Instructions to use aloobun/open-llama-3b-v2-elmv3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use aloobun/open-llama-3b-v2-elmv3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="aloobun/open-llama-3b-v2-elmv3")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("aloobun/open-llama-3b-v2-elmv3") model = AutoModelForCausalLM.from_pretrained("aloobun/open-llama-3b-v2-elmv3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use aloobun/open-llama-3b-v2-elmv3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "aloobun/open-llama-3b-v2-elmv3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "aloobun/open-llama-3b-v2-elmv3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/aloobun/open-llama-3b-v2-elmv3
- SGLang
How to use aloobun/open-llama-3b-v2-elmv3 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 "aloobun/open-llama-3b-v2-elmv3" \ --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": "aloobun/open-llama-3b-v2-elmv3", "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 "aloobun/open-llama-3b-v2-elmv3" \ --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": "aloobun/open-llama-3b-v2-elmv3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use aloobun/open-llama-3b-v2-elmv3 with Docker Model Runner:
docker model run hf.co/aloobun/open-llama-3b-v2-elmv3
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,18 +15,4 @@ Eval Results :
|
|
| 15 |
|
| 16 |

|
| 17 |
|
| 18 |
-
I like to tweak smaller models than 3B and mix loras, but now I'm trying my hand at finetuning a 3B model. Lets see how it goes.
|
| 19 |
-
|
| 20 |
-
LFG
|
| 21 |
-
LFG
|
| 22 |
-
LFG
|
| 23 |
-
LFG
|
| 24 |
-
LFG
|
| 25 |
-
LFG
|
| 26 |
-
|
| 27 |
-
LFG
|
| 28 |
-
LFG
|
| 29 |
-
LFG
|
| 30 |
-
LFG
|
| 31 |
-
LFG
|
| 32 |
-
LFG
|
|
|
|
| 15 |
|
| 16 |

|
| 17 |
|
| 18 |
+
I like to tweak smaller models than 3B and mix loras, but now I'm trying my hand at finetuning a 3B model. Lets see how it goes.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|