Text Generation
Transformers
PyTorch
English
llama
code
text-generation-inference
Information Extraction
IE
Named Entity Recogniton
Event Extraction
Relation Extraction
LLaMA
custom_code
Instructions to use HiTZ/GoLLIE-34B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HiTZ/GoLLIE-34B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="HiTZ/GoLLIE-34B", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("HiTZ/GoLLIE-34B", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("HiTZ/GoLLIE-34B", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use HiTZ/GoLLIE-34B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "HiTZ/GoLLIE-34B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HiTZ/GoLLIE-34B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/HiTZ/GoLLIE-34B
- SGLang
How to use HiTZ/GoLLIE-34B 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 "HiTZ/GoLLIE-34B" \ --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": "HiTZ/GoLLIE-34B", "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 "HiTZ/GoLLIE-34B" \ --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": "HiTZ/GoLLIE-34B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use HiTZ/GoLLIE-34B with Docker Model Runner:
docker model run hf.co/HiTZ/GoLLIE-34B
Update config.json
Browse files- config.json +4 -1
config.json
CHANGED
|
@@ -3,6 +3,9 @@
|
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
|
|
|
|
|
|
|
|
| 6 |
"attention_bias": false,
|
| 7 |
"bos_token_id": 1,
|
| 8 |
"eos_token_id": 2,
|
|
@@ -21,7 +24,7 @@
|
|
| 21 |
"rope_theta": 1000000,
|
| 22 |
"tie_word_embeddings": false,
|
| 23 |
"torch_dtype": "bfloat16",
|
| 24 |
-
"transformers_version": "4.
|
| 25 |
"use_cache": true,
|
| 26 |
"vocab_size": 32000
|
| 27 |
}
|
|
|
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoModelForCausalLM": "modeling_flash_llama.LlamaForCausalLM"
|
| 8 |
+
},
|
| 9 |
"attention_bias": false,
|
| 10 |
"bos_token_id": 1,
|
| 11 |
"eos_token_id": 2,
|
|
|
|
| 24 |
"rope_theta": 1000000,
|
| 25 |
"tie_word_embeddings": false,
|
| 26 |
"torch_dtype": "bfloat16",
|
| 27 |
+
"transformers_version": "4.33.1",
|
| 28 |
"use_cache": true,
|
| 29 |
"vocab_size": 32000
|
| 30 |
}
|