Instructions to use POWERHACK/TheoVersion2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use POWERHACK/TheoVersion2 with Transformers:

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

pipe = pipeline("text-generation", model="POWERHACK/TheoVersion2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("POWERHACK/TheoVersion2")
model = AutoModelForCausalLM.from_pretrained("POWERHACK/TheoVersion2")
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]:]))

PEFT
How to use POWERHACK/TheoVersion2 with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use POWERHACK/TheoVersion2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "POWERHACK/TheoVersion2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "POWERHACK/TheoVersion2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/POWERHACK/TheoVersion2

SGLang

How to use POWERHACK/TheoVersion2 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 "POWERHACK/TheoVersion2" \
    --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": "POWERHACK/TheoVersion2",
		"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 "POWERHACK/TheoVersion2" \
        --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": "POWERHACK/TheoVersion2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use POWERHACK/TheoVersion2 with Docker Model Runner:
```
docker model run hf.co/POWERHACK/TheoVersion2
```

POWERHACK commited on Sep 23, 2024

Commit

78fb7f4

verified ·

1 Parent(s): d4eea02

Update config.json

Browse files

Files changed (1) hide show

config.json +21 -5

config.json CHANGED Viewed

@@ -1,4 +1,5 @@
 {
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -15,14 +16,29 @@
   "num_attention_heads": 16,
   "num_hidden_layers": 36,
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_theta": 1000000.0,
-  "sliding_window": 32768,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.1",
-  "use_cache": true,
   "use_mrope": false,
   "use_sliding_window": false,
-  "vocab_size": 151936
-}

 {
+  "_name_or_path": "Qwen/Qwen2.5-3B",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "num_attention_heads": 16,
   "num_hidden_layers": 36,
   "num_key_value_heads": 2,
+  "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"
+  },
   "rms_norm_eps": 1e-06,
   "rope_theta": 1000000.0,
+  "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
   "use_mrope": false,
   "use_sliding_window": false,
+  "vocab_size": 151665
+}