Instructions to use llmware/bling-phi-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmware/bling-phi-3 with Transformers:

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

pipe = pipeline("text-generation", model="llmware/bling-phi-3", trust_remote_code=True)
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("llmware/bling-phi-3", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("llmware/bling-phi-3", trust_remote_code=True, 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 llmware/bling-phi-3 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/llmware/bling-phi-3

SGLang

How to use llmware/bling-phi-3 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 "llmware/bling-phi-3" \
    --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": "llmware/bling-phi-3",
		"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 "llmware/bling-phi-3" \
        --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": "llmware/bling-phi-3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use llmware/bling-phi-3 with Docker Model Runner:
```
docker model run hf.co/llmware/bling-phi-3
```

doberst commited on May 2, 2024

Commit

c80968e

verified ·

1 Parent(s): 11c462d

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -4

README.md CHANGED Viewed

@@ -23,7 +23,9 @@ Evaluated against the benchmark test:   [RAG-Instruct-Benchmark-Tester](https://
 --Summarization Quality (1-5):  4 (Above Average)
 --Hallucinations:  No hallucinations observed in test runs.
-For test run results (and good indicator of target use cases), please see the files ("core_rag_test" and "answer_sheet" in this repo).
 ### Model Description
@@ -99,15 +101,15 @@ If you are using a HuggingFace generation script:
     inputs = tokenizer(new_prompt, return_tensors="pt")
     start_of_output = len(inputs.input_ids[0])
-    #   temperature: set at 0.3 for consistency of output
     #   max_new_tokens:  set at 100 - may prematurely stop a few of the summaries
     outputs = model.generate(
             inputs.input_ids.to(device),
             eos_token_id=tokenizer.eos_token_id,
             pad_token_id=tokenizer.eos_token_id,
-            do_sample=True,
-            temperature=0.3,
             max_new_tokens=100,
             )

 --Summarization Quality (1-5):  4 (Above Average)
 --Hallucinations:  No hallucinations observed in test runs.
+For test run results (and good indicator of target use cases), please see the files ("core_rag_test" and "answer_sheet" in this repo).
+Note: the Pytorch version answered 1 question with "Not Found" while the quantized version answered it correctly, hence the small difference in scores.
 ### Model Description
     inputs = tokenizer(new_prompt, return_tensors="pt")
     start_of_output = len(inputs.input_ids[0])
+    #   temperature: set at 0.0 with do_sample=False for consistency of output
     #   max_new_tokens:  set at 100 - may prematurely stop a few of the summaries
     outputs = model.generate(
             inputs.input_ids.to(device),
             eos_token_id=tokenizer.eos_token_id,
             pad_token_id=tokenizer.eos_token_id,
+            do_sample=False,
+            temperature=0.0,
             max_new_tokens=100,
             )