Instructions to use DS-Archive/Chronohermes-Grad-L2-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DS-Archive/Chronohermes-Grad-L2-13b with Transformers:

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

pipe = pipeline("text-generation", model="DS-Archive/Chronohermes-Grad-L2-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DS-Archive/Chronohermes-Grad-L2-13b")
model = AutoModelForCausalLM.from_pretrained("DS-Archive/Chronohermes-Grad-L2-13b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DS-Archive/Chronohermes-Grad-L2-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DS-Archive/Chronohermes-Grad-L2-13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DS-Archive/Chronohermes-Grad-L2-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DS-Archive/Chronohermes-Grad-L2-13b

SGLang

How to use DS-Archive/Chronohermes-Grad-L2-13b 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 "DS-Archive/Chronohermes-Grad-L2-13b" \
    --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": "DS-Archive/Chronohermes-Grad-L2-13b",
		"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 "DS-Archive/Chronohermes-Grad-L2-13b" \
        --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": "DS-Archive/Chronohermes-Grad-L2-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DS-Archive/Chronohermes-Grad-L2-13b with Docker Model Runner:
```
docker model run hf.co/DS-Archive/Chronohermes-Grad-L2-13b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card: Chronohermes-Grad-L2-13b

This is a Llama 2-based model consisting of a gradient merge between:

Quantized Models Provided by TheBloke (Thanks!):

GGML
GPTQ

The merge was performed using BlockMerge_Gradient by Gryphe

The intended objective was to combine NH2's superior instruction following capabilities with the creativity and response length of Chronos v2. Merge ratios used are identical to those used in Chronoboros Grad, with NH2 starting with a weight of 0.9 at the 1st layer and phasing out by the 25th layer. The method is illustrated in the image below, with green representing NH2 and blue representing Chronos v2:

Usage:

Intended to be prompted with the Alpaca instruction format of the base models:

### Instruction:
<prompt>

### Response:
<leave a newline blank for model to respond>

Bias, Risks, and Limitations

The model will show biases similar to those exhibited by the base models. It is not intended for supplying factual information or advice in any form.

Training Details

This model is a merge. Please refer to the link repositories of the base models for details.

Downloads last month: 29

Model tree for DS-Archive/Chronohermes-Grad-L2-13b

Finetunes

1 model

Quantizations

3 models