Instructions to use gradientai/Llama-3-8B-Instruct-262k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gradientai/Llama-3-8B-Instruct-262k with Transformers:

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

pipe = pipeline("text-generation", model="gradientai/Llama-3-8B-Instruct-262k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gradientai/Llama-3-8B-Instruct-262k")
model = AutoModelForCausalLM.from_pretrained("gradientai/Llama-3-8B-Instruct-262k", 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 gradientai/Llama-3-8B-Instruct-262k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gradientai/Llama-3-8B-Instruct-262k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gradientai/Llama-3-8B-Instruct-262k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gradientai/Llama-3-8B-Instruct-262k

SGLang

How to use gradientai/Llama-3-8B-Instruct-262k 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 "gradientai/Llama-3-8B-Instruct-262k" \
    --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": "gradientai/Llama-3-8B-Instruct-262k",
		"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 "gradientai/Llama-3-8B-Instruct-262k" \
        --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": "gradientai/Llama-3-8B-Instruct-262k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use gradientai/Llama-3-8B-Instruct-262k with Docker Model Runner:
```
docker model run hf.co/gradientai/Llama-3-8B-Instruct-262k
```

Update Readme.md

by michaelfeil - opened Apr 25, 2024

base: refs/heads/main

←

from: refs/pr/4

Discussion Files changed

-3

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -9,17 +9,17 @@ tags:
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6585dc9be92bc5f258156bd6/hiHWva3CbsrnPvZTp5-lu.png)
-This model extends LLama-3 8B's context length from 8k to > 160K, developed by Gradient, sponsored by compute from Crusoe Energy. It demonstrates that SOTA LLMs can learn to operate on long context with minimal training (< 200M tokens) by appropriately adjusting RoPE theta.
 **Approach:**
 - [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) as the base
 - NTK-aware interpolation [1] to initialize an optimal schedule for RoPE theta, followed by a new data-driven RoPE theta optimization technique
-- progressive training on increasing context lengths similar to the [Large World Model](https://huggingface.co/LargeWorldModel) [2]
 **Infra:**
-We build on top of the EasyContext Blockwise RingAttention library [3] to scalably and efficiently train on contexts up to 256k in length on Crusoe Energy's high performance L40S cluster.
 **Data:**

 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6585dc9be92bc5f258156bd6/hiHWva3CbsrnPvZTp5-lu.png)
+This model extends LLama-3 8B's context length from 8k to > 160K, developed by Gradient, sponsored by compute from [Crusoe Energy](https://huggingface.co/crusoeai). It demonstrates that SOTA LLMs can learn to operate on long context with minimal training (< 200M tokens) by appropriately adjusting RoPE theta.
 **Approach:**
 - [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) as the base
 - NTK-aware interpolation [1] to initialize an optimal schedule for RoPE theta, followed by a new data-driven RoPE theta optimization technique
+- Progressive training on increasing context lengths similar to the [Large World Model](https://huggingface.co/LargeWorldModel) [2] (See details below)
 **Infra:**
+We build on top of the EasyContext Blockwise RingAttention library [3] to scalably and efficiently train on contexts up to 262144 tokens on [Crusoe Energy](https://huggingface.co/crusoeai) high performance L40S cluster.
 **Data:**