Instructions to use zpn/llama-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zpn/llama-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="zpn/llama-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("zpn/llama-7b") model = AutoModelForCausalLM.from_pretrained("zpn/llama-7b") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use zpn/llama-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "zpn/llama-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zpn/llama-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/zpn/llama-7b
- SGLang
How to use zpn/llama-7b 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 "zpn/llama-7b" \ --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": "zpn/llama-7b", "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 "zpn/llama-7b" \ --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": "zpn/llama-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use zpn/llama-7b with Docker Model Runner:
docker model run hf.co/zpn/llama-7b
Update tokenizer_config.json
Browse files- tokenizer_config.json +3 -3
tokenizer_config.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token": "",
|
| 3 |
-
"eos_token": "",
|
| 4 |
"model_max_length": 2048,
|
| 5 |
"special_tokens_map_file": "llama_model/tokenizer/special_tokens_map.json",
|
| 6 |
"tokenizer_class": "LlamaTokenizer",
|
| 7 |
-
"unk_token": ""
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
"model_max_length": 2048,
|
| 5 |
"special_tokens_map_file": "llama_model/tokenizer/special_tokens_map.json",
|
| 6 |
"tokenizer_class": "LlamaTokenizer",
|
| 7 |
+
"unk_token": "<unk>"
|
| 8 |
}
|