Instructions to use Praful932/dolphin-2.2.1-mistral-7b-samsum-ft-v1-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Praful932/dolphin-2.2.1-mistral-7b-samsum-ft-v1-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="Praful932/dolphin-2.2.1-mistral-7b-samsum-ft-v1-GPTQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Praful932/dolphin-2.2.1-mistral-7b-samsum-ft-v1-GPTQ")
model = AutoModelForCausalLM.from_pretrained("Praful932/dolphin-2.2.1-mistral-7b-samsum-ft-v1-GPTQ")
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 Praful932/dolphin-2.2.1-mistral-7b-samsum-ft-v1-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Praful932/dolphin-2.2.1-mistral-7b-samsum-ft-v1-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Praful932/dolphin-2.2.1-mistral-7b-samsum-ft-v1-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Praful932/dolphin-2.2.1-mistral-7b-samsum-ft-v1-GPTQ

SGLang

How to use Praful932/dolphin-2.2.1-mistral-7b-samsum-ft-v1-GPTQ 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 "Praful932/dolphin-2.2.1-mistral-7b-samsum-ft-v1-GPTQ" \
    --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": "Praful932/dolphin-2.2.1-mistral-7b-samsum-ft-v1-GPTQ",
		"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 "Praful932/dolphin-2.2.1-mistral-7b-samsum-ft-v1-GPTQ" \
        --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": "Praful932/dolphin-2.2.1-mistral-7b-samsum-ft-v1-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Praful932/dolphin-2.2.1-mistral-7b-samsum-ft-v1-GPTQ with Docker Model Runner:
```
docker model run hf.co/Praful932/dolphin-2.2.1-mistral-7b-samsum-ft-v1-GPTQ
```

Praful932 commited on Jan 21, 2024

Commit

821ec26

verified ·

1 Parent(s): beb7245

update config.json for transformers GPTQ support

Browse files

Files changed (1) hide show

config.json +12 -1

config.json CHANGED Viewed

@@ -22,5 +22,16 @@
   "torch_dtype": "float16",
   "transformers_version": "4.36.2",
   "use_cache": false,
-  "vocab_size": 32002
 }

   "torch_dtype": "float16",
   "transformers_version": "4.36.2",
   "use_cache": false,
+  "vocab_size": 32002,
+  "quantization_config" : {
+    "bits": 4,
+    "group_size": 128,
+    "damp_percent": 0.1,
+    "desc_act": true,
+    "static_groups": false,
+    "sym": true,
+    "true_sequential": true,
+    "model_name_or_path": "/kaggle/working/v0_quantized_model_desc_act/",
+    "model_file_base_name": "model"
+  }
 }