Text Generation
Transformers
PyTorch
code
gpt2
custom_code
Eval Results (legacy)
text-generation-inference
Instructions to use bigcode/santacoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigcode/santacoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bigcode/santacoder", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("bigcode/santacoder", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("bigcode/santacoder", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use bigcode/santacoder with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bigcode/santacoder" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bigcode/santacoder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/bigcode/santacoder
- SGLang
How to use bigcode/santacoder 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 "bigcode/santacoder" \ --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": "bigcode/santacoder", "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 "bigcode/santacoder" \ --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": "bigcode/santacoder", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use bigcode/santacoder with Docker Model Runner:
docker model run hf.co/bigcode/santacoder
Commit ·
d3c3868
1
Parent(s): e02c7b7
Update README.md
Browse files
README.md
CHANGED
|
@@ -20,38 +20,39 @@ model-index:
|
|
| 20 |
- task:
|
| 21 |
type: text-generation
|
| 22 |
dataset:
|
| 23 |
-
type:
|
| 24 |
-
name: HumanEval (Python)
|
| 25 |
metrics:
|
| 26 |
- name: pass@1
|
| 27 |
type: pass@1
|
| 28 |
-
value: 0.
|
| 29 |
verified: false
|
| 30 |
- name: pass@10
|
| 31 |
type: pass@10
|
| 32 |
-
value: 0.
|
| 33 |
verified: false
|
| 34 |
- name: pass@100
|
| 35 |
type: pass@100
|
| 36 |
-
value: 0.
|
| 37 |
verified: false
|
| 38 |
- task:
|
| 39 |
type: text-generation
|
| 40 |
dataset:
|
| 41 |
type: nuprl/MultiPL-E
|
| 42 |
-
name: MultiPL
|
| 43 |
metrics:
|
| 44 |
- name: pass@1
|
| 45 |
type: pass@1
|
| 46 |
-
value: 0.
|
| 47 |
verified: false
|
| 48 |
- name: pass@10
|
| 49 |
type: pass@10
|
| 50 |
-
value: 0.
|
| 51 |
verified: false
|
| 52 |
- name: pass@100
|
| 53 |
type: pass@100
|
| 54 |
-
value: 0.
|
|
|
|
| 55 |
- task:
|
| 56 |
type: text-generation
|
| 57 |
dataset:
|
|
@@ -60,67 +61,70 @@ model-index:
|
|
| 60 |
metrics:
|
| 61 |
- name: pass@1
|
| 62 |
type: pass@1
|
| 63 |
-
value: 0.
|
| 64 |
verified: false
|
| 65 |
- name: pass@10
|
| 66 |
type: pass@10
|
| 67 |
-
value: 0.
|
| 68 |
verified: false
|
| 69 |
- name: pass@100
|
| 70 |
type: pass@100
|
| 71 |
value: 0.47
|
|
|
|
| 72 |
- task:
|
| 73 |
type: text-generation
|
| 74 |
dataset:
|
| 75 |
-
type:
|
| 76 |
-
name: MBPP (
|
| 77 |
metrics:
|
| 78 |
- name: pass@1
|
| 79 |
type: pass@1
|
| 80 |
-
value: 0.
|
| 81 |
verified: false
|
| 82 |
- name: pass@10
|
| 83 |
type: pass@10
|
| 84 |
-
value: 0.
|
| 85 |
verified: false
|
| 86 |
- name: pass@100
|
| 87 |
type: pass@100
|
| 88 |
-
value: 0.
|
| 89 |
verified: false
|
| 90 |
- task:
|
| 91 |
type: text-generation
|
| 92 |
dataset:
|
| 93 |
type: nuprl/MultiPL-E
|
| 94 |
-
name: MultiPL
|
| 95 |
metrics:
|
| 96 |
- name: pass@1
|
| 97 |
type: pass@1
|
| 98 |
-
value: 0.
|
| 99 |
verified: false
|
| 100 |
- name: pass@10
|
| 101 |
type: pass@10
|
| 102 |
-
value: 0.
|
| 103 |
verified: false
|
| 104 |
- name: pass@100
|
| 105 |
type: pass@100
|
| 106 |
-
value: 0.
|
|
|
|
| 107 |
- task:
|
| 108 |
type: text-generation
|
| 109 |
dataset:
|
| 110 |
type: nuprl/MultiPL-E
|
| 111 |
-
name: MultiPL MBPP (
|
| 112 |
metrics:
|
| 113 |
- name: pass@1
|
| 114 |
type: pass@1
|
| 115 |
-
value: 0.
|
| 116 |
verified: false
|
| 117 |
- name: pass@10
|
| 118 |
type: pass@10
|
| 119 |
-
value: 0.
