Instructions to use lebe1/opt-125m-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lebe1/opt-125m-2bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lebe1/opt-125m-2bit")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lebe1/opt-125m-2bit") model = AutoModelForCausalLM.from_pretrained("lebe1/opt-125m-2bit") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use lebe1/opt-125m-2bit with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lebe1/opt-125m-2bit" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lebe1/opt-125m-2bit", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/lebe1/opt-125m-2bit
- SGLang
How to use lebe1/opt-125m-2bit 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 "lebe1/opt-125m-2bit" \ --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": "lebe1/opt-125m-2bit", "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 "lebe1/opt-125m-2bit" \ --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": "lebe1/opt-125m-2bit", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use lebe1/opt-125m-2bit with Docker Model Runner:
docker model run hf.co/lebe1/opt-125m-2bit
AutoGPTQ model for facebook/opt-125m: 2 bits
Browse files- config.json +1 -1
- generation_config.json +1 -1
config.json
CHANGED
|
@@ -51,7 +51,7 @@
|
|
| 51 |
"use_cuda_fp16": true
|
| 52 |
},
|
| 53 |
"torch_dtype": "float16",
|
| 54 |
-
"transformers_version": "4.
|
| 55 |
"use_cache": true,
|
| 56 |
"vocab_size": 50272,
|
| 57 |
"word_embed_proj_dim": 768
|
|
|
|
| 51 |
"use_cuda_fp16": true
|
| 52 |
},
|
| 53 |
"torch_dtype": "float16",
|
| 54 |
+
"transformers_version": "4.36.0.dev0",
|
| 55 |
"use_cache": true,
|
| 56 |
"vocab_size": 50272,
|
| 57 |
"word_embed_proj_dim": 768
|
generation_config.json
CHANGED
|
@@ -3,5 +3,5 @@
|
|
| 3 |
"bos_token_id": 2,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 1,
|
| 6 |
-
"transformers_version": "4.
|
| 7 |
}
|
|
|
|
| 3 |
"bos_token_id": 2,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 1,
|
| 6 |
+
"transformers_version": "4.36.0.dev0"
|
| 7 |
}
|