Instructions to use OEvortex/EMO-phi-128k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OEvortex/EMO-phi-128k with Transformers:

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

pipe = pipeline("text-generation", model="OEvortex/EMO-phi-128k", 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("OEvortex/EMO-phi-128k", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("OEvortex/EMO-phi-128k", 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 OEvortex/EMO-phi-128k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OEvortex/EMO-phi-128k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OEvortex/EMO-phi-128k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OEvortex/EMO-phi-128k

SGLang

How to use OEvortex/EMO-phi-128k 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 "OEvortex/EMO-phi-128k" \
    --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": "OEvortex/EMO-phi-128k",
		"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 "OEvortex/EMO-phi-128k" \
        --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": "OEvortex/EMO-phi-128k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OEvortex/EMO-phi-128k with Docker Model Runner:
```
docker model run hf.co/OEvortex/EMO-phi-128k
```

Abhaykoul commited on Apr 24, 2024

Commit

4a472c2

verified ·

1 Parent(s): bf69865

Update tokenizer_config.json

Browse files

Files changed (1) hide show

tokenizer_config.json +6 -7

tokenizer_config.json CHANGED Viewed

@@ -348,19 +348,18 @@
     }
   },
   "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
   ],
-  "bos_token": "<|im_start|>",
-  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
   "legacy": false,
   "model_max_length": 131072,
-  "pad_token": "<|im_end|>",
   "padding_side": "left",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
-}

     }
   },
   "additional_special_tokens": [
+    "<|/inst|>"
   ],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
   "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
   "legacy": false,
   "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
   "padding_side": "left",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
+}