Not-for-all-Audiences

Instructions to use sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0 with Transformers:

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

pipe = pipeline("text-generation", model="sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0")
model = AutoModelForCausalLM.from_pretrained("sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0")
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
Local Apps Settings

vLLM

How to use sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0

SGLang

How to use sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0 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 "sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0" \
    --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": "sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0",
		"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 "sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0" \
        --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": "sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0 with Docker Model Runner:
```
docker model run hf.co/sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0
```

sophosympatheia commited on Jun 21, 2024

Commit

8dec167

verified ·

1 Parent(s): 998403c

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -35,7 +35,7 @@ You can run this model out to 32K context with alpha_rope set to 1.
 * I recommend using Quadratic Sampling (i.e. smoothing factor) for creative work. I think this version performs best with a smoothing factor close to 0.2.
 * I recommend using Min-P. Experiment to find your best setting. I find this model tolerates high Min-P settings rather nicely, but use whatever floats your boat.
 * You can enable dynamic temperature if you want, but that adds yet another variable to consider and I find it's unnecessary with you're already using Min-P and smoothing factor.
-* If you use Textgen WebUI as your backend, I recommend enabling the DRY sample settings to reduce repititions, otherwise some repitition penalty plus frequency penalty ought to do the trick.
 Experiment with any and all of the settings below! What suits my preferences may not suit yours.
@@ -466,10 +466,10 @@ dtype: float16
 ---
 name: new-dawn-llama3-70b-32K-v1.0
 models:
-  - model: /home/llm/mergequant/models/new-dawn-llama3-70b-v0.16-32K
-  - model: /home/llm/mergequant/models/new-dawn-llama3-70b-v0.18-32K
 merge_method: slerp
-base_model: /home/llm/mergequant/models/new-dawn-llama3-70b-v0.16-32K
 parameters:
   t:
     - value: 0.5

 * I recommend using Quadratic Sampling (i.e. smoothing factor) for creative work. I think this version performs best with a smoothing factor close to 0.2.
 * I recommend using Min-P. Experiment to find your best setting. I find this model tolerates high Min-P settings rather nicely, but use whatever floats your boat.
 * You can enable dynamic temperature if you want, but that adds yet another variable to consider and I find it's unnecessary with you're already using Min-P and smoothing factor.
+* If you use Textgen WebUI as your backend, I recommend enabling the DRY sampler settings to reduce repititions, otherwise some repitition penalty plus frequency penalty ought to do the trick.
 Experiment with any and all of the settings below! What suits my preferences may not suit yours.
 ---
 name: new-dawn-llama3-70b-32K-v1.0
 models:
+  - model: new-dawn-llama3-70b-v0.16-32K
+  - model: new-dawn-llama3-70b-v0.18-32K
 merge_method: slerp
+base_model: new-dawn-llama3-70b-v0.16-32K
 parameters:
   t:
     - value: 0.5