Instructions to use LumiOpen/Llama-Poro-2-8B-Long-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LumiOpen/Llama-Poro-2-8B-Long-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="LumiOpen/Llama-Poro-2-8B-Long-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

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

tokenizer = AutoTokenizer.from_pretrained("LumiOpen/Llama-Poro-2-8B-Long-Instruct")
model = AutoModelForCausalLM.from_pretrained("LumiOpen/Llama-Poro-2-8B-Long-Instruct", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LumiOpen/Llama-Poro-2-8B-Long-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LumiOpen/Llama-Poro-2-8B-Long-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LumiOpen/Llama-Poro-2-8B-Long-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LumiOpen/Llama-Poro-2-8B-Long-Instruct

SGLang

How to use LumiOpen/Llama-Poro-2-8B-Long-Instruct 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 "LumiOpen/Llama-Poro-2-8B-Long-Instruct" \
    --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": "LumiOpen/Llama-Poro-2-8B-Long-Instruct",
		"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 "LumiOpen/Llama-Poro-2-8B-Long-Instruct" \
        --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": "LumiOpen/Llama-Poro-2-8B-Long-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LumiOpen/Llama-Poro-2-8B-Long-Instruct with Docker Model Runner:
```
docker model run hf.co/LumiOpen/Llama-Poro-2-8B-Long-Instruct
```

Llama-Poro-2-8B-Long-Instruct / config.json

ezosa

Upload model from /shared_silo/scratch/elaizosa/models/poro-2-long-instruct-sft-merged-80-20

fb680b9 verified 5 months ago

Raw History Blame Contribute Delete

4.24 kB

{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "dtype": "float16",
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "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,
  "original_max_position_embeddings": 8192,
  "pad_token_id": 128009,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 16.0,
    "long_factor": [
0700000524520874,
100000023841858,
1399999856948853,
1399999856948853,
149999976158142,
159999966621399,
159999966621399,
1799999475479126,
1799999475479126,
1899999380111694,
2299998998641968,
2299998998641968,
2999998331069946,
3799998760223389,
429999828338623,
4399996995925903,
869999647140503,
9199997186660767,
9399996995925903,
3799996376037598,
4599997997283936,
499999761581421,
9099998474121094,
2799994945526123,
8399994373321533,
589999198913574,
739999771118164,
800000190734863,
260000228881836,
260000228881836,
310000419616699,
330000877380371,
209999084472656,
889999389648438,
729999542236328,
369999885559082,
589999198913574,
589999198913574,
479998588562012,
479998588562012,
489999771118164,
899998664855957,
989998817443848,
049999237060547,
10999870300293,
10999870300293,
1299991607666,
170000076293945,
190000534057617,
200000762939453,
200000762939453,
30000114440918,
329999923706055,
329999923706055,
34000015258789,
530000686645508,
64000129699707,
68000030517578,
700000762939453,
700002670288086,
790002822875977,
800003051757812,
800003051757812,
01000213623047
    ],
    "original_max_position_embeddings": 8192,
    "rope_type": "longrope",
    "short_factor": [
0700000524520874,
100000023841858,
1399999856948853,
1399999856948853,
149999976158142,
159999966621399,
159999966621399,
1799999475479126,
1799999475479126,
1899999380111694,
2299998998641968,
2299998998641968,
2999998331069946,
3799998760223389,
429999828338623,
4399996995925903,
869999647140503,
9199997186660767,
9399996995925903,
3799996376037598,
4599997997283936,
499999761581421,
9099998474121094,
2799994945526123,
8399994373321533,
589999198913574,
739999771118164,
800000190734863,
260000228881836,
260000228881836,
310000419616699,
330000877380371,
209999084472656,
889999389648438,
729999542236328,
369999885559082,
589999198913574,
589999198913574,
479998588562012,
479998588562012,
489999771118164,
899998664855957,
989998817443848,
049999237060547,
10999870300293,
10999870300293,
1299991607666,
170000076293945,
190000534057617,
200000762939453,
200000762939453,
30000114440918,
329999923706055,
329999923706055,
34000015258789,
530000686645508,
64000129699707,
68000030517578,
700000762939453,
700002670288086,
790002822875977,
800003051757812,
800003051757812,
01000213623047
    ],
    "type": "longrope"
  },
  "rope_theta": 500000,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.1",
  "use_cache": true,
  "vocab_size": 128256
}

