Instructions to use normalcomputing/extended-mind-llama-2-7b-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use normalcomputing/extended-mind-llama-2-7b-chat with Transformers:

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

pipe = pipeline("text-generation", model="normalcomputing/extended-mind-llama-2-7b-chat", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("normalcomputing/extended-mind-llama-2-7b-chat", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use normalcomputing/extended-mind-llama-2-7b-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "normalcomputing/extended-mind-llama-2-7b-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "normalcomputing/extended-mind-llama-2-7b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/normalcomputing/extended-mind-llama-2-7b-chat

SGLang

How to use normalcomputing/extended-mind-llama-2-7b-chat 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 "normalcomputing/extended-mind-llama-2-7b-chat" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "normalcomputing/extended-mind-llama-2-7b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "normalcomputing/extended-mind-llama-2-7b-chat" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "normalcomputing/extended-mind-llama-2-7b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use normalcomputing/extended-mind-llama-2-7b-chat with Docker Model Runner:
```
docker model run hf.co/normalcomputing/extended-mind-llama-2-7b-chat
```

phoebeklett commited on May 30, 2024

Commit

e7bd27f

verified ·

1 Parent(s): 4b1c32e

Upload 2 files

Browse files

Files changed (1) hide show

modeling.py +2 -1

modeling.py CHANGED Viewed

@@ -654,7 +654,7 @@ class ExtendedLlamaAttention(nn.Module):
         if not output_attentions:
             attn_weights = None
-        if not output_retrieved_memory_idx:
             reshaped_idx = None
         return attn_output, attn_weights, past_key_value, reshaped_idx
@@ -1568,6 +1568,7 @@ class ExtendedLlamaForCausalLM(LlamaPreTrainedModel):
                 "attention_mask": attention_mask,
                 "use_external_mind": kwargs.get("use_external_mind"), # EM: Add config here
                 "topk": kwargs.get("topk"),
             }
         )
         return model_inputs

         if not output_attentions:
             attn_weights = None
+        if not output_retrieved_memory_idx or (long_range_past_key_value is None and faiss_indexes is None):
             reshaped_idx = None
         return attn_output, attn_weights, past_key_value, reshaped_idx
                 "attention_mask": attention_mask,
                 "use_external_mind": kwargs.get("use_external_mind"), # EM: Add config here
                 "topk": kwargs.get("topk"),
+                "output_retrieved_memory_idx": kwargs.get("output_retrieved_memory_idx"),
             }
         )
         return model_inputs