Instructions to use Qwen/Qwen-14B-Chat-Int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/Qwen-14B-Chat-Int4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Qwen/Qwen-14B-Chat-Int4", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-14B-Chat-Int4", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Qwen/Qwen-14B-Chat-Int4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Qwen/Qwen-14B-Chat-Int4" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Qwen/Qwen-14B-Chat-Int4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Qwen/Qwen-14B-Chat-Int4
- SGLang
How to use Qwen/Qwen-14B-Chat-Int4 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 "Qwen/Qwen-14B-Chat-Int4" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Qwen/Qwen-14B-Chat-Int4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "Qwen/Qwen-14B-Chat-Int4" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Qwen/Qwen-14B-Chat-Int4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Qwen/Qwen-14B-Chat-Int4 with Docker Model Runner:
docker model run hf.co/Qwen/Qwen-14B-Chat-Int4
format
Browse files- config.json +1 -1
- generation_config.json +9 -9
- tokenizer_config.json +8 -9
config.json
CHANGED
|
@@ -46,4 +46,4 @@
|
|
| 46 |
"use_flash_attn": "auto",
|
| 47 |
"use_logn_attn": true,
|
| 48 |
"vocab_size": 152064
|
| 49 |
-
}
|
|
|
|
| 46 |
"use_flash_attn": "auto",
|
| 47 |
"use_logn_attn": true,
|
| 48 |
"vocab_size": 152064
|
| 49 |
+
}
|
generation_config.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"chat_format": "chatml",
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"pad_token_id": 151643,
|
| 5 |
+
"max_window_size": 6144,
|
| 6 |
+
"max_new_tokens": 512,
|
| 7 |
+
"do_sample": true,
|
| 8 |
+
"top_k": 0,
|
| 9 |
+
"top_p": 0.5,
|
| 10 |
+
"transformers_version": "4.31.0"
|
| 11 |
}
|
tokenizer_config.json
CHANGED
|
@@ -1,11 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
}
|
| 10 |
}
|
| 11 |
-
|
|
|
|
| 1 |
{
|
| 2 |
+
"model_max_length": 8192,
|
| 3 |
+
"tokenizer_class": "QWenTokenizer",
|
| 4 |
+
"auto_map": {
|
| 5 |
+
"AutoTokenizer": [
|
| 6 |
+
"tokenization_qwen.QWenTokenizer",
|
| 7 |
+
null
|
| 8 |
+
]
|
|
|
|
| 9 |
}
|
| 10 |
+
}
|