Instructions to use typeof/miqu-70b-split with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use typeof/miqu-70b-split with Transformers:

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

pipe = pipeline("text-generation", model="typeof/miqu-70b-split")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("typeof/miqu-70b-split")
model = AutoModelForCausalLM.from_pretrained("typeof/miqu-70b-split")
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

vLLM

How to use typeof/miqu-70b-split with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "typeof/miqu-70b-split"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "typeof/miqu-70b-split",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/typeof/miqu-70b-split

SGLang

How to use typeof/miqu-70b-split 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 "typeof/miqu-70b-split" \
    --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": "typeof/miqu-70b-split",
		"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 "typeof/miqu-70b-split" \
        --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": "typeof/miqu-70b-split",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use typeof/miqu-70b-split with Docker Model Runner:
```
docker model run hf.co/typeof/miqu-70b-split
```

typeof commited on Feb 5, 2024

Commit

beebbef

1 Parent(s): 926ef97

init

Browse files

Files changed (17) hide show

model-00001-of-00723.safetensors +3 -0
model-00705-of-00723.safetensors +3 -0
model-00706-of-00723.safetensors +3 -0
model-00707-of-00723.safetensors +3 -0
model-00708-of-00723.safetensors +3 -0
model-00709-of-00723.safetensors +3 -0
model-00711-of-00723.safetensors +3 -0
model-00714-of-00723.safetensors +3 -0
model-00715-of-00723.safetensors +3 -0
model-00716-of-00723.safetensors +3 -0
model-00717-of-00723.safetensors +3 -0
model-00718-of-00723.safetensors +3 -0
model-00719-of-00723.safetensors +3 -0
model-00720-of-00723.safetensors +3 -0
model-00721-of-00723.safetensors +3 -0
model-00722-of-00723.safetensors +3 -0
model-00723-of-00723.safetensors +3 -0

model-00001-of-00723.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3fc649c0badaccfbf7d0f934bf4d42aa3114e54fd613f4988583980ee168031d
+size 524288128

model-00705-of-00723.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5abb48b532530f1d2c3ace839933eebdfb3991229978d4eefa3e419a037bf741
+size 16528

model-00706-of-00723.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9ec9c54e7f056c8e628ca3dc3159bf2a68af3e3ee29676de6a0e63056680695b
+size 469762200

model-00707-of-00723.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f4687768b500e6d76e5a03b8b8029a0923322fc330213b02f02c6be8303f4229
+size 469762200

model-00708-of-00723.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:23e20306a0b227e1f82757a4e45309ad31e08e0bc81850f6035f7385ce7c299b
+size 469762192

model-00709-of-00723.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5ae6d15ce301401e78cae93fab1221fd1d7193112fe3ae6c984781b8d75c7ecb
+size 16536

model-00711-of-00723.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3147157502c9c1bc71d023c396a94206e25edfae15d9aeed7ebc59dd7bdecdc4
+size 134217880

model-00714-of-00723.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:65bfdbb7e9814aac3cf82a624b47dcf0d8bb9b1604c3146efe3ec4e7331f1f37
+size 16528

model-00715-of-00723.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5484a4a12ffa9f30001c394d984f2471f68e29494c8dfeeceb2489cd1f18e1
+size 469762200

model-00716-of-00723.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:eddff99e75f53901932328dd41faa15a2c8830e7af1ad9d8efc2e3989a764fa7
+size 469762200

model-00717-of-00723.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9a5b70bd223dbeb15f95def30d23cb31384331aae22456542a198a29c96d1268
+size 469762192

model-00718-of-00723.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5c8c1d080de15fe82c95c92110bb35c171a27287c89cd14b51fdde0df9d0a55e
+size 16536

model-00719-of-00723.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:56cfad1acb47d550b56950f5d8d236fbe5251402ba7d73cd1c1226abd33011c0
+size 16777368

model-00720-of-00723.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d15215349b89905e91675dfeb10081a2dd7101e3f60868ac1456dd6d5c09e5e0
+size 134217880

model-00721-of-00723.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f1ee281b5e389ee778a3763c3b036d70d4d7bcb798995f40cc6db450f78c1c44
+size 134217880

model-00722-of-00723.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cad86b986bc1f725c49eed71074a2ec556170961d8a60b4a1dc8cbe208eaa13e
+size 16777368

model-00723-of-00723.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bcd854e7a21b23ed64112bc947d830b0f0ffaf86cb958d9c08c32d3f33218cf1
+size 16504