Instructions to use athirdpath/BigMistral-13b-GLUED with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use athirdpath/BigMistral-13b-GLUED with Transformers:

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

pipe = pipeline("text-generation", model="athirdpath/BigMistral-13b-GLUED")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("athirdpath/BigMistral-13b-GLUED")
model = AutoModelForCausalLM.from_pretrained("athirdpath/BigMistral-13b-GLUED")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use athirdpath/BigMistral-13b-GLUED with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/athirdpath/BigMistral-13b-GLUED

SGLang

How to use athirdpath/BigMistral-13b-GLUED 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 "athirdpath/BigMistral-13b-GLUED" \
    --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": "athirdpath/BigMistral-13b-GLUED",
		"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 "athirdpath/BigMistral-13b-GLUED" \
        --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": "athirdpath/BigMistral-13b-GLUED",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use athirdpath/BigMistral-13b-GLUED with Docker Model Runner:
```
docker model run hf.co/athirdpath/BigMistral-13b-GLUED
```

Description

This is BigMistral-13b (a 13b Mistral base model, using a modified NeverSleep recipe) merged with a 512-rank LORA trained over it directly.

Logic

My 20b Llama 2 merges did well, in part due to the inclusion of Elieithyia-20b, trained on top of a 20b merge directly. This time, I trained the LoRA not with the traditional goals in mind, but with “healing” the 13b merge. This involved increasing the gradient accumulation steps significantly, lowering the learning rate, and decreasing the dropout. Fingers crossed!

Results

Prelimary results are an improvement. Really needs a bigger dataset of more cognitive tasks like OpenOrca. Writes okay stories and responds mostly factually. Idea is solid.

Dataset

This LORA was trained on a dataset that consists of teknium1’s roleplay-instruct-v2.1, and then part of the private Elieithyia dataset and of HF’s No Robots, chosen randomly to form a even (filesize) 3 way split.

Downloads last month: 8