Instructions to use YoungXuan/Llama-3.1-8B-NHS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YoungXuan/Llama-3.1-8B-NHS with Transformers:

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

pipe = pipeline("text-generation", model="YoungXuan/Llama-3.1-8B-NHS")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("YoungXuan/Llama-3.1-8B-NHS")
model = AutoModelForCausalLM.from_pretrained("YoungXuan/Llama-3.1-8B-NHS", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use YoungXuan/Llama-3.1-8B-NHS with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YoungXuan/Llama-3.1-8B-NHS"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YoungXuan/Llama-3.1-8B-NHS",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/YoungXuan/Llama-3.1-8B-NHS

SGLang

How to use YoungXuan/Llama-3.1-8B-NHS 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 "YoungXuan/Llama-3.1-8B-NHS" \
    --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": "YoungXuan/Llama-3.1-8B-NHS",
		"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 "YoungXuan/Llama-3.1-8B-NHS" \
        --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": "YoungXuan/Llama-3.1-8B-NHS",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use YoungXuan/Llama-3.1-8B-NHS with Docker Model Runner:
```
docker model run hf.co/YoungXuan/Llama-3.1-8B-NHS
```

Llama-3.1-8B-NHS / config.json

YoungXuan

Llama-3.1-8B TTT-NTP (small-init + specnorm eta 0.3, 200 steps): RULER 67.83 vs base 55.87

0c53399 verified 3 months ago

Raw History Blame Contribute Delete

1.18 kB

{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "dtype": "bfloat16",
  "eos_token_id": 128001,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.3",
  "use_cache": true,
  "vocab_size": 128256,
  "ttt_layers": [
    0,
    6,
    12,
    18,
    24,
    30
  ],
  "ttt_mode": true,
  "ttt_proj": true,
  "ttt_proj_init": "small",
  "ttt_conv": false,
  "ttt_predict_mode": "next",
  "ttt_target": "hidden_states",
  "ttt_update_rule": "paper",
  "ttt_chunk": 1024,
  "ttt_norm_preserve": true,
  "ttt_inner_opt": "specnorm",
  "ttt_lr": 0.3
}

	{
	"architectures": [
	"LlamaForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 128000,
	"dtype": "bfloat16",
	"eos_token_id": 128001,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 14336,
	"max_position_embeddings": 131072,
	"mlp_bias": false,
	"model_type": "llama",
	"num_attention_heads": 32,
	"num_hidden_layers": 32,
	"num_key_value_heads": 8,
	"pretraining_tp": 1,
	"rms_norm_eps": 1e-05,
	"rope_scaling": {
	"factor": 8.0,
	"high_freq_factor": 4.0,
	"low_freq_factor": 1.0,
	"original_max_position_embeddings": 8192,
	"rope_type": "llama3"
	},
	"rope_theta": 500000.0,
	"tie_word_embeddings": false,
	"transformers_version": "4.57.3",
	"use_cache": true,
	"vocab_size": 128256,
	"ttt_layers": [
	0,
	6,
	12,
	18,
	24,
	30
	],
	"ttt_mode": true,
	"ttt_proj": true,
	"ttt_proj_init": "small",
	"ttt_conv": false,
	"ttt_predict_mode": "next",
	"ttt_target": "hidden_states",
	"ttt_update_rule": "paper",
	"ttt_chunk": 1024,
	"ttt_norm_preserve": true,
	"ttt_inner_opt": "specnorm",
	"ttt_lr": 0.3
	}