Instructions to use trl-internal-testing/tiny-Phi3ForCausalLM-3.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trl-internal-testing/tiny-Phi3ForCausalLM-3.5 with Transformers:

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

pipe = pipeline("text-generation", model="trl-internal-testing/tiny-Phi3ForCausalLM-3.5")
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("trl-internal-testing/tiny-Phi3ForCausalLM-3.5")
model = AutoModelForCausalLM.from_pretrained("trl-internal-testing/tiny-Phi3ForCausalLM-3.5", 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 trl-internal-testing/tiny-Phi3ForCausalLM-3.5 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-3.5"
# 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-3.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/trl-internal-testing/tiny-Phi3ForCausalLM-3.5

SGLang

How to use trl-internal-testing/tiny-Phi3ForCausalLM-3.5 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-3.5" \
    --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-3.5",
		"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-3.5" \
        --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-3.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use trl-internal-testing/tiny-Phi3ForCausalLM-3.5 with Docker Model Runner:
```
docker model run hf.co/trl-internal-testing/tiny-Phi3ForCausalLM-3.5
```

Upload Phi3ForCausalLM

by albertvillanova HF Staff - opened 23 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+16

-8

Files changed (3) hide show

config.json +13 -5
generation_config.json +1 -1
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -11,7 +11,7 @@
   "hidden_size": 8,
   "initializer_range": 0.02,
   "intermediate_size": 32,
-  "max_position_embeddings": 4096,
   "model_type": "phi3",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
@@ -21,11 +21,19 @@
   "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
 }

   "hidden_size": 8,
   "initializer_range": 0.02,
   "intermediate_size": 32,
+  "max_position_embeddings": 131072,
   "model_type": "phi3",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
   "partial_rotary_factor": 1.0,
   "resid_pdrop": 0.0,
   "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1.0800000429153442
+    ],
+    "short_factor": [
+      1.0
+    ],
+    "type": "longrope"
+  },
   "rope_theta": 10000.0,
+  "sliding_window": 262144,
   "tie_word_embeddings": false,
+  "transformers_version": "4.56.2",
   "use_cache": true,
+  "vocab_size": 32064
 }

generation_config.json CHANGED Viewed

@@ -7,5 +7,5 @@
     32000
   ],
   "pad_token_id": 32000,
-  "transformers_version": "4.57.6"
 }

     32000
   ],
   "pad_token_id": 32000,
+  "transformers_version": "4.56.2"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc5a4cde7361dd8625f2254ae28b629afa8eaf0fb32bf2a4a67cf6f8e3451032
-size 1029840

 version https://git-lfs.github.com/spec/v1
+oid sha256:841d5326bb8c53c1a86222fa68965c59fd6338ee24bff636d5ee087dd0f97fd5
+size 1031536