Instructions to use lu-vae/llama-8b-fft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lu-vae/llama-8b-fft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lu-vae/llama-8b-fft")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lu-vae/llama-8b-fft") model = AutoModelForCausalLM.from_pretrained("lu-vae/llama-8b-fft", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use lu-vae/llama-8b-fft with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lu-vae/llama-8b-fft" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lu-vae/llama-8b-fft", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/lu-vae/llama-8b-fft
- SGLang
How to use lu-vae/llama-8b-fft 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 "lu-vae/llama-8b-fft" \ --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": "lu-vae/llama-8b-fft", "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 "lu-vae/llama-8b-fft" \ --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": "lu-vae/llama-8b-fft", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use lu-vae/llama-8b-fft with Docker Model Runner:
docker model run hf.co/lu-vae/llama-8b-fft
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -74,7 +74,7 @@ eval_table_size:
|
|
| 74 |
saves_per_epoch: 4
|
| 75 |
save_total_limit: 8
|
| 76 |
debug:
|
| 77 |
-
deepspeed:
|
| 78 |
weight_decay: 0.0
|
| 79 |
fsdp:
|
| 80 |
fsdp_config:
|
|
@@ -90,7 +90,7 @@ tokens:
|
|
| 90 |
|
| 91 |
</details><br>
|
| 92 |
|
| 93 |
-
#
|
| 94 |
|
| 95 |
This model was trained from scratch on the None dataset.
|
| 96 |
|
|
|
|
| 74 |
saves_per_epoch: 4
|
| 75 |
save_total_limit: 8
|
| 76 |
debug:
|
| 77 |
+
deepspeed: deepspeed/zero2.json
|
| 78 |
weight_decay: 0.0
|
| 79 |
fsdp:
|
| 80 |
fsdp_config:
|
|
|
|
| 90 |
|
| 91 |
</details><br>
|
| 92 |
|
| 93 |
+
# llama-8B-fft
|
| 94 |
|
| 95 |
This model was trained from scratch on the None dataset.
|
| 96 |
|