Instructions to use rizerphe/CodeLlama-function-calling-1354-7b-Instruct-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rizerphe/CodeLlama-function-calling-1354-7b-Instruct-hf with Transformers:

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

pipe = pipeline("text-generation", model="rizerphe/CodeLlama-function-calling-1354-7b-Instruct-hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rizerphe/CodeLlama-function-calling-1354-7b-Instruct-hf")
model = AutoModelForCausalLM.from_pretrained("rizerphe/CodeLlama-function-calling-1354-7b-Instruct-hf")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rizerphe/CodeLlama-function-calling-1354-7b-Instruct-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rizerphe/CodeLlama-function-calling-1354-7b-Instruct-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rizerphe/CodeLlama-function-calling-1354-7b-Instruct-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rizerphe/CodeLlama-function-calling-1354-7b-Instruct-hf

SGLang

How to use rizerphe/CodeLlama-function-calling-1354-7b-Instruct-hf 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 "rizerphe/CodeLlama-function-calling-1354-7b-Instruct-hf" \
    --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": "rizerphe/CodeLlama-function-calling-1354-7b-Instruct-hf",
		"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 "rizerphe/CodeLlama-function-calling-1354-7b-Instruct-hf" \
        --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": "rizerphe/CodeLlama-function-calling-1354-7b-Instruct-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rizerphe/CodeLlama-function-calling-1354-7b-Instruct-hf with Docker Model Runner:
```
docker model run hf.co/rizerphe/CodeLlama-function-calling-1354-7b-Instruct-hf
```

rizerphe commited on Sep 5, 2023

Commit

50b756a

1 Parent(s): e5975bd

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -0

README.md CHANGED Viewed

@@ -1,3 +1,11 @@
 ---
 license: cc-by-sa-4.0
 ---

 ---
 license: cc-by-sa-4.0
+datasets:
+- rizerphe/glaive-function-calling-v2-llama
+- rizerphe/sharegpt-hyperfiltered-3k-llama
+- totally-not-an-llm/sharegpt-hyperfiltered-3k
+- glaiveai/glaive-function-calling-v2
 ---
+# CodeLlama-7b Instruct finetuned on 1354 function calling and generic chat examples
+Fine-tuned with LoRA on small fractions of the [glaive-function-calling-v2](glaiveai/glaive-function-calling-v2) and [sharegpt-hyperfiltered-3k](https://huggingface.co/datasets/totally-not-an-llm/sharegpt-hyperfiltered-3k)