Instructions to use MikeMpapa/lmd-4bars-2048-epochs01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MikeMpapa/lmd-4bars-2048-epochs01 with Transformers:

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

pipe = pipeline("text-generation", model="MikeMpapa/lmd-4bars-2048-epochs01")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MikeMpapa/lmd-4bars-2048-epochs01")
model = AutoModelForCausalLM.from_pretrained("MikeMpapa/lmd-4bars-2048-epochs01", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MikeMpapa/lmd-4bars-2048-epochs01 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MikeMpapa/lmd-4bars-2048-epochs01"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MikeMpapa/lmd-4bars-2048-epochs01",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MikeMpapa/lmd-4bars-2048-epochs01

SGLang

How to use MikeMpapa/lmd-4bars-2048-epochs01 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 "MikeMpapa/lmd-4bars-2048-epochs01" \
    --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": "MikeMpapa/lmd-4bars-2048-epochs01",
		"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 "MikeMpapa/lmd-4bars-2048-epochs01" \
        --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": "MikeMpapa/lmd-4bars-2048-epochs01",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MikeMpapa/lmd-4bars-2048-epochs01 with Docker Model Runner:
```
docker model run hf.co/MikeMpapa/lmd-4bars-2048-epochs01
```

MikeMpapa commited on Apr 17, 2024

Commit

aa8acae

verified ·

1 Parent(s): 9c9d8d7

End of training

Browse files

Files changed (2) hide show

README.md +60 -0
generation_config.json +5 -0

README.md ADDED Viewed

	@@ -0,0 +1,60 @@

+---
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+model-index:
+- name: lmd-4bars-2048-epochs7
+  results: []
+---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+# lmd-4bars-2048-epochs7
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.7679
+## 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: 0.005
+- train_batch_size: 8
+- eval_batch_size: 4
+- seed: 1
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.01
+- num_epochs: 7
+### Training results
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 4.9268        | 4.17  | 5000 | 4.7679          |
+### Framework versions
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

generation_config.json ADDED Viewed

	@@ -0,0 +1,5 @@

+{
+  "_from_model_config": true,
+  "pad_token_id": 3,
+  "transformers_version": "4.38.2"
+}