Instructions to use cmcmaster/llama_shared_80m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cmcmaster/llama_shared_80m with Transformers:

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

pipe = pipeline("text-generation", model="cmcmaster/llama_shared_80m", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cmcmaster/llama_shared_80m", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("cmcmaster/llama_shared_80m", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use cmcmaster/llama_shared_80m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cmcmaster/llama_shared_80m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cmcmaster/llama_shared_80m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cmcmaster/llama_shared_80m

SGLang

How to use cmcmaster/llama_shared_80m 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 "cmcmaster/llama_shared_80m" \
    --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": "cmcmaster/llama_shared_80m",
		"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 "cmcmaster/llama_shared_80m" \
        --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": "cmcmaster/llama_shared_80m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use cmcmaster/llama_shared_80m with Docker Model Runner:
```
docker model run hf.co/cmcmaster/llama_shared_80m
```

cmcmaster commited on Jul 13, 2024

Commit

115126e

verified ·

1 Parent(s): 337fe85

Update tokenizer_config.json

Browse files

Files changed (1) hide show

tokenizer_config.json +1 -0

tokenizer_config.json CHANGED Viewed

@@ -2052,6 +2052,7 @@
   "bos_token": "<|begin_of_text|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
   "model_input_names": [
     "input_ids",
     "attention_mask"

   "bos_token": "<|begin_of_text|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
+  "pad_token": "<|end_of_text|>",
   "model_input_names": [
     "input_ids",
     "attention_mask"