Instructions to use rootacess/FlashCoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rootacess/FlashCoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="rootacess/FlashCoder")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("rootacess/FlashCoder") model = AutoModelForCausalLM.from_pretrained("rootacess/FlashCoder") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use rootacess/FlashCoder with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "rootacess/FlashCoder" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "rootacess/FlashCoder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/rootacess/FlashCoder
- SGLang
How to use rootacess/FlashCoder 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 "rootacess/FlashCoder" \ --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": "rootacess/FlashCoder", "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 "rootacess/FlashCoder" \ --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": "rootacess/FlashCoder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use rootacess/FlashCoder with Docker Model Runner:
docker model run hf.co/rootacess/FlashCoder
Upload tokenizer
Browse files- added_tokens.json +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +9 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<pad>": 32768
|
| 3 |
+
}
|
special_tokens_map.json
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"bos_token": "<|endoftext|>",
|
| 3 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 4 |
"unk_token": "<|endoftext|>"
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"bos_token": "<|endoftext|>",
|
| 3 |
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
"unk_token": "<|endoftext|>"
|
| 6 |
}
|
tokenizer.json
CHANGED
|
@@ -11,6 +11,15 @@
|
|
| 11 |
"rstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
}
|
| 15 |
],
|
| 16 |
"normalizer": null,
|
|
|
|
| 11 |
"rstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 32768,
|
| 17 |
+
"content": "<pad>",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": true,
|
| 22 |
+
"special": false
|
| 23 |
}
|
| 24 |
],
|
| 25 |
"normalizer": null,
|