Instructions to use Giang07/phi3-mini-4k-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Giang07/phi3-mini-4k-qlora with Transformers:

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

pipe = pipeline("text-generation", model="Giang07/phi3-mini-4k-qlora", 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("Giang07/phi3-mini-4k-qlora", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Giang07/phi3-mini-4k-qlora", 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 Settings

vLLM

How to use Giang07/phi3-mini-4k-qlora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Giang07/phi3-mini-4k-qlora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Giang07/phi3-mini-4k-qlora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Giang07/phi3-mini-4k-qlora

SGLang

How to use Giang07/phi3-mini-4k-qlora 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 "Giang07/phi3-mini-4k-qlora" \
    --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": "Giang07/phi3-mini-4k-qlora",
		"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 "Giang07/phi3-mini-4k-qlora" \
        --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": "Giang07/phi3-mini-4k-qlora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Giang07/phi3-mini-4k-qlora with Docker Model Runner:
```
docker model run hf.co/Giang07/phi3-mini-4k-qlora
```

Giang07 commited on Jul 5, 2024

Commit

b09f886

verified ·

1 Parent(s): 59b6855

Upload Phi3ForCausalLM

Browse files

Files changed (5) hide show

README.md +1 -1
config.json +2 -1
generation_config.json +1 -1
model-00001-of-00002.safetensors +1 -1
model-00002-of-00002.safetensors +1 -1

README.md CHANGED Viewed

@@ -2,9 +2,9 @@
 language:
 - en
 license: mit
 tags:
 - text-generation-inference
 - trl
 - sft
-pipeline_tag: text-generation
 ---

 language:
 - en
 license: mit
+pipeline_tag: text-generation
 tags:
 - text-generation-inference
 - trl
 - sft
 ---

config.json CHANGED Viewed

@@ -3,6 +3,7 @@
   "architectures": [
     "Phi3ForCausalLM"
   ],
   "attention_dropout": 0.0,
   "auto_map": {
     "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
@@ -29,7 +30,7 @@
   "sliding_window": 2047,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.41.1",
   "use_cache": true,
   "vocab_size": 32064
 }

   "architectures": [
     "Phi3ForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
   "auto_map": {
     "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
   "sliding_window": 2047,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
   "use_cache": true,
   "vocab_size": 32064
 }

generation_config.json CHANGED Viewed

@@ -7,5 +7,5 @@
     32007
   ],
   "pad_token_id": 32000,
-  "transformers_version": "4.41.1"
 }

     32007
   ],
   "pad_token_id": 32000,
+  "transformers_version": "4.41.2"
 }

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:947f4d97f71eb6e55f5c7acd60467c8711df0b48db2d2c688f52637b1c1892e1
 size 4972489200

 version https://git-lfs.github.com/spec/v1
+oid sha256:89bd6ab32adfd6a6696229c1c5f955ff0df6753e39ae498d1557fc68c6bfb8f8
 size 4972489200

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d93ddaeaa861799800dceed75cbff426d63647938d0d877277ca1d60da52a36a
 size 2669692488

 version https://git-lfs.github.com/spec/v1
+oid sha256:409550382fb434cc224d90a33aa628ba6ebe60648ff09bfb55b9c560c36f033d
 size 2669692488