Instructions to use yrju/CodeLlaMa-7B-dare-ties with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yrju/CodeLlaMa-7B-dare-ties with Transformers:

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

pipe = pipeline("text-generation", model="yrju/CodeLlaMa-7B-dare-ties")

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

tokenizer = AutoTokenizer.from_pretrained("yrju/CodeLlaMa-7B-dare-ties")
model = AutoModelForCausalLM.from_pretrained("yrju/CodeLlaMa-7B-dare-ties", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yrju/CodeLlaMa-7B-dare-ties with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yrju/CodeLlaMa-7B-dare-ties"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yrju/CodeLlaMa-7B-dare-ties",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/yrju/CodeLlaMa-7B-dare-ties

SGLang

How to use yrju/CodeLlaMa-7B-dare-ties 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 "yrju/CodeLlaMa-7B-dare-ties" \
    --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": "yrju/CodeLlaMa-7B-dare-ties",
		"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 "yrju/CodeLlaMa-7B-dare-ties" \
        --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": "yrju/CodeLlaMa-7B-dare-ties",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yrju/CodeLlaMa-7B-dare-ties with Docker Model Runner:
```
docker model run hf.co/yrju/CodeLlaMa-7B-dare-ties
```

yrju commited on Jun 4, 2024

Commit

d238f22

verified ·

1 Parent(s): b346a5a

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -7,7 +7,9 @@ library_name: transformers
 tags:
 - mergekit
 - merge
 ---
 # merge
@@ -43,4 +45,4 @@ merge_method: dare_ties
 base_model: meta-llama/Llama-2-7b-hf
 dtype: float16
-```

 tags:
 - mergekit
 - merge
+license: apache-2.0
+language:
+- en
 ---
 # merge
 base_model: meta-llama/Llama-2-7b-hf
 dtype: float16
+```