Text Generation
Transformers
Safetensors
English
qwen2
qwen
qwen2.5
finetune
dpo
orpo
chat
conversational
instruct
storywriting
roleplay
novelwriting
Eval Results (legacy)
text-generation-inference
Instructions to use v000000/Qwen2.5-Lumen-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use v000000/Qwen2.5-Lumen-14B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="v000000/Qwen2.5-Lumen-14B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("v000000/Qwen2.5-Lumen-14B") model = AutoModelForCausalLM.from_pretrained("v000000/Qwen2.5-Lumen-14B", device_map="auto") 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]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use v000000/Qwen2.5-Lumen-14B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "v000000/Qwen2.5-Lumen-14B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "v000000/Qwen2.5-Lumen-14B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/v000000/Qwen2.5-Lumen-14B
- SGLang
How to use v000000/Qwen2.5-Lumen-14B 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 "v000000/Qwen2.5-Lumen-14B" \ --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": "v000000/Qwen2.5-Lumen-14B", "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 "v000000/Qwen2.5-Lumen-14B" \ --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": "v000000/Qwen2.5-Lumen-14B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use v000000/Qwen2.5-Lumen-14B with Docker Model Runner:
docker model run hf.co/v000000/Qwen2.5-Lumen-14B
Update README.md
Browse files
README.md
CHANGED
|
@@ -27,7 +27,7 @@ pipeline_tag: text-generation
|
|
| 27 |
|
| 28 |
# Qwen2.5-Lumen-14B
|
| 29 |
|
| 30 |
-
* *Direct preference optimization finetuned for 3 epoch
|
| 31 |
|
| 32 |

|
| 33 |
|
|
@@ -41,6 +41,8 @@ Trained [Qwen2.5-14B-Instruct] for 2 epochs on [jondurbin/gutenberg-dpo-v0.1] sa
|
|
| 41 |
|
| 42 |
[Tanliboy](https://huggingface.co/tanliboy) trained [Qwen2.5-14B-Instruct] for 1 epoch on [HuggingFaceH4/ultrafeedback_binarized].
|
| 43 |
|
|
|
|
|
|
|
| 44 |
## Merge
|
| 45 |
|
| 46 |
* Merged with a sophosympatheia <b>SLERP</b> *Ultrafeedback-Binarized DPO* and *Gutenberg DPO*
|
|
|
|
| 27 |
|
| 28 |
# Qwen2.5-Lumen-14B
|
| 29 |
|
| 30 |
+
* *Direct preference optimization finetuned for 3 epoch*
|
| 31 |
|
| 32 |

|
| 33 |
|
|
|
|
| 41 |
|
| 42 |
[Tanliboy](https://huggingface.co/tanliboy) trained [Qwen2.5-14B-Instruct] for 1 epoch on [HuggingFaceH4/ultrafeedback_binarized].
|
| 43 |
|
| 44 |
+
*Mass checkpoint merged, Based on Qwen2.5-14B-Instruct.*
|
| 45 |
+
|
| 46 |
## Merge
|
| 47 |
|
| 48 |
* Merged with a sophosympatheia <b>SLERP</b> *Ultrafeedback-Binarized DPO* and *Gutenberg DPO*
|