	{
	"architectures": [
	"LlamaForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 128000,
	"dtype": "float16",
	"eos_token_id": [
	128001,
	128008,
	128009
	],
	"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,
	"original_max_position_embeddings": 8192,
	"pad_token_id": 128009,
	"pretraining_tp": 1,
	"rms_norm_eps": 1e-05,
	"rope_scaling": {
	"factor": 16.0,
	"long_factor": [
	1.0700000524520874,
	1.100000023841858,
	1.1399999856948853,
	1.1399999856948853,
	1.149999976158142,
	1.159999966621399,
	1.159999966621399,
	1.1799999475479126,
	1.1799999475479126,
	1.1899999380111694,
	1.2299998998641968,
	1.2299998998641968,
	1.2999998331069946,
	1.3799998760223389,
	1.429999828338623,
	1.4399996995925903,
	1.869999647140503,
	1.9199997186660767,
	1.9399996995925903,
	2.3799996376037598,
	2.4599997997283936,
	2.499999761581421,
	2.9099998474121094,
	3.2799994945526123,
	3.8399994373321533,
	4.589999198913574,
	4.739999771118164,
	4.800000190734863,
	5.260000228881836,
	5.260000228881836,
	6.310000419616699,
	8.330000877380371,
	9.209999084472656,
	9.889999389648438,
	10.729999542236328,
	11.369999885559082,
	13.589999198913574,
	13.589999198913574,
	15.479998588562012,
	15.479998588562012,
	15.489999771118164,
	15.899998664855957,
	15.989998817443848,
	16.049999237060547,
	16.10999870300293,
	16.10999870300293,
	16.1299991607666,
	16.170000076293945,
	16.190000534057617,
	16.200000762939453,
	16.200000762939453,
	16.30000114440918,
	16.329999923706055,
	16.329999923706055,
	16.34000015258789,
	16.530000686645508,
	16.64000129699707,
	16.68000030517578,
	16.700000762939453,
	16.700002670288086,
	16.790002822875977,
	16.800003051757812,
	16.800003051757812,
	17.01000213623047
	],
	"original_max_position_embeddings": 8192,
	"rope_type": "longrope",
	"short_factor": [
	1.0700000524520874,
	1.100000023841858,
	1.1399999856948853,
	1.1399999856948853,
	1.149999976158142,
	1.159999966621399,
	1.159999966621399,
	1.1799999475479126,
	1.1799999475479126,
	1.1899999380111694,
	1.2299998998641968,
	1.2299998998641968,
	1.2999998331069946,
	1.3799998760223389,
	1.429999828338623,
	1.4399996995925903,
	1.869999647140503,
	1.9199997186660767,
	1.9399996995925903,
	2.3799996376037598,
	2.4599997997283936,
	2.499999761581421,
	2.9099998474121094,
	3.2799994945526123,
	3.8399994373321533,
	4.589999198913574,
	4.739999771118164,
	4.800000190734863,
	5.260000228881836,
	5.260000228881836,
	6.310000419616699,
	8.330000877380371,
	9.209999084472656,
	9.889999389648438,
	10.729999542236328,
	11.369999885559082,
	13.589999198913574,
	13.589999198913574,
	15.479998588562012,
	15.479998588562012,
	15.489999771118164,
	15.899998664855957,
	15.989998817443848,
	16.049999237060547,
	16.10999870300293,
	16.10999870300293,
	16.1299991607666,
	16.170000076293945,
	16.190000534057617,
	16.200000762939453,
	16.200000762939453,
	16.30000114440918,
	16.329999923706055,
	16.329999923706055,
	16.34000015258789,
	16.530000686645508,
	16.64000129699707,
	16.68000030517578,
	16.700000762939453,
	16.700002670288086,
	16.790002822875977,
	16.800003051757812,
	16.800003051757812,
	17.01000213623047
	],
	"type": "longrope"
	},
	"rope_theta": 500000,
	"tie_word_embeddings": false,
	"transformers_version": "4.57.1",
	"use_cache": true,
	"vocab_size": 128256
	}