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

Libraries

How to use pearl-ai/Llama-3.1-8B-Instruct-pearl with Transformers:

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

pipe = pipeline("text-generation", model="pearl-ai/Llama-3.1-8B-Instruct-pearl")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pearl-ai/Llama-3.1-8B-Instruct-pearl")
model = AutoModelForCausalLM.from_pretrained("pearl-ai/Llama-3.1-8B-Instruct-pearl", 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 pearl-ai/Llama-3.1-8B-Instruct-pearl with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/pearl-ai/Llama-3.1-8B-Instruct-pearl

SGLang

How to use pearl-ai/Llama-3.1-8B-Instruct-pearl 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 "pearl-ai/Llama-3.1-8B-Instruct-pearl" \
    --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": "pearl-ai/Llama-3.1-8B-Instruct-pearl",
		"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 "pearl-ai/Llama-3.1-8B-Instruct-pearl" \
        --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": "pearl-ai/Llama-3.1-8B-Instruct-pearl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Llama-3.1-8B-Instruct-pearl / config.json

netanell-pearl

Inital commit

9741b87 4 months ago

Raw

History Blame Contribute Delete

3.13 kB

	{
	"architectures": [
	"LlamaForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 128000,
	"dtype": "bfloat16",
	"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,
	"pretraining_tp": 1,
	"quantization_config": {
	"config_groups": {
	"group_0": {
	"format": "float-quantized",
	"input_activations": {
	"actorder": null,
	"block_structure": null,
	"dynamic": true,
	"group_size": 128,
	"num_bits": 8,
	"observer": null,
	"observer_kwargs": {},
	"strategy": "group",
	"symmetric": true,
	"type": "float"
	},
	"output_activations": null,
	"targets": [
	"re:.*\\.down_proj$",
	"re:model\\.layers\\.([0-9]\|1[0-5])\\.self_attn\\.[qkv]_proj$"
	],
	"weights": {
	"actorder": null,
	"block_structure": [
	128,
	128
	],
	"dynamic": false,
	"group_size": null,
	"num_bits": 8,
	"observer": "minmax",
	"observer_kwargs": {},
	"strategy": "block",
	"symmetric": true,
	"type": "float"
	}
	},
	"group_1": {
	"format": "int-quantized",
	"input_activations": {
	"actorder": null,
	"block_structure": null,
	"dynamic": true,
	"group_size": null,
	"num_bits": 7,
	"observer": null,
	"observer_kwargs": {},
	"strategy": "token",
	"symmetric": true,
	"type": "int"
	},
	"output_activations": null,
	"targets": [
	"re:.*self_attn\\.o_proj$",
	"re:.*\\.gate_proj$",
	"re:.*\\.up_proj$",
	"re:model\\.layers\\.(1[6-9]\|2[0-9]\|3[01])\\.self_attn\\.[qkv]_proj$"
	],
	"weights": {
	"actorder": null,
	"block_structure": null,
	"dynamic": false,
	"group_size": null,
	"num_bits": 7,
	"observer": "minmax",
	"observer_kwargs": {},
	"strategy": "channel",
	"symmetric": true,
	"type": "int"
	}
	}
	},
	"format": "mixed-precision",
	"global_compression_ratio": null,
	"ignore": [
	"lm_head"
	],
	"kv_cache_scheme": null,
	"quant_method": "pearl",
	"quantization_status": "compressed",
	"sparsity_config": {},
	"transform_config": {},
	"version": "0.13.0"
	},
	"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": "4.57.6",
	"use_cache": true,
	"vocab_size": 128256
	}