Instructions to use ghdi/punic-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ghdi/punic-model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ghdi/punic-model")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ghdi/punic-model") model = AutoModelForCausalLM.from_pretrained("ghdi/punic-model") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ghdi/punic-model with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ghdi/punic-model" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ghdi/punic-model", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ghdi/punic-model
- SGLang
How to use ghdi/punic-model 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 "ghdi/punic-model" \ --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": "ghdi/punic-model", "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 "ghdi/punic-model" \ --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": "ghdi/punic-model", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ghdi/punic-model with Docker Model Runner:
docker model run hf.co/ghdi/punic-model
Training in progress epoch 59
Browse files- README.md +4 -3
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Train Loss:
|
| 18 |
-
- Validation Loss: 7.
|
| 19 |
-
- Epoch:
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -101,6 +101,7 @@ The following hyperparameters were used during training:
|
|
| 101 |
| 4.2240 | 7.6315 | 56 |
|
| 102 |
| 4.1587 | 7.6412 | 57 |
|
| 103 |
| 4.0442 | 7.6748 | 58 |
|
|
|
|
| 104 |
|
| 105 |
|
| 106 |
### Framework versions
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Train Loss: 3.9858
|
| 18 |
+
- Validation Loss: 7.6193
|
| 19 |
+
- Epoch: 59
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 101 |
| 4.2240 | 7.6315 | 56 |
|
| 102 |
| 4.1587 | 7.6412 | 57 |
|
| 103 |
| 4.0442 | 7.6748 | 58 |
|
| 104 |
+
| 3.9858 | 7.6193 | 59 |
|
| 105 |
|
| 106 |
|
| 107 |
### Framework versions
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497935440
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88e21c068acea3b03fc804dc3dd9522b1ea22d7216cc312d89462445b7e086c9
|
| 3 |
size 497935440
|