Instructions to use RedHatAI/Llama-2-7b-evolcodealpaca with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Llama-2-7b-evolcodealpaca with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/Llama-2-7b-evolcodealpaca")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/Llama-2-7b-evolcodealpaca")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/Llama-2-7b-evolcodealpaca")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RedHatAI/Llama-2-7b-evolcodealpaca with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Llama-2-7b-evolcodealpaca"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Llama-2-7b-evolcodealpaca",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RedHatAI/Llama-2-7b-evolcodealpaca

SGLang

How to use RedHatAI/Llama-2-7b-evolcodealpaca 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 "RedHatAI/Llama-2-7b-evolcodealpaca" \
    --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": "RedHatAI/Llama-2-7b-evolcodealpaca",
		"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 "RedHatAI/Llama-2-7b-evolcodealpaca" \
        --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": "RedHatAI/Llama-2-7b-evolcodealpaca",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RedHatAI/Llama-2-7b-evolcodealpaca with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Llama-2-7b-evolcodealpaca
```

Llama-2-7b-evolcodealpaca / evaluation_results.json

mgoin

Upload folder using huggingface_hub

6483017 verified about 2 years ago

raw

history blame contribute delete

1.5 kB

	{
	"humaneval": {
	"pass@1": 0.32036585365853665,
	"pass@10": 0.46779679420398335
	},
	"config": {
	"prefix": "",
	"do_sample": true,
	"temperature": 0.2,
	"top_k": 0,
	"top_p": 0.95,
	"n_samples": 50,
	"eos": "<\|endoftext\|>",
	"seed": 0,
	"model": "/home/abhinav/src/llama-recipes/llama_7b_evol_codealpaca_dense/dense-sft_llama_lr1e-4_epochs2_gradclip5.0_cosine_seqlen1024_run2-/combined/",
	"modeltype": "causal",
	"peft_model": null,
	"revision": null,
	"use_auth_token": false,
	"trust_remote_code": false,
	"tasks": "humaneval",
	"instruction_tokens": null,
	"batch_size": 16,
	"max_length_generation": 512,
	"precision": "fp16",
	"load_in_8bit": false,
	"load_in_4bit": false,
	"left_padding": false,
	"limit": null,
	"limit_start": 0,
	"save_every_k_tasks": -1,
	"postprocess": true,
	"allow_code_execution": true,
	"generation_only": false,
	"load_generations_path": null,
	"load_data_path": null,
	"metric_output_path": "/home/abhinav/src/llama-recipes/llama_7b_evol_codealpaca_dense/dense-sft_llama_lr1e-4_epochs2_gradclip5.0_cosine_seqlen1024_run2-/combined//evaluation_results.json",
	"save_generations": true,
	"load_generations_intermediate_paths": null,
	"save_generations_path": "generations.json",
	"save_references": false,
	"save_references_path": "references.json",
	"prompt": "prompt",
	"max_memory_per_gpu": "auto",
	"check_references": false
	}
	}