Instructions to use apps90/OrpoGPT2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use apps90/OrpoGPT2 with Transformers:

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

pipe = pipeline("text-generation", model="apps90/OrpoGPT2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("apps90/OrpoGPT2")
model = AutoModelForCausalLM.from_pretrained("apps90/OrpoGPT2")
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 apps90/OrpoGPT2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "apps90/OrpoGPT2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "apps90/OrpoGPT2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/apps90/OrpoGPT2

SGLang

How to use apps90/OrpoGPT2 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 "apps90/OrpoGPT2" \
    --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": "apps90/OrpoGPT2",
		"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 "apps90/OrpoGPT2" \
        --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": "apps90/OrpoGPT2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use apps90/OrpoGPT2 with Docker Model Runner:
```
docker model run hf.co/apps90/OrpoGPT2
```

apps90 commited on May 20, 2024

Commit

28da64f

verified ·

1 Parent(s): 5c35123

Upload model

Browse files

Files changed (4) hide show

README.md +3 -1
config.json +12 -11
generation_config.json +3 -2
model.safetensors +2 -2

README.md CHANGED Viewed

@@ -1,6 +1,8 @@
 ---
 library_name: transformers
-tags: []
 ---
 # Model Card for Model ID

 ---
 library_name: transformers
+tags:
+- trl
+- orpo
 ---
 # Model Card for Model ID

config.json CHANGED Viewed

@@ -5,9 +5,9 @@
     "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
   "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
@@ -17,19 +17,20 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
   "quantization_config": {
-    "_load_in_4bit": false,
-    "_load_in_8bit": true,
-    "bnb_4bit_compute_dtype": "float32",
     "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "fp4",
-    "bnb_4bit_use_double_quant": false,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,
     "llm_int8_threshold": 6.0,
-    "load_in_4bit": false,
-    "load_in_8bit": true,
     "quant_method": "bitsandbytes"
   },
   "reorder_and_upcast_attn": false,
@@ -47,8 +48,8 @@
       "max_length": 50
     }
   },
-  "torch_dtype": "float16",
   "transformers_version": "4.41.0",
   "use_cache": true,
-  "vocab_size": 50257
 }

     "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
+  "bos_token_id": 50257,
   "embd_pdrop": 0.1,
+  "eos_token_id": 50258,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
+  "pad_token_id": 50258,
   "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float16",
     "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,
     "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
     "quant_method": "bitsandbytes"
   },
   "reorder_and_upcast_attn": false,
       "max_length": 50
     }
   },
+  "torch_dtype": "float32",
   "transformers_version": "4.41.0",
   "use_cache": true,
+  "vocab_size": 50259
 }

generation_config.json CHANGED Viewed

@@ -1,6 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
   "transformers_version": "4.41.0"
 }

 {
   "_from_model_config": true,
+  "bos_token_id": 50257,
+  "eos_token_id": 50258,
+  "pad_token_id": 50258,
   "transformers_version": "4.41.0"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:169b433e4d424c0dcf2b3c5905e79b1a54791212ab36c95cb5a891b3c344136c
-size 166663760

 version https://git-lfs.github.com/spec/v1
+oid sha256:ad32865291e3569bed247f4a26c7126789296ff4b14bc47e4209e1cd22cb54e4
+size 204307666