Upload tokenizer.json (#12)⁠

initial commit