Instructions to use charioteer/Neural-phi2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use charioteer/Neural-phi2 with Transformers:

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

pipe = pipeline("text-generation", model="charioteer/Neural-phi2", 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("charioteer/Neural-phi2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("charioteer/Neural-phi2", 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 charioteer/Neural-phi2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "charioteer/Neural-phi2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "charioteer/Neural-phi2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/charioteer/Neural-phi2

SGLang

How to use charioteer/Neural-phi2 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 "charioteer/Neural-phi2" \
    --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": "charioteer/Neural-phi2",
		"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 "charioteer/Neural-phi2" \
        --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": "charioteer/Neural-phi2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use charioteer/Neural-phi2 with Docker Model Runner:
```
docker model run hf.co/charioteer/Neural-phi2
```

charioteer commited on Apr 8, 2024

Commit

a17616e

verified ·

1 Parent(s): 9de5aac

Update README.md

Browse files

Add the training parameters section.

Files changed (1) hide show

README.md +36 -0

README.md CHANGED Viewed

@@ -24,6 +24,42 @@ pipeline_tag: text-generation
   - Initializing the DPO Trainer and training the model
   - Saving the finetuned model and tokenizer
 ## Intended Use
 The Neural-phi2 model is intended to be used as a general-purpose language model for a variety of natural language processing tasks, such as text generation, summarization, and question answering. It may be particularly useful in applications where the model needs to generate coherent and contextually appropriate responses, such as in chatbots or virtual assistants.

   - Initializing the DPO Trainer and training the model
   - Saving the finetuned model and tokenizer
+## Training Parameters
+This section outlines the key training parameters used to finetune the Phi2 model from Microsoft using the Direct Preference Optimization (DPO) technique on the `distilabel-intel-orca-dpo-pairs` dataset, resulting in the Neural-phi2 model.
+- **SFT Model Name**: `phi2-sft-alpaca_loraemb-right-pad`
+- **New Model Name**: `Neural-phi2-v2`
+- **Dataset**: `argilla/distilabel-intel-orca-dpo-pairs`
+- **Tokenizer**: Custom tokenizer created from the `phi2-sft-alpaca_loraemb-right-pad` model
+- **Quantization Config**:
+  - `load_in_4bit=True`
+  - `bnb_4bit_quant_type="nf4"`
+  - `bnb_4bit_compute_dtype=torch.float16`
+- **LoRA Config**:
+  - `r=16`
+  - `lora_alpha=64`
+  - `lora_dropout=0.05`
+  - `bias="none"`
+  - `task_type="CAUSAL_LM"`
+  - `target_modules=["q_proj", "k_proj", "v_proj", "dense", "fc1", "fc2"]`
+- **Training Arguments**:
+  - `per_device_train_batch_size=1`
+  - `gradient_accumulation_steps=8`
+  - `gradient_checkpointing=True`
+  - `learning_rate=5e-7`
+  - `lr_scheduler_type="linear"`
+  - `max_steps=500`
+  - `optim="paged_adamw_32bit"`
+  - `warmup_steps=100`
+  - `bf16=True`
+  - `report_to="wandb"`
+- **DPO Trainer**:
+  - `loss_type="sigmoid"`
+  - `beta=0.1`
+  - `max_prompt_length=768`
+  - `max_length=1024`
 ## Intended Use
 The Neural-phi2 model is intended to be used as a general-purpose language model for a variety of natural language processing tasks, such as text generation, summarization, and question answering. It may be particularly useful in applications where the model needs to generate coherent and contextually appropriate responses, such as in chatbots or virtual assistants.