Instructions to use glaborie/shawgpt-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use glaborie/shawgpt-ft with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("TheBloke/Mistral-7B-Instruct-v0.2-GPTQ")
model = PeftModel.from_pretrained(base_model, "glaborie/shawgpt-ft")

Transformers

How to use glaborie/shawgpt-ft with Transformers:

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

pipe = pipeline("text-generation", model="glaborie/shawgpt-ft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("glaborie/shawgpt-ft", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use glaborie/shawgpt-ft with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/glaborie/shawgpt-ft

SGLang

How to use glaborie/shawgpt-ft 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 "glaborie/shawgpt-ft" \
    --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": "glaborie/shawgpt-ft",
		"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 "glaborie/shawgpt-ft" \
        --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": "glaborie/shawgpt-ft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use glaborie/shawgpt-ft with Docker Model Runner:
```
docker model run hf.co/glaborie/shawgpt-ft
```

shawgpt-ft

This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.4650

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 2
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
4.2259	1.0	4	3.7826
3.4714	2.0	8	3.1217
2.9082	3.0	12	2.6339
2.4457	4.0	16	2.2700
2.1686	5.0	20	1.9701
1.699	6.0	24	1.7254
1.4794	7.0	28	1.5955
1.4546	8.0	32	1.5156
1.3939	9.0	36	1.4769
1.2823	10.0	40	1.4650

Framework versions

PEFT 0.16.0
Transformers 4.53.2
Pytorch 2.6.0+cu124
Datasets 4.0.0
Tokenizers 0.21.2

Downloads last month: 1

Model tree for glaborie/shawgpt-ft

Base model

mistralai/Mistral-7B-Instruct-v0.2

Quantized

TheBloke/Mistral-7B-Instruct-v0.2-GPTQ

Adapter

(438)

this model