Instructions to use learnanything/llama-7b-huggingface with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use learnanything/llama-7b-huggingface with Transformers:

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

pipe = pipeline("text-generation", model="learnanything/llama-7b-huggingface")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("learnanything/llama-7b-huggingface")
model = AutoModelForCausalLM.from_pretrained("learnanything/llama-7b-huggingface")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use learnanything/llama-7b-huggingface with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/learnanything/llama-7b-huggingface

SGLang

How to use learnanything/llama-7b-huggingface 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 "learnanything/llama-7b-huggingface" \
    --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": "learnanything/llama-7b-huggingface",
		"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 "learnanything/llama-7b-huggingface" \
        --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": "learnanything/llama-7b-huggingface",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use learnanything/llama-7b-huggingface with Docker Model Runner:
```
docker model run hf.co/learnanything/llama-7b-huggingface
```

nan commited on Apr 17, 2023

Commit

ea81e7d

1 Parent(s): 5f98eef

model config and tokenizer config adapted for transformers 4.28.x

Browse files

Files changed (2) hide show

config.json +1 -1
tokenizer_config.json +1 -1

config.json CHANGED Viewed

@@ -1 +1 @@

- {"architectures": ["~~LLaMAForCausalLM~~"], "bos_token_id": 0, "eos_token_id": 1, "hidden_act": "silu", "hidden_size": 4096, "intermediate_size": 11008, "initializer_range": 0.02, "max_sequence_length": 2048, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 32, "pad_token_id": -1, "rms_norm_eps": 1e-06, "torch_dtype": "float16", "transformers_version": "4.27.0~~.dev0~~", "use_cache": true, "vocab_size": 32000}

+ {"architectures": ["LlamaForCausalLM"], "bos_token_id": 0, "eos_token_id": 1, "hidden_act": "silu", "hidden_size": 4096, "intermediate_size": 11008, "initializer_range": 0.02, "max_sequence_length": 2048, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 32, "pad_token_id": -1, "rms_norm_eps": 1e-06, "torch_dtype": "float16", "transformers_version": "4.28.0", "use_cache": true, "vocab_size": 32000}

tokenizer_config.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"bos_token": "", "eos_token": "", "model_max_length": 1000000000000000019884624838656, "tokenizer_class": "~~LLaMATokenizer~~", "unk_token": ""}


1	+ {"bos_token": "", "eos_token": "", "model_max_length": 1000000000000000019884624838656, "tokenizer_class": "LlamaTokenizer", "unk_token": ""}