Instructions to use trl-internal-testing/tiny-Phi3ForCausalLM-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trl-internal-testing/tiny-Phi3ForCausalLM-3 with Transformers:

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

pipe = pipeline("text-generation", model="trl-internal-testing/tiny-Phi3ForCausalLM-3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("trl-internal-testing/tiny-Phi3ForCausalLM-3")
model = AutoModelForCausalLM.from_pretrained("trl-internal-testing/tiny-Phi3ForCausalLM-3")
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 trl-internal-testing/tiny-Phi3ForCausalLM-3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trl-internal-testing/tiny-Phi3ForCausalLM-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": "trl-internal-testing/tiny-Phi3ForCausalLM-3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/trl-internal-testing/tiny-Phi3ForCausalLM-3

SGLang

How to use trl-internal-testing/tiny-Phi3ForCausalLM-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 "trl-internal-testing/tiny-Phi3ForCausalLM-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": "trl-internal-testing/tiny-Phi3ForCausalLM-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 "trl-internal-testing/tiny-Phi3ForCausalLM-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": "trl-internal-testing/tiny-Phi3ForCausalLM-3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use trl-internal-testing/tiny-Phi3ForCausalLM-3 with Docker Model Runner:
```
docker model run hf.co/trl-internal-testing/tiny-Phi3ForCausalLM-3
```

qgallouedec HF Staff commited on Apr 14

Commit

87a7e57

verified ·

1 Parent(s): a568b7d

Upload Phi3ForCausalLM

Browse files

Files changed (3) hide show

config.json +4 -6
generation_config.json +2 -6
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -18,16 +18,14 @@
   "num_key_value_heads": 2,
   "original_max_position_embeddings": 4096,
   "pad_token_id": 32000,
   "resid_pdrop": 0.0,
   "rms_norm_eps": 1e-05,
-  "rope_parameters": {
-    "partial_rotary_factor": 1.0,
-    "rope_theta": 10000.0,
-    "rope_type": "default"
-  },
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "transformers_version": "5.6.0.dev0",
   "use_cache": true,
   "vocab_size": 32011
 }

   "num_key_value_heads": 2,
   "original_max_position_embeddings": 4096,
   "pad_token_id": 32000,
+  "partial_rotary_factor": 1.0,
   "resid_pdrop": 0.0,
   "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
   "use_cache": true,
   "vocab_size": 32011
 }

generation_config.json CHANGED Viewed

@@ -1,11 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": [
-    32000,
-    32001,
-    32007
-  ],
   "pad_token_id": 32000,
-  "transformers_version": "5.6.0.dev0"
 }

 {
   "_from_model_config": true,
   "bos_token_id": 1,
+  "eos_token_id": 32000,
   "pad_token_id": 32000,
+  "transformers_version": "4.57.6"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36e4fecbdc4e0761417e7e340ed77224844933a82349b292a84b07e6f00f7363
 size 1029840

 version https://git-lfs.github.com/spec/v1
+oid sha256:92db07521db27e0bd20add8911ff59e16c4cbad65c816afa2ecd81a33ed02f00
 size 1029840