Instructions to use FPHam/Writing_Partner_Mistral_7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FPHam/Writing_Partner_Mistral_7B with Transformers:

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

pipe = pipeline("text-generation", model="FPHam/Writing_Partner_Mistral_7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FPHam/Writing_Partner_Mistral_7B")
model = AutoModelForCausalLM.from_pretrained("FPHam/Writing_Partner_Mistral_7B", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FPHam/Writing_Partner_Mistral_7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FPHam/Writing_Partner_Mistral_7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FPHam/Writing_Partner_Mistral_7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FPHam/Writing_Partner_Mistral_7B

SGLang

How to use FPHam/Writing_Partner_Mistral_7B 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 "FPHam/Writing_Partner_Mistral_7B" \
    --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": "FPHam/Writing_Partner_Mistral_7B",
		"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 "FPHam/Writing_Partner_Mistral_7B" \
        --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": "FPHam/Writing_Partner_Mistral_7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FPHam/Writing_Partner_Mistral_7B with Docker Model Runner:
```
docker model run hf.co/FPHam/Writing_Partner_Mistral_7B
```

FPHam commited on Nov 13, 2023

Commit

606f30f

1 Parent(s): 0b73251

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -45

README.md CHANGED Viewed

@@ -59,50 +59,5 @@ In the distant reaches of the cosmos, where starlight weaves a tapestry of unkno
 >"Thank you, Ensign," Alara replied, not taking her eyes off the swirling vortex ahead. "Let's see what lies beyond."
-Example 2:
-Give me example of good and bad dialogue
->Good Dialogue Example:
->
->"What do you think?" I asked, holding up my finished project. "Is it okay?"
->
->"It's perfect," Tom said, smiling broadly. He walked over and gave me a hug. "You did great."
->
->Bad Dialogue Example:
->
->"Hey, wanna come over and watch a movie tonight?" Mike asked.
->
->"Sure," Sally replied. "Which one?"
->
->"The new action flick. You know, the one with the guy who used to be on TV."
->
->"Oh, yeah. That one. Okay."
->
->"Okay. So see ya at seven?"
->
->"Sure. See ya at seven."
->
->"See ya."
->
->This exchange lacks any kind of personality, energy, or uniqueness. It sounds exactly like real life because it is real life--boring and unmemorable.
-How would you fix the bad example?
->Here's my revised version:
->
->Mike looked up from his computer. "Sally, do you want to come over and watch a movie tonight?"
->
->She leaned against the doorjamb. "What movie?"
->
->"You know, that new action flick with the guy who used to be on TV."
->
->"Oh, I like him!" She grinned. "I'm in."
->
->He smiled back. "Great. How about seven o'clock?"
->
->"That works for me."
->
->"See ya then."


59	>"Thank you, Ensign," Alara replied, not taking her eyes off the swirling vortex ahead. "Let's see what lies beyond."
60
61













































62
63