Instructions to use solidrust/Cognitron-8B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use solidrust/Cognitron-8B-AWQ with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="solidrust/Cognitron-8B-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("solidrust/Cognitron-8B-AWQ")
model = AutoModelForCausalLM.from_pretrained("solidrust/Cognitron-8B-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use solidrust/Cognitron-8B-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "solidrust/Cognitron-8B-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "solidrust/Cognitron-8B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/solidrust/Cognitron-8B-AWQ

SGLang

How to use solidrust/Cognitron-8B-AWQ 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 "solidrust/Cognitron-8B-AWQ" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "solidrust/Cognitron-8B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "solidrust/Cognitron-8B-AWQ" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "solidrust/Cognitron-8B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use solidrust/Cognitron-8B-AWQ with Docker Model Runner:
```
docker model run hf.co/solidrust/Cognitron-8B-AWQ
```

Suparious commited on May 4, 2024

Commit

1cf0b06

verified ·

1 Parent(s): 24862be

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -0

README.md CHANGED Viewed

@@ -1,6 +1,10 @@
 ---
 library_name: transformers
 tags:
 - 4-bit
 - AWQ
 - text-generation
@@ -15,7 +19,15 @@ quantized_by: Suparious
 - Model creator: [bunnycore](https://huggingface.co/bunnycore)
 - Original model: [Cognitron-8B](https://huggingface.co/bunnycore/Cognitron-8B)
 ## How to use

 ---
 library_name: transformers
+license: apache-2.0
 tags:
+- merge
+- mergekit
+- lazymergekit
 - 4-bit
 - AWQ
 - text-generation
 - Model creator: [bunnycore](https://huggingface.co/bunnycore)
 - Original model: [Cognitron-8B](https://huggingface.co/bunnycore/Cognitron-8B)
+## Model Summary
+Cognitron-8B is an experimental large language model (LLM) created by combining three pre-existing models: Llama-3-8B-Lexi-Uncensored, Einstein-v6.1-Llama3-8B, and dolphin-2.9-llama3-8b. This combination aims to achieve a unique blend of capabilities:
+* Uncensored Knowledge: By incorporating Llama-3-8B-Lexi-Uncensored, Cognitron-8B has access to a wider range of information without filtering.
+* Enhanced Intelligence: The inclusion of Einstein-v6.1-Llama3-8B is intended to boost Cognitron-8B's reasoning and problem-solving abilities.
+* Creative Fluency: The dolphin-2.9-llama3-8b component is designed to contribute creativity and unconventional thinking to Cognitron-8B's responses.
+It is important to note that combining these models is an experiment, and the resulting performance is unknown.
 ## How to use