Instructions to use yunconglong/7Bx4_DPO_2e with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yunconglong/7Bx4_DPO_2e with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="yunconglong/7Bx4_DPO_2e")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("yunconglong/7Bx4_DPO_2e") model = AutoModelForCausalLM.from_pretrained("yunconglong/7Bx4_DPO_2e") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use yunconglong/7Bx4_DPO_2e with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "yunconglong/7Bx4_DPO_2e" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "yunconglong/7Bx4_DPO_2e", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/yunconglong/7Bx4_DPO_2e
- SGLang
How to use yunconglong/7Bx4_DPO_2e 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 "yunconglong/7Bx4_DPO_2e" \ --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": "yunconglong/7Bx4_DPO_2e", "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 "yunconglong/7Bx4_DPO_2e" \ --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": "yunconglong/7Bx4_DPO_2e", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use yunconglong/7Bx4_DPO_2e with Docker Model Runner:
docker model run hf.co/yunconglong/7Bx4_DPO_2e
Update config.json
Browse files- config.json +2 -2
config.json
CHANGED
|
@@ -13,10 +13,10 @@
|
|
| 13 |
"max_position_embeddings": 32768,
|
| 14 |
"model_type": "mixtral",
|
| 15 |
"num_attention_heads": 32,
|
| 16 |
-
"num_experts_per_tok":
|
| 17 |
"num_hidden_layers": 32,
|
| 18 |
"num_key_value_heads": 8,
|
| 19 |
-
"num_local_experts":
|
| 20 |
"output_router_logits": false,
|
| 21 |
"rms_norm_eps": 1e-05,
|
| 22 |
"rope_theta": 10000.0,
|
|
|
|
| 13 |
"max_position_embeddings": 32768,
|
| 14 |
"model_type": "mixtral",
|
| 15 |
"num_attention_heads": 32,
|
| 16 |
+
"num_experts_per_tok": 2,
|
| 17 |
"num_hidden_layers": 32,
|
| 18 |
"num_key_value_heads": 8,
|
| 19 |
+
"num_local_experts": 4,
|
| 20 |
"output_router_logits": false,
|
| 21 |
"rms_norm_eps": 1e-05,
|
| 22 |
"rope_theta": 10000.0,
|