Instructions to use Amod/falcon7b-fine-tuned-therapy-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Amod/falcon7b-fine-tuned-therapy-merged with Transformers:

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

pipe = pipeline("text-generation", model="Amod/falcon7b-fine-tuned-therapy-merged", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Amod/falcon7b-fine-tuned-therapy-merged", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Amod/falcon7b-fine-tuned-therapy-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Amod/falcon7b-fine-tuned-therapy-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Amod/falcon7b-fine-tuned-therapy-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Amod/falcon7b-fine-tuned-therapy-merged

SGLang

How to use Amod/falcon7b-fine-tuned-therapy-merged 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 "Amod/falcon7b-fine-tuned-therapy-merged" \
    --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": "Amod/falcon7b-fine-tuned-therapy-merged",
		"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 "Amod/falcon7b-fine-tuned-therapy-merged" \
        --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": "Amod/falcon7b-fine-tuned-therapy-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Amod/falcon7b-fine-tuned-therapy-merged with Docker Model Runner:
```
docker model run hf.co/Amod/falcon7b-fine-tuned-therapy-merged
```

Amod commited on Jun 24, 2023

Commit

e2bb8ae

1 Parent(s): d506aac

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -2

README.md CHANGED Viewed

@@ -1,5 +1,11 @@
 ---
-library_name: peft
 ---
 ## Training procedure
@@ -29,4 +35,4 @@ The following `bitsandbytes` quantization config was used during training:
 - PEFT 0.4.0.dev0
-- PEFT 0.4.0.dev0

 ---
+library_name: transformers
+license: apache-2.0
+datasets:
+- Amod/mental_health_counseling_conversations
+language:
+- en
+pipeline_tag: conversational
 ---
 ## Training procedure
 - PEFT 0.4.0.dev0
+- PEFT 0.4.0.dev0