Text Generation
Transformers
Safetensors
English
mistral
Eval Results (legacy)
text-generation-inference
Instructions to use cognAI/lil-c3po with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cognAI/lil-c3po with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cognAI/lil-c3po")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("cognAI/lil-c3po") model = AutoModelForCausalLM.from_pretrained("cognAI/lil-c3po", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use cognAI/lil-c3po with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "cognAI/lil-c3po" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cognAI/lil-c3po", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/cognAI/lil-c3po
- SGLang
How to use cognAI/lil-c3po 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 "cognAI/lil-c3po" \ --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": "cognAI/lil-c3po", "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 "cognAI/lil-c3po" \ --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": "cognAI/lil-c3po", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use cognAI/lil-c3po with Docker Model Runner:
docker model run hf.co/cognAI/lil-c3po
Commit ·
2c06fcf
1
Parent(s): dd5a42d
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,8 @@ language:
|
|
| 5 |
---
|
| 6 |
|
| 7 |
# deepnight-research/lil-c3po
|
| 8 |
-
<
|
|
|
|
| 9 |
|
| 10 |
## Model Details:
|
| 11 |
lil-c3po is an open-source large language model (LLM) resulting from the linear merge of two distinct fine-tuned Mistral-7B models, internally referred to as c3-1 and c3-2. These models, developed in-house, bring together unique characteristics to enhance performance and utility.
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
# deepnight-research/lil-c3po
|
| 8 |
+
<div style="display: flex; justify-content: center; align-items: center;">
|
| 9 |
+
<img src="./cover.jpg" style="width: 100%; max-width: 350px; height: auto;"/></div>
|
| 10 |
|
| 11 |
## Model Details:
|
| 12 |
lil-c3po is an open-source large language model (LLM) resulting from the linear merge of two distinct fine-tuned Mistral-7B models, internally referred to as c3-1 and c3-2. These models, developed in-house, bring together unique characteristics to enhance performance and utility.
|