Instructions to use DevQuasar-3/llama3_8b_chat_brainstorm_plus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DevQuasar-3/llama3_8b_chat_brainstorm_plus with Transformers:

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

pipe = pipeline("text-generation", model="DevQuasar-3/llama3_8b_chat_brainstorm_plus")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DevQuasar-3/llama3_8b_chat_brainstorm_plus")
model = AutoModelForCausalLM.from_pretrained("DevQuasar-3/llama3_8b_chat_brainstorm_plus")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DevQuasar-3/llama3_8b_chat_brainstorm_plus with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DevQuasar-3/llama3_8b_chat_brainstorm_plus"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DevQuasar-3/llama3_8b_chat_brainstorm_plus",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DevQuasar-3/llama3_8b_chat_brainstorm_plus

SGLang

How to use DevQuasar-3/llama3_8b_chat_brainstorm_plus 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 "DevQuasar-3/llama3_8b_chat_brainstorm_plus" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DevQuasar-3/llama3_8b_chat_brainstorm_plus",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "DevQuasar-3/llama3_8b_chat_brainstorm_plus" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DevQuasar-3/llama3_8b_chat_brainstorm_plus",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DevQuasar-3/llama3_8b_chat_brainstorm_plus with Docker Model Runner:
```
docker model run hf.co/DevQuasar-3/llama3_8b_chat_brainstorm_plus
```

csabakecskemeti commited on May 12, 2024

Commit

ceb3d76

verified ·

1 Parent(s): 595517e

Update README.md

Browse files

Files changed (1) hide show

README.md +16 -1

README.md CHANGED Viewed

@@ -2,4 +2,19 @@
 license: apache-2.0
 datasets:
 - DevQuasar/brainstorm_vicuna_10k
----

 license: apache-2.0
 datasets:
 - DevQuasar/brainstorm_vicuna_10k
+base_model: meta-llama/Meta-Llama-3-8B
+pipeline_tag: text-generation
+---
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64e6d37e02dee9bcb9d9fa18/WG1N9oT6suD86W4DpGiml.png)
+# Model intention
+Brainstorm facilitates idea exploration through interaction with a Language Model (LLM).
+Rather than providing direct answers, the model engages in a dialogue with users, offering
+probing questions aimed at fostering deeper contemplation and consideration of various
+facets of their ideas.
+## Examples
+### Inference code
+https://github.com/csabakecskemeti/ai_utils/blob/main/brainstorm_inference.py