Instructions to use Tensoic/Cerule-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Tensoic/Cerule-v0.1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Tensoic/Cerule-v0.1", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Tensoic/Cerule-v0.1", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Tensoic/Cerule-v0.1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Tensoic/Cerule-v0.1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Tensoic/Cerule-v0.1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Tensoic/Cerule-v0.1
- SGLang
How to use Tensoic/Cerule-v0.1 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 "Tensoic/Cerule-v0.1" \ --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": "Tensoic/Cerule-v0.1", "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 "Tensoic/Cerule-v0.1" \ --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": "Tensoic/Cerule-v0.1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Tensoic/Cerule-v0.1 with Docker Model Runner:
docker model run hf.co/Tensoic/Cerule-v0.1
fix `_name_or_path` in config.json
#3
by not-lain - opened
- README.md +6 -0
- config.json +2 -2
- requirements.txt +2 -0
README.md
CHANGED
|
@@ -40,6 +40,12 @@ The training setup was `4xA100's 80GB` and took ~6 hours to pretrain and ~13 hou
|
|
| 40 |
---
|
| 41 |
|
| 42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
## Training:
|
| 44 |
We will release the training code in some time.
|
| 45 |
|
|
|
|
| 40 |
---
|
| 41 |
|
| 42 |
|
| 43 |
+
## Installing requirements
|
| 44 |
+
```
|
| 45 |
+
pip install -qr https://huggingface.co/Tensoic/Cerule-v0.1/resolve/main/requirements.txt
|
| 46 |
+
```
|
| 47 |
+
|
| 48 |
+
|
| 49 |
## Training:
|
| 50 |
We will release the training code in some time.
|
| 51 |
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "Tensoic/Cerule",
|
| 3 |
"architectures": [
|
| 4 |
"CeruleGemmaForCausalLM"
|
| 5 |
],
|
|
@@ -34,7 +34,7 @@
|
|
| 34 |
"tokenizer_model_max_length": 2048,
|
| 35 |
"tokenizer_padding_side": "right",
|
| 36 |
"torch_dtype": "bfloat16",
|
| 37 |
-
"transformers_version": "4.39.
|
| 38 |
"tune_mm_mlp_adapter": false,
|
| 39 |
"use_cache": true,
|
| 40 |
"use_mm_proj": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "Tensoic/Cerule-v0.1",
|
| 3 |
"architectures": [
|
| 4 |
"CeruleGemmaForCausalLM"
|
| 5 |
],
|
|
|
|
| 34 |
"tokenizer_model_max_length": 2048,
|
| 35 |
"tokenizer_padding_side": "right",
|
| 36 |
"torch_dtype": "bfloat16",
|
| 37 |
+
"transformers_version": "4.39.1",
|
| 38 |
"tune_mm_mlp_adapter": false,
|
| 39 |
"use_cache": true,
|
| 40 |
"use_mm_proj": true,
|
requirements.txt
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
transformers>=4.39.1
|
| 2 |
+
flash_attn
|