Instructions to use blockblockblock/Cerebrum-1.0-8x7b-bpw4.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use blockblockblock/Cerebrum-1.0-8x7b-bpw4.2 with Transformers:

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

pipe = pipeline("text-generation", model="blockblockblock/Cerebrum-1.0-8x7b-bpw4.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("blockblockblock/Cerebrum-1.0-8x7b-bpw4.2")
model = AutoModelForCausalLM.from_pretrained("blockblockblock/Cerebrum-1.0-8x7b-bpw4.2", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use blockblockblock/Cerebrum-1.0-8x7b-bpw4.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "blockblockblock/Cerebrum-1.0-8x7b-bpw4.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "blockblockblock/Cerebrum-1.0-8x7b-bpw4.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/blockblockblock/Cerebrum-1.0-8x7b-bpw4.2

SGLang

How to use blockblockblock/Cerebrum-1.0-8x7b-bpw4.2 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 "blockblockblock/Cerebrum-1.0-8x7b-bpw4.2" \
    --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": "blockblockblock/Cerebrum-1.0-8x7b-bpw4.2",
		"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 "blockblockblock/Cerebrum-1.0-8x7b-bpw4.2" \
        --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": "blockblockblock/Cerebrum-1.0-8x7b-bpw4.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use blockblockblock/Cerebrum-1.0-8x7b-bpw4.2 with Docker Model Runner:
```
docker model run hf.co/blockblockblock/Cerebrum-1.0-8x7b-bpw4.2
```

blockblockblock commited on Mar 22, 2024

Commit

18f3e56

verified ·

1 Parent(s): 79e61c4

Upload folder using huggingface_hub

Browse files

Files changed (4) hide show

README.md +1 -1
output-00001-of-00003.safetensors +2 -2
output-00002-of-00003.safetensors +2 -2
output-00003-of-00003.safetensors +2 -2

README.md CHANGED Viewed

@@ -1,5 +1,5 @@
 ---
-base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
 license: apache-2.0
 ---

 ---
+base_model: mistralai/Mixtral-8x7B-v0.1
 license: apache-2.0
 ---

output-00001-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1cdad59f5ef0a8ea7992c9a0ee6815bf275b0c530cca760baa64a6912fb6b2c
-size 8586043088

 version https://git-lfs.github.com/spec/v1
+oid sha256:1a708c352c441f719753268d2c4fe63063b40a03f53eb7d960a66a8ae0507d85
+size 8581187168

output-00002-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c03acf8114aa3d008bc622fabcfc33fdca24883f57bc8fb631e9592117ec8d2
-size 8564290488

 version https://git-lfs.github.com/spec/v1
+oid sha256:0b4c2b54598d3e84e1ca79a576f85096aafeb56b72deb4d5afbf6be5e41fa09a
+size 8579134024

output-00003-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e2289e147ec10e2dda55c3b3daad800f60efe7344a0baf64879cd1f1c49f34c
-size 7591732088

 version https://git-lfs.github.com/spec/v1
+oid sha256:a313390110e4882182b8750fffe6e57abfbc675121caaf8dc1a42973ab997bf4
+size 7585340312