Instructions to use RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", trust_remote_code=True)
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

vLLM

How to use RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16

SGLang

How to use RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16 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 "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16" \
    --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": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16",
		"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 "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16" \
        --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": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16
```

Phi-3-medium-128k-instruct-quantized.w4a16 / config.json

mgoin

Updated compression_config to quantization_config

8670dfa verified over 1 year ago

raw

history blame contribute delete

4.24 kB

	{
	"_name_or_path": "/root/.cache/huggingface/hub/models--microsoft--Phi-3-medium-128k-instruct/snapshots/cae1d42b5577398fd1be9f0746052562ae552886",
	"architectures": [
	"Phi3ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"auto_map": {
	"AutoConfig": "configuration_phi3.Phi3Config",
	"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
	},
	"bos_token_id": 1,
	"embd_pdrop": 0.0,
	"eos_token_id": 32000,
	"hidden_act": "silu",
	"hidden_size": 5120,
	"initializer_range": 0.02,
	"intermediate_size": 17920,
	"max_position_embeddings": 131072,
	"model_type": "phi3",
	"num_attention_heads": 40,
	"num_hidden_layers": 40,
	"num_key_value_heads": 10,
	"original_max_position_embeddings": 4096,
	"pad_token_id": null,
	"resid_pdrop": 0.0,
	"rms_norm_eps": 1e-05,
	"rope_scaling": {
	"long_factor": [
	1.0,
	1.0,
	1.0,
	1.0,
	1.0,
	1.0,
	1.0,
	1.0,
	1.0,
	1.0,
	1.0,
	1.0,
	1.0,
	1.25,
	1.25,
	1.5,
	2.0,
	2.75,
	5.75,
	5.75,
	6.5,
	9.25,
	11.0,
	13.25,
	19.25,
	19.75,
	19.75,
	21.25,
	21.5,
	26.5,
	30.0,
	33.75,
	35.25,
	38.5,
	42.0,
	42.25,
	46.0,
	47.0,
	50.0,
	50.5,
	51.0,
	52.0,
	52.75,
	53.75,
	54.75,
	57.0,
	57.25,
	58.5,
	59.25,
	59.5,
	62.0,
	62.5,
	62.75,
	63.25,
	63.25,
	63.25,
	63.75,
	64.0,
	64.0,
	64.25,
	64.5,
	64.5,
	65.0,
	65.0
	],
	"short_factor": [
	1.0,
	1.0,
	1.0,
	1.0,
	1.0,
	1.0,
	1.01,
	1.02,
	1.02,
	1.04,
	1.04,
	1.07,
	1.07,
	1.1,
	1.3000000000000003,
	1.3000000000000003,
	1.5000000000000004,
	1.5700000000000005,
	1.9000000000000008,
	2.3100000000000014,
	2.759999999999992,
	3.3899999999999784,
	3.9399999999999666,
	4.009999999999965,
	4.289999999999959,
	4.349999999999958,
	5.349999999999937,
	6.659999999999909,
	7.029999999999901,
	7.51999999999989,
	8.00999999999988,
	8.249999999999876,
	8.279999999999875,
	9.629999999999846,
	9.89999999999984,
	10.589999999999826,
	11.049999999999816,
	11.7899999999998,
	12.189999999999792,
	12.889999999999777,
	13.129999999999772,
	13.16999999999977,
	13.20999999999977,
	13.479999999999764,
	13.539999999999763,
	13.779999999999758,
	13.929999999999755,
	14.429999999999744,
	14.759999999999737,
	15.149999999999729,
	15.419999999999723,
	15.53999999999972,
	15.659999999999718,
	15.749999999999716,
	15.759999999999716,
	15.799999999999715,
	16.05999999999971,
	16.079999999999714,
	16.11999999999972,
	16.11999999999972,
	16.18999999999973,
	16.31999999999975,
	16.539999999999786,
	16.799999999999827
	],
	"type": "su"
	},
	"rope_theta": 10000.0,
	"sliding_window": 131072,
	"tie_word_embeddings": false,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.42.4",
	"use_cache": true,
	"vocab_size": 32064,
	"quantization_config": {
	"config_groups": {
	"group_0": {
	"input_activations": null,
	"output_activations": null,
	"targets": [
	"Linear"
	],
	"weights": {
	"block_structure": null,
	"dynamic": false,
	"group_size": 128,
	"num_bits": 4,
	"observer": "minmax",
	"observer_kwargs": {},
	"strategy": "group",
	"symmetric": true,
	"type": "int"
	}
	}
	},
	"format": "pack-quantized",
	"global_compression_ratio": 1.4217800438908097,
	"ignore": [
	"lm_head"
	],
	"kv_cache_scheme": null,
	"quant_method": "compressed-tensors",
	"quantization_status": "frozen",
	"sparsity_config": {
	"format": "dense",
	"global_sparsity": 14.910563402082037,
	"registry_requires_subclass": false,
	"sparsity_structure": "unstructured"
	}
	}
	}