Instructions to use Norquinal/Jamba-v0.1-Claude-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Norquinal/Jamba-v0.1-Claude-Chat with Transformers:

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

pipe = pipeline("text-generation", model="Norquinal/Jamba-v0.1-Claude-Chat")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Norquinal/Jamba-v0.1-Claude-Chat")
model = AutoModelForCausalLM.from_pretrained("Norquinal/Jamba-v0.1-Claude-Chat", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Norquinal/Jamba-v0.1-Claude-Chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Norquinal/Jamba-v0.1-Claude-Chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Norquinal/Jamba-v0.1-Claude-Chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Norquinal/Jamba-v0.1-Claude-Chat

SGLang

How to use Norquinal/Jamba-v0.1-Claude-Chat 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 "Norquinal/Jamba-v0.1-Claude-Chat" \
    --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": "Norquinal/Jamba-v0.1-Claude-Chat",
		"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 "Norquinal/Jamba-v0.1-Claude-Chat" \
        --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": "Norquinal/Jamba-v0.1-Claude-Chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Norquinal/Jamba-v0.1-Claude-Chat with Docker Model Runner:
```
docker model run hf.co/Norquinal/Jamba-v0.1-Claude-Chat
```

Norquinal commited on May 3, 2024

Commit

2392504

verified ·

1 Parent(s): 43b37db

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -3,7 +3,7 @@ datasets:
 - Norquinal/claude_multiround_chat_1k
 license: cc-by-nc-4.0
 ---
-This is [Jamba-v0.1](https://huggingface.co/ai21labs/Jamba-v0.1) fine-tuned using QLoRA (4-bit precision) on my [claude_multiround_chat_1k](https://huggingface.co/datasets/Norquinal/claude_multiround_chat_1k) dataset, which is a randomized subset of ~1000 samples from my [claude_multiround_chat_30k](https://huggingface.co/datasets/Norquinal/claude_multiround_chat_30k) dataset.
 ## Prompt Format
 The model was finetuned with a pseudo-Alpaca format:

 - Norquinal/claude_multiround_chat_1k
 license: cc-by-nc-4.0
 ---
+This is [Jamba-v0.1](https://huggingface.co/ai21labs/Jamba-v0.1) fine-tuned using [QLoRA](https://huggingface.co/Norquinal/Jamba-v0.1-Claude-Chat-LoRA) (4-bit precision) on my [claude_multiround_chat_1k](https://huggingface.co/datasets/Norquinal/claude_multiround_chat_1k) dataset, which is a randomized subset of ~1000 samples from my [claude_multiround_chat_30k](https://huggingface.co/datasets/Norquinal/claude_multiround_chat_30k) dataset.
 ## Prompt Format
 The model was finetuned with a pseudo-Alpaca format: