Instructions to use danielpark/asp-9b-inst-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use danielpark/asp-9b-inst-base with Transformers:

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

pipe = pipeline("text-generation", model="danielpark/asp-9b-inst-base", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("danielpark/asp-9b-inst-base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("danielpark/asp-9b-inst-base", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use danielpark/asp-9b-inst-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "danielpark/asp-9b-inst-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "danielpark/asp-9b-inst-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/danielpark/asp-9b-inst-base

SGLang

How to use danielpark/asp-9b-inst-base 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 "danielpark/asp-9b-inst-base" \
    --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": "danielpark/asp-9b-inst-base",
		"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 "danielpark/asp-9b-inst-base" \
        --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": "danielpark/asp-9b-inst-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use danielpark/asp-9b-inst-base with Docker Model Runner:
```
docker model run hf.co/danielpark/asp-9b-inst-base
```

Update README.md

by danielpark - opened Apr 26, 2024

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-1

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -13,7 +13,8 @@ tags:
 Required Weights for Follow-up Research
-The original model is **AI21lab's Jamba-v0.1**, which requires an **A100 80GB GPU**. Unfortunately, this was not available via Google Colab or cloud computing services. Attempts were made to perform **MoE (Mixture of Experts) splitting**, using the following resources as a basis:
 - **Original Model:** [Jamba-v0.1](https://huggingface.co/ai21labs/Jamba-v0.1)
 - **MoE Layer Separation**: Consult [this script](https://github.com/TechxGenus/Jamba-utils/blob/main/dense_downcycling.py) and using [TechxGenus/Jamba-v0.1-9B](https://huggingface.co/TechxGenus/Jamba-v0.1-9B).

 Required Weights for Follow-up Research
+The original model is **[AI21lab's Jamba-v0.1](https://huggingface.co/ai21labs/Jamba-v0.1)**, which requires an **A100 80GB GPU**. Unfortunately, this almonst was not available via Google Colab or cloud computing services. Thus, attempts were made to perform **MoE (Mixture of Experts) splitting**, using the following resources as a basis:
 - **Original Model:** [Jamba-v0.1](https://huggingface.co/ai21labs/Jamba-v0.1)
 - **MoE Layer Separation**: Consult [this script](https://github.com/TechxGenus/Jamba-utils/blob/main/dense_downcycling.py) and using [TechxGenus/Jamba-v0.1-9B](https://huggingface.co/TechxGenus/Jamba-v0.1-9B).
+Check [ai21labs/Jamba-tiny-random](https://huggingface.co/ai21labs/Jamba-tiny-random), which has 128M parameters (instead of 52B), and is initialized with random weights and did not undergo any training.has 128M parameters (instead of 52B), and is initialized with random weights and did not undergo any training.