|
| 120 |
verified: false
|
| 121 |
- name: pass@100
|
| 122 |
type: pass@100
|
| 123 |
-
value: 0.
|
|
|
|
| 124 |
- task:
|
| 125 |
type: text-generation
|
| 126 |
dataset:
|
|
|
|
| 20 |
- task:
|
| 21 |
type: text-generation
|
| 22 |
dataset:
|
| 23 |
+
type: nuprl/MultiPL-E
|
| 24 |
+
name: MultiPL HumanEval (Python)
|
| 25 |
metrics:
|
| 26 |
- name: pass@1
|
| 27 |
type: pass@1
|
| 28 |
+
value: 0.18
|
| 29 |
verified: false
|
| 30 |
- name: pass@10
|
| 31 |
type: pass@10
|
| 32 |
+
value: 0.29
|
| 33 |
verified: false
|
| 34 |
- name: pass@100
|
| 35 |
type: pass@100
|
| 36 |
+
value: 0.49
|
| 37 |
verified: false
|
| 38 |
- task:
|
| 39 |
type: text-generation
|
| 40 |
dataset:
|
| 41 |
type: nuprl/MultiPL-E
|
| 42 |
+
name: MultiPL MBPP (Python)
|
| 43 |
metrics:
|
| 44 |
- name: pass@1
|
| 45 |
type: pass@1
|
| 46 |
+
value: 0.35
|
| 47 |
verified: false
|
| 48 |
- name: pass@10
|
| 49 |
type: pass@10
|
| 50 |
+
value: 0.58
|
| 51 |
verified: false
|
| 52 |
- name: pass@100
|
| 53 |
type: pass@100
|
| 54 |
+
value: 0.77
|
| 55 |
+
verified: false
|
| 56 |
- task:
|
| 57 |
type: text-generation
|
| 58 |
dataset:
|
|
|
|
| 61 |
metrics:
|
| 62 |
- name: pass@1
|
| 63 |
type: pass@1
|
| 64 |
+
value: 0.16
|
| 65 |
verified: false
|
| 66 |
- name: pass@10
|
| 67 |
type: pass@10
|
| 68 |
+
value: 0.27
|
| 69 |
verified: false
|
| 70 |
- name: pass@100
|
| 71 |
type: pass@100
|
| 72 |
value: 0.47
|
| 73 |
+
verified: false
|
| 74 |
- task:
|
| 75 |
type: text-generation
|
| 76 |
dataset:
|
| 77 |
+
type: nuprl/MultiPL-E
|
| 78 |
+
name: MultiPL MBPP (Javascript)
|
| 79 |
metrics:
|
| 80 |
- name: pass@1
|
| 81 |
type: pass@1
|
| 82 |
+
value: 0.28
|
| 83 |
verified: false
|
| 84 |
- name: pass@10
|
| 85 |
type: pass@10
|
| 86 |
+
value: 0.51
|
| 87 |
verified: false
|
| 88 |
- name: pass@100
|
| 89 |
type: pass@100
|
| 90 |
+
value: 0.70
|
| 91 |
verified: false
|
| 92 |
- task:
|
| 93 |
type: text-generation
|
| 94 |
dataset:
|
| 95 |
type: nuprl/MultiPL-E
|
| 96 |
+
name: MultiPL HumanEval (Java)
|
| 97 |
metrics:
|
| 98 |
- name: pass@1
|
| 99 |
type: pass@1
|
| 100 |
+
value: 0.15
|
| 101 |
verified: false
|
| 102 |
- name: pass@10
|
| 103 |
type: pass@10
|
| 104 |
+
value: 0.26
|
| 105 |
verified: false
|
| 106 |
- name: pass@100
|
| 107 |
type: pass@100
|
| 108 |
+
value: 0.41
|
| 109 |
+
verified: false
|
| 110 |
- task:
|
| 111 |
type: text-generation
|
| 112 |
dataset:
|
| 113 |
type: nuprl/MultiPL-E
|
| 114 |
+
name: MultiPL MBPP (Java)
|
| 115 |
metrics:
|
| 116 |
- name: pass@1
|
| 117 |
type: pass@1
|
| 118 |
+
value: 0.28
|
| 119 |
verified: false
|
| 120 |
- name: pass@10
|
| 121 |
type: pass@10
|
| 122 |
+
value: 0.44
|
| 123 |
verified: false
|
| 124 |
- name: pass@100
|
| 125 |
type: pass@100
|
| 126 |
+
value: 0.59
|
| 127 |
+
verified: false
|
| 128 |
- task:
|
| 129 |
type: text-generation
|
| 130 |
dataset:
|