Instructions to use dgnk007/crow with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dgnk007/crow with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dgnk007/crow")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("dgnk007/crow") model = AutoModelForCausalLM.from_pretrained("dgnk007/crow") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use dgnk007/crow with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dgnk007/crow" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dgnk007/crow", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/dgnk007/crow
- SGLang
How to use dgnk007/crow 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 "dgnk007/crow" \ --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": "dgnk007/crow", "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 "dgnk007/crow" \ --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": "dgnk007/crow", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use dgnk007/crow with Docker Model Runner:
docker model run hf.co/dgnk007/crow
Upload tokenizer
Browse files- tokenizer.json +55 -4
tokenizer.json
CHANGED
|
@@ -48,10 +48,61 @@
|
|
| 48 |
"use_regex": true
|
| 49 |
},
|
| 50 |
"post_processor": {
|
| 51 |
-
"type": "
|
| 52 |
-
"
|
| 53 |
-
|
| 54 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
},
|
| 56 |
"decoder": {
|
| 57 |
"type": "ByteLevel",
|
|
|
|
| 48 |
"use_regex": true
|
| 49 |
},
|
| 50 |
"post_processor": {
|
| 51 |
+
"type": "TemplateProcessing",
|
| 52 |
+
"single": [
|
| 53 |
+
{
|
| 54 |
+
"SpecialToken": {
|
| 55 |
+
"id": "<s>",
|
| 56 |
+
"type_id": 0
|
| 57 |
+
}
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"Sequence": {
|
| 61 |
+
"id": "A",
|
| 62 |
+
"type_id": 0
|
| 63 |
+
}
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"SpecialToken": {
|
| 67 |
+
"id": "###",
|
| 68 |
+
"type_id": 0
|
| 69 |
+
}
|
| 70 |
+
}
|
| 71 |
+
],
|
| 72 |
+
"pair": [
|
| 73 |
+
{
|
| 74 |
+
"Sequence": {
|
| 75 |
+
"id": "A",
|
| 76 |
+
"type_id": 0
|
| 77 |
+
}
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"Sequence": {
|
| 81 |
+
"id": "B",
|
| 82 |
+
"type_id": 1
|
| 83 |
+
}
|
| 84 |
+
}
|
| 85 |
+
],
|
| 86 |
+
"special_tokens": {
|
| 87 |
+
"###": {
|
| 88 |
+
"id": "###",
|
| 89 |
+
"ids": [
|
| 90 |
+
21017
|
| 91 |
+
],
|
| 92 |
+
"tokens": [
|
| 93 |
+
"###"
|
| 94 |
+
]
|
| 95 |
+
},
|
| 96 |
+
"<s>": {
|
| 97 |
+
"id": "<s>",
|
| 98 |
+
"ids": [
|
| 99 |
+
50257
|
| 100 |
+
],
|
| 101 |
+
"tokens": [
|
| 102 |
+
"<s>"
|
| 103 |
+
]
|
| 104 |
+
}
|
| 105 |
+
}
|
| 106 |
},
|
| 107 |
"decoder": {
|
| 108 |
"type": "ByteLevel",
|