Text Generation
Transformers
PyTorch
code
gpt2
custom_code
Eval Results (legacy)
text-generation-inference
Instructions to use lambdasec/santafixer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lambdasec/santafixer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lambdasec/santafixer", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lambdasec/santafixer", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("lambdasec/santafixer", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use lambdasec/santafixer with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lambdasec/santafixer" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lambdasec/santafixer", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/lambdasec/santafixer
- SGLang
How to use lambdasec/santafixer 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 "lambdasec/santafixer" \ --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": "lambdasec/santafixer", "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 "lambdasec/santafixer" \ --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": "lambdasec/santafixer", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use lambdasec/santafixer with Docker Model Runner:
docker model run hf.co/lambdasec/santafixer
Asankhaya Sharma commited on
Commit ·
f4f68fd
1
Parent(s): 12408c7
update model
Browse files- all_results.json +4 -4
- special_tokens_map.json +1 -0
all_results.json
CHANGED
|
@@ -2,15 +2,15 @@
|
|
| 2 |
"epoch": 2.98,
|
| 3 |
"eval_accuracy": 0.7246660149885956,
|
| 4 |
"eval_loss": 1.3612703084945679,
|
| 5 |
-
"eval_runtime": 4.
|
| 6 |
"eval_samples": 12,
|
| 7 |
-
"eval_samples_per_second": 2.
|
| 8 |
"eval_steps_per_second": 0.422,
|
| 9 |
"perplexity": 3.901145814186261,
|
| 10 |
"total_flos": 4887048754298880.0,
|
| 11 |
"train_loss": 0.6763701610076122,
|
| 12 |
-
"train_runtime":
|
| 13 |
"train_samples": 262,
|
| 14 |
-
"train_samples_per_second": 0.
|
| 15 |
"train_steps_per_second": 0.155
|
| 16 |
}
|
|
|
|
| 2 |
"epoch": 2.98,
|
| 3 |
"eval_accuracy": 0.7246660149885956,
|
| 4 |
"eval_loss": 1.3612703084945679,
|
| 5 |
+
"eval_runtime": 4.7402,
|
| 6 |
"eval_samples": 12,
|
| 7 |
+
"eval_samples_per_second": 2.532,
|
| 8 |
"eval_steps_per_second": 0.422,
|
| 9 |
"perplexity": 3.901145814186261,
|
| 10 |
"total_flos": 4887048754298880.0,
|
| 11 |
"train_loss": 0.6763701610076122,
|
| 12 |
+
"train_runtime": 1257.1352,
|
| 13 |
"train_samples": 262,
|
| 14 |
+
"train_samples_per_second": 0.625,
|
| 15 |
"train_steps_per_second": 0.155
|
| 16 |
}
|
special_tokens_map.json
CHANGED
|
@@ -8,5 +8,6 @@
|
|
| 8 |
],
|
| 9 |
"bos_token": "<|endoftext|>",
|
| 10 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 11 |
"unk_token": "<|endoftext|>"
|
| 12 |
}
|
|
|
|
| 8 |
],
|
| 9 |
"bos_token": "<|endoftext|>",
|
| 10 |
"eos_token": "<|endoftext|>",
|
| 11 |
+
"pad_token": "<|endoftext|>",
|
| 12 |
"unk_token": "<|endoftext|>"
|
| 13 |
}
|