Instructions to use bitext/Mistral-7B-Customer-Support with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bitext/Mistral-7B-Customer-Support with Transformers:

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

pipe = pipeline("text-generation", model="bitext/Mistral-7B-Customer-Support")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bitext/Mistral-7B-Customer-Support")
model = AutoModelForCausalLM.from_pretrained("bitext/Mistral-7B-Customer-Support")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bitext/Mistral-7B-Customer-Support with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/bitext/Mistral-7B-Customer-Support

SGLang

How to use bitext/Mistral-7B-Customer-Support 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 "bitext/Mistral-7B-Customer-Support" \
    --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": "bitext/Mistral-7B-Customer-Support",
		"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 "bitext/Mistral-7B-Customer-Support" \
        --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": "bitext/Mistral-7B-Customer-Support",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bitext/Mistral-7B-Customer-Support with Docker Model Runner:
```
docker model run hf.co/bitext/Mistral-7B-Customer-Support
```

Bitext commited on May 15, 2024

Commit

afdd454

verified ·

1 Parent(s): 40dd104

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ widget:
         content: I want to cancel an order
 ---
-# Mistral-7B-Customer-Service-v0.2
 ## Model Description
@@ -32,8 +32,8 @@ This model is a fine-tuned version of the [mistralai/Mistral-7B-Instruct-v0.2](h
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-model = AutoModelForCausalLM.from_pretrained("bitext-llm/Mistral-7B-Customer-Service-v0.2")
-tokenizer = AutoTokenizer.from_pretrained("bitext-llm/Mistral-7B-Customer-Service-v0.2")
 inputs = tokenizer("<s>[INST] I want to change to the standard account [/INST] ", return_tensors="pt")
 outputs = model.generate(inputs['input_ids'], max_length=50)
@@ -134,7 +134,7 @@ This model was developed by Bitext and trained on infrastructure provided by Bit
 ## License
-This model, "Mistral-7B-Customer-Service-v0.2," is licensed under the Apache License 2.0 by Bitext Innovations International, Inc. This open-source license allows for free use, modification, and distribution of the model but requires that proper credit be given to Bitext.
 ### Key Points of the Apache 2.0 License

         content: I want to cancel an order
 ---
+# Mistral-7B-Customer-Support-v1
 ## Model Description
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+model = AutoModelForCausalLM.from_pretrained("bitext-llm/Mistral-7B-Customer-Support-v1")
+tokenizer = AutoTokenizer.from_pretrained("bitext-llm/Mistral-7B-Customer-Support-v1")
 inputs = tokenizer("<s>[INST] I want to change to the standard account [/INST] ", return_tensors="pt")
 outputs = model.generate(inputs['input_ids'], max_length=50)
 ## License
+This model, "Mistral-7B-Customer-Support-v1," is licensed under the Apache License 2.0 by Bitext Innovations International, Inc. This open-source license allows for free use, modification, and distribution of the model but requires that proper credit be given to Bitext.
 ### Key Points of the Apache 2.0 License