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

Libraries

How to use Frinkles/QuantizedModel with Transformers:

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

pipe = pipeline("text-generation", model="Frinkles/QuantizedModel", 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("Frinkles/QuantizedModel", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Frinkles/QuantizedModel", 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

vLLM

How to use Frinkles/QuantizedModel with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Frinkles/QuantizedModel

SGLang

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

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

Frinkles commited on Jun 13, 2024

Commit

7322d1c

verified ·

1 Parent(s): 72708ae

Upload Phi3ForCausalLM

Browse files

Files changed (2) hide show

config.json +9 -13
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -24,19 +24,15 @@
   "original_max_position_embeddings": 4096,
   "pad_token_id": 32000,
   "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "bfloat16",
-    "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"
   },
   "resid_pdrop": 0.0,
   "rms_norm_eps": 1e-05,

   "original_max_position_embeddings": 4096,
   "pad_token_id": 32000,
   "quantization_config": {
+    "bits": 4,
+    "damp_percent": 0.1,
+    "dataset": "wikitext2",
+    "desc_act": false,
+    "group_size": 128,
+    "modules_in_block_to_quantize": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "true_sequential": true
   },
   "resid_pdrop": 0.0,
   "rms_norm_eps": 1e-05,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0afd3681888f095180a4010a0889d2f6ed55fb35fb91c7e4d877c2d038ef1320
-size 2264109944

 version https://git-lfs.github.com/spec/v1
+oid sha256:8cc2aa9e1daa06456ef8061063e9bade3fd2103ffb3eadcc5370c9a2888dda7b
+size 2279413824