Instructions to use newmindai/Llama-3.1-8B-Instruct-w16a8-rw-with-gw-hp-4nodes with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use newmindai/Llama-3.1-8B-Instruct-w16a8-rw-with-gw-hp-4nodes with Transformers:

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

pipe = pipeline("text-generation", model="newmindai/Llama-3.1-8B-Instruct-w16a8-rw-with-gw-hp-4nodes")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("newmindai/Llama-3.1-8B-Instruct-w16a8-rw-with-gw-hp-4nodes")
model = AutoModelForCausalLM.from_pretrained("newmindai/Llama-3.1-8B-Instruct-w16a8-rw-with-gw-hp-4nodes", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use newmindai/Llama-3.1-8B-Instruct-w16a8-rw-with-gw-hp-4nodes with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "newmindai/Llama-3.1-8B-Instruct-w16a8-rw-with-gw-hp-4nodes"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "newmindai/Llama-3.1-8B-Instruct-w16a8-rw-with-gw-hp-4nodes",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/newmindai/Llama-3.1-8B-Instruct-w16a8-rw-with-gw-hp-4nodes

SGLang

How to use newmindai/Llama-3.1-8B-Instruct-w16a8-rw-with-gw-hp-4nodes 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 "newmindai/Llama-3.1-8B-Instruct-w16a8-rw-with-gw-hp-4nodes" \
    --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": "newmindai/Llama-3.1-8B-Instruct-w16a8-rw-with-gw-hp-4nodes",
		"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 "newmindai/Llama-3.1-8B-Instruct-w16a8-rw-with-gw-hp-4nodes" \
        --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": "newmindai/Llama-3.1-8B-Instruct-w16a8-rw-with-gw-hp-4nodes",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use newmindai/Llama-3.1-8B-Instruct-w16a8-rw-with-gw-hp-4nodes with Docker Model Runner:
```
docker model run hf.co/newmindai/Llama-3.1-8B-Instruct-w16a8-rw-with-gw-hp-4nodes
```

Llama-3.1-8B-Instruct-w16a8-rw-with-gw-hp-4nodes / training_info.json

nmmursit

Update training_info.json

417979f verified 9 months ago

Raw

History Blame Contribute Delete

2.31 kB

	{
	"base_model": "meta-llama/Llama-3.1-8B-Instruct",
	"dataset": "newmindai/euro_hpc-legal",
	"training_args": {
	"model_id": "meta-llama/Llama-3.1-8B-Instruct",
	"trust_remote_code": true,
	"dataset": "newmindai/euro_hpc-legal",
	"dataset_config": null,
	"split": "train",
	"format": "qa",
	"seq_len": 4096,
	"num_samples": null,
	"combine_configs": true,
	"output_dir": "./lama3.1_8b_rowwise_with_gw_hp_4nodes",
	"num_epochs": 1,
	"max_steps": 1000,
	"batch_size": 8,
	"gradient_accumulation_steps": 8,
	"lr": 2e-05,
	"weight_decay": 0.01,
	"adam_beta1": 0.9,
	"adam_beta2": 0.95,
	"adam_epsilon": 1e-08,
	"max_grad_norm": 1.0,
	"lr_scheduler_type": "cosine",
	"warmup_steps": 100,
	"warmup_ratio": 0.1,
	"dtype": "bf16",
	"fp8": true,
	"save_steps": 500,
	"save_total_limit": 2,
	"save_best_metric": "val_loss",
	"resume_from_checkpoint": null,
	"val_steps": 5,
	"val_samples": 1000,
	"val_batch_size": null,
	"eval_split": "test",
	"eval_samples": 1000,
	"run_final_eval": true,
	"logging_steps": 1,
	"log_file": "./lama3.1_8b_rowwise_with_gw_hp_4nodes/logs/training.log",
	"use_wandb": true,
	"wandb_entity": null,
	"use_tensorboard": false,
	"tensorboard_dir": null,
	"compile": false,
	"gradient_checkpointing": true,
	"seed": 100,
	"fsdp_cpu_offload": false,
	"enable_profiler": false,
	"profiler_output_dir": null,
	"profiler_wait_steps": 1,
	"profiler_warmup_steps": 1,
	"profiler_active_steps": 3,
	"profiler_repeat": 1,
	"profiler_record_shapes": false,
	"profiler_profile_memory": false,
	"profiler_with_stack": false,
	"profiler_with_flops": false,
	"profiler_with_modules": false,
	"profiler_print_summary": false,
	"enable_tf32": true,
	"disable_tf32": false,
	"cudnn_benchmark": true,
	"flash_attention": true,
	"memory_efficient_attention": true,
	"attn_implementation": "sdpa",
	"input_scaling_granularity": "axiswise",
	"input_dtype": "e4m3fn",
	"weight_scaling_granularity": "axiswise",
	"weight_dtype": "e4m3fn",
	"grad_output_scaling_granularity": "axiswise",
	"grad_output_dtype": "e4m3fn",
	"fp8_recipe": "rowwise_with_gw_hp"
	},
	"checkpoint_type": "distributed_sharded"
	}