Instructions to use hackint0sh/new_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hackint0sh/new_model with Transformers:

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

pipe = pipeline("text-generation", model="hackint0sh/new_model", 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("hackint0sh/new_model", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("hackint0sh/new_model", 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 hackint0sh/new_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hackint0sh/new_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hackint0sh/new_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hackint0sh/new_model

SGLang

How to use hackint0sh/new_model 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 "hackint0sh/new_model" \
    --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": "hackint0sh/new_model",
		"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 "hackint0sh/new_model" \
        --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": "hackint0sh/new_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hackint0sh/new_model with Docker Model Runner:
```
docker model run hf.co/hackint0sh/new_model
```

new_model / config.json

hackint0sh

Upload Phi3ForCausalLM

ca7c469 verified about 2 years ago

raw

history blame contribute delete

3.84 kB

	{
	"_name_or_path": "phi-3-new",
	"architectures": [
	"Phi3ForCausalLM"
	],
	"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": 3072,
	"initializer_range": 0.02,
	"intermediate_size": 8192,
	"max_position_embeddings": 131072,
	"model_type": "phi3",
	"num_attention_heads": 32,
	"num_hidden_layers": 32,
	"num_key_value_heads": 32,
	"original_max_position_embeddings": 4096,
	"pad_token_id": 32000,
	"pretraining_tp": 1,
	"quantization_config": {
	"_load_in_4bit": true,
	"_load_in_8bit": false,
	"bnb_4bit_compute_dtype": "float16",
	"bnb_4bit_quant_storage": "uint8",
	"bnb_4bit_quant_type": "nf4",
	"bnb_4bit_use_double_quant": false,
	"llm_int8_enable_fp32_cpu_offload": false,
	"llm_int8_has_fp16_weight": false,
	"llm_int8_skip_modules": null,
	"llm_int8_threshold": 6.0,
	"load_in_4bit": true,
	"load_in_8bit": false,
	"quant_method": "bitsandbytes"
	},
	"resid_pdrop": 0.0,
	"rms_norm_eps": 1e-05,
	"rope_scaling": {
	"long_factor": [
	1.0299999713897705,
	1.0499999523162842,
	1.0499999523162842,
	1.0799999237060547,
	1.2299998998641968,
	1.2299998998641968,
	1.2999999523162842,
	1.4499999284744263,
	1.5999999046325684,
	1.6499998569488525,
	1.8999998569488525,
	2.859999895095825,
	3.68999981880188,
	5.419999599456787,
	5.489999771118164,
	5.489999771118164,
	9.09000015258789,
	11.579999923706055,
	15.65999984741211,
	15.769999504089355,
	15.789999961853027,
	18.360000610351562,
	21.989999771118164,
	23.079999923706055,
	30.009998321533203,
	32.35000228881836,
	32.590003967285156,
	35.56000518798828,
	39.95000457763672,
	53.840003967285156,
	56.20000457763672,
	57.95000457763672,
	59.29000473022461,
	59.77000427246094,
	59.920005798339844,
	61.190006256103516,
	61.96000671386719,
	62.50000762939453,
	63.3700065612793,
	63.48000717163086,
	63.48000717163086,
	63.66000747680664,
	63.850006103515625,
	64.08000946044922,
	64.760009765625,
	64.80001068115234,
	64.81001281738281,
	64.81001281738281
	],
	"short_factor": [
	1.05,
	1.05,
	1.05,
	1.1,
	1.1,
	1.1500000000000001,
	1.2000000000000002,
	1.2500000000000002,
	1.3000000000000003,
	1.3500000000000003,
	1.5000000000000004,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.000000000000001,
	2.0500000000000007,
	2.0500000000000007,
	2.0500000000000007,
	2.1000000000000005,
	2.1000000000000005,
	2.1000000000000005,
	2.1500000000000004,
	2.1500000000000004,
	2.3499999999999996,
	2.549999999999999,
	2.5999999999999988,
	2.5999999999999988,
	2.7499999999999982,
	2.849999999999998,
	2.849999999999998,
	2.9499999999999975
	],
	"type": "su"
	},
	"rope_theta": 10000.0,
	"sliding_window": 262144,
	"tie_word_embeddings": false,
	"torch_dtype": "float16",
	"transformers_version": "4.40.2",
	"use_cache": false,
	"vocab_size": 32064
	}