Instructions to use openlm-research/open_llama_3b_v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openlm-research/open_llama_3b_v2 with Transformers:

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

pipe = pipeline("text-generation", model="openlm-research/open_llama_3b_v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openlm-research/open_llama_3b_v2")
model = AutoModelForCausalLM.from_pretrained("openlm-research/open_llama_3b_v2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use openlm-research/open_llama_3b_v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openlm-research/open_llama_3b_v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openlm-research/open_llama_3b_v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openlm-research/open_llama_3b_v2

SGLang

How to use openlm-research/open_llama_3b_v2 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 "openlm-research/open_llama_3b_v2" \
    --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": "openlm-research/open_llama_3b_v2",
		"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 "openlm-research/open_llama_3b_v2" \
        --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": "openlm-research/open_llama_3b_v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openlm-research/open_llama_3b_v2 with Docker Model Runner:
```
docker model run hf.co/openlm-research/open_llama_3b_v2
```

Unexpected `inv_freq` buffers in the checkpoint

by sadra-barikbin - opened Sep 20, 2023

Discussion

sadra-barikbin

Sep 20, 2023

Hi,
As of transformers==4.32.0 (the latest is 4.33.2), inv_freq buffers of rotary embeddings in the model are not part of the state dict, hence producing error on loading checkpoints.

To reproduce:

from transformers import LlamaForCausalLM, LlamaConfig

config_dict = json.load(open("config.json"))
config = LlamaConfig(**config_dict)

model = LlamaForCausalLM(config)
state_dict = torch.load(open("pytorch_model.bin", 'rb'))
model.load_state_dict(state_dict)

Output:

Error(s) in loading state_dict for LlamaForCausalLM:
    Unexpected key(s) in state_dict: "model.layers.0.self_attn.rotary_emb.inv_freq", "model.layers.1.self_attn.rotary_emb.inv_freq", "model.layers.2.self_attn.rotary_emb.inv_freq", "model.layers.3.self_attn.rotary_emb.inv_freq", ...

luckstar

Oct 6, 2024

I suffer the same issue.

luckstar

Oct 6, 2024

•

edited Oct 6, 2024

just delete the keys include inv_freq of state dict can solve this issue, inv_freq is just a constant.
https://github.com/huggingface/transformers/pull/24998

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment