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

Libraries

How to use FuseAI/FuseChat-7B-TA with Transformers:

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

pipe = pipeline("text-generation", model="FuseAI/FuseChat-7B-TA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FuseAI/FuseChat-7B-TA")
model = AutoModelForCausalLM.from_pretrained("FuseAI/FuseChat-7B-TA")
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 FuseAI/FuseChat-7B-TA with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/FuseAI/FuseChat-7B-TA

SGLang

How to use FuseAI/FuseChat-7B-TA 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 "FuseAI/FuseChat-7B-TA" \
    --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": "FuseAI/FuseChat-7B-TA",
		"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 "FuseAI/FuseChat-7B-TA" \
        --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": "FuseAI/FuseChat-7B-TA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FuseAI/FuseChat-7B-TA with Docker Model Runner:
```
docker model run hf.co/FuseAI/FuseChat-7B-TA
```

Wanfq commited on Mar 8, 2024

Commit

31b828e

verified ·

1 Parent(s): c8e22d8

Update README.md

Browse files

Files changed (1) hide show

README.md +18 -0

README.md CHANGED Viewed

@@ -2,6 +2,9 @@
 license: apache-2.0
 language:
 - en
 pipeline_tag: text-generation
 tags:
 - mistral
@@ -10,6 +13,21 @@ tags:
 - model-fusion
 - fusechat
 library_name: transformers
 ---
 <p align="center" width="100%">
 </p>

 license: apache-2.0
 language:
 - en
+base_model: openchat/openchat_3.5
+datasets:
+- FuseAI/FuseChat-Mixture
 pipeline_tag: text-generation
 tags:
 - mistral
 - model-fusion
 - fusechat
 library_name: transformers
+model-index:
+- name: FuseChat-7B-TA
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MT-Bench
+      type: unknown
+    metrics:
+    - type: unknown
+      value: 8.20
+      name: score
+    source:
+      url: https://huggingface.co/spaces/lmsys/mt-bench
 ---
 <p align="center" width="100%">
 </p>