Instructions to use OpenNLPLab/TransNormerLLM-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenNLPLab/TransNormerLLM-7B with Transformers:

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

pipe = pipeline("text-generation", model="OpenNLPLab/TransNormerLLM-7B", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("OpenNLPLab/TransNormerLLM-7B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenNLPLab/TransNormerLLM-7B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/OpenNLPLab/TransNormerLLM-7B

SGLang

How to use OpenNLPLab/TransNormerLLM-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 "OpenNLPLab/TransNormerLLM-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": "OpenNLPLab/TransNormerLLM-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 "OpenNLPLab/TransNormerLLM-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": "OpenNLPLab/TransNormerLLM-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenNLPLab/TransNormerLLM-7B with Docker Model Runner:
```
docker model run hf.co/OpenNLPLab/TransNormerLLM-7B
```

OpenNLPLab commited on Nov 13, 2023

Commit

a5b83ec

1 Parent(s): 1da34bf

Update modeling_transnormer.py

Browse files

Files changed (1) hide show

modeling_transnormer.py +0 -40

modeling_transnormer.py CHANGED Viewed

@@ -734,43 +734,6 @@ class TransnormerModel(TransnormerPreTrainedModel):
             slope_rate = slope_rates[idx]
             slope_rate = slope_rate * (1 - idx / (self.num_layers - 1) + 1e-5)
             mask = linear_attn_mask
-            # if self.gradient_checkpointing and self.training:
-            #     def create_custom_forward(module):
-            #         def custom_forward(*inputs):
-            #             # None for past_key_value
-            #             return module(*inputs, output_attentions, None)
-            #         return custom_forward
-            #     # layer_outputs = torch.utils.checkpoint.checkpoint(
-            #     #     create_custom_forward(layer),
-            #     #     hidden_states,
-            #     #     mask,
-            #     #     linear_attn_padding_mask,
-            #     #     None,
-            #     # )
-            #     layer_outputs = torch.utils.checkpoint.checkpoint(
-            #         create_custom_forward(layer),
-            #         hidden_states,
-            #         mask,
-            #         linear_attn_padding_mask,
-            #         None,
-            #         output_attentions,
-            #         use_cache,
-            #         slope_rate,
-            #     )
-            # else:
-            #     layer_outputs = layer(
-            #         hidden_states,
-            #         attn_mask=mask,
-            #         attn_padding_mask=linear_attn_padding_mask,
-            #         past_key_value=past_key_value,
-            #         output_attentions=output_attentions,
-            #         use_cache=use_cache,
-            #         slope_rate=slope_rate,
-            #     )
             layer_outputs = layer(
                 hidden_states,
@@ -789,9 +752,6 @@ class TransnormerModel(TransnormerPreTrainedModel):
             if output_attentions:
                 all_self_attns += (layer_outputs[1],)
-            # if idx == 0:
-            #     break
         hidden_states = self.final_norm(hidden_states)

             slope_rate = slope_rates[idx]
             slope_rate = slope_rate * (1 - idx / (self.num_layers - 1) + 1e-5)
             mask = linear_attn_mask
             layer_outputs = layer(
                 hidden_states,
             if output_attentions:
                 all_self_attns += (layer_outputs[1],)
         hidden_states = self.final_norm(hidden_states)