初始化项目，由ModelHub XC社区提供模型

Model: bigcode/gpt_bigcode-santacoder Source: Original Platform
2026-06-28 14:07:12 +08:00
commit e429ae7f19
9 changed files with 345 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,51 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+ 
+ 
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+ 
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+model.safetensors filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,236 @@
+---
+license: openrail
+datasets:
+- bigcode/the-stack
+language:
+- code
+programming_language: 
+- Java
+- JavaScript
+- Python
+pipeline_tag: text-generation
+inference: false
+
+model-index:
+- name: SantaCoder
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      type: nuprl/MultiPL-E
+      name: MultiPL HumanEval (Python)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 0.18
+      verified: false
+    - name: pass@10
+      type: pass@10
+      value: 0.29
+      verified: false
+    - name: pass@100
+      type: pass@100
+      value: 0.49
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: nuprl/MultiPL-E
+      name: MultiPL MBPP (Python)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 0.35
+      verified: false
+    - name: pass@10
+      type: pass@10
+      value: 0.58
+      verified: false
+    - name: pass@100
+      type: pass@100
+      value: 0.77
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: nuprl/MultiPL-E
+      name: MultiPL HumanEval (JavaScript)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 0.16
+      verified: false
+    - name: pass@10
+      type: pass@10
+      value: 0.27
+      verified: false
+    - name: pass@100
+      type: pass@100
+      value: 0.47
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: nuprl/MultiPL-E
+      name: MultiPL MBPP (Javascript)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 0.28
+      verified: false
+    - name: pass@10
+      type: pass@10
+      value: 0.51
+      verified: false
+    - name: pass@100
+      type: pass@100
+      value: 0.70
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: nuprl/MultiPL-E
+      name: MultiPL HumanEval (Java)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 0.15
+      verified: false
+    - name: pass@10
+      type: pass@10
+      value: 0.26
+      verified: false
+    - name: pass@100
+      type: pass@100
+      value: 0.41
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: nuprl/MultiPL-E
+      name: MultiPL MBPP (Java)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 0.28
+      verified: false
+    - name: pass@10
+      type: pass@10
+      value: 0.44
+      verified: false
+    - name: pass@100
+      type: pass@100
+      value: 0.59
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: loubnabnl/humaneval_infilling
+      name: HumanEval FIM (Python)
+    metrics:
+    - name: single_line
+      type: exact_match
+      value: 0.44
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: nuprl/MultiPL-E
+      name: MultiPL HumanEval FIM (Java)
+    metrics:
+    - name: single_line
+      type: exact_match
+      value: 0.62
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: nuprl/MultiPL-E
+      name: MultiPL HumanEval FIM (JavaScript)
+    metrics:
+    - name: single_line
+      type: exact_match
+      value: 0.60
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: code_x_glue_ct_code_to_text
+      name: CodeXGLUE code-to-text (Python)
+    metrics:
+    - name: BLEU
+      type: bleu
+      value: 18.13
+      verified: false
+---
+
+# SantaCoder
+
+![banner](https://huggingface.co/datasets/bigcode/admin/resolve/main/banner.png)
+
+Play with the model on the [SantaCoder Space Demo](https://huggingface.co/spaces/bigcode/santacoder-demo).
+
+#  Table of Contents
+
+1. [Model Summary](#model-summary)
+2. [Use](#use)
+3. [Limitations](#limitations)
+4. [Training](#training)
+5. [License](#license)
+6. [Citation](#citation)
+
+# Model Summary
+
+This is the same model as [SantaCoder](https://huggingface.co/bigcode/santacoder) but it can be loaded with transformers >=4.28.1 to use the GPTBigCode architecture.
+We refer the reader to the [SantaCoder model page](https://huggingface.co/bigcode/santacoder) for full documentation about this model
+
+
+- **Repository:** [bigcode/Megatron-LM](https://github.com/bigcode-project/Megatron-LM)
+- **Project Website:** [bigcode-project.org](www.bigcode-project.org)
+- **Paper:** [🎅SantaCoder: Don't reach for the stars!🌟](https://t.co/YV3pzUbYOr)
+- **Point of Contact:** [contact@bigcode-project.org](mailto:contact@bigcode-project.org)
+- **Languages:** Python, Java, and JavaScript
+
+There are two versions (branches) of the model:
+* `main`: Uses the `gpt_bigcode` model. [Requires the bigcode fork of transformers](https://github.com/bigcode-project/transformers).
+* `main_custom`: Packaged with its modeling code. Requires `transformers>=4.27`.
+  Alternatively, it can run on older versions by setting the configuration parameter `activation_function = "gelu_pytorch_tanh"`.
+
+# Use
+
+## Intended use
+
+The model was trained on GitHub code. As such it is _not_ an instruction model and commands like "Write a function that computes the square root." do not work well.
+You should phrase commands like they occur in source code such as comments (e.g. `# the following function computes the sqrt`) or write a function signature and docstring and let the model complete the function body.
+
+### Attribution & Other Requirements
+
+The pretraining dataset of the model was filtered for permissive licenses only. Nevertheless, the model can generate source code verbatim from the dataset. The code's license might require attribution and/or other specific requirements that must be respected. We provide a [search index](https://huggingface.co/spaces/bigcode/santacoder-search) that let's you search through the pretraining data to identify where generated code came from and apply the proper attribution to your code.
+
+# Limitations
+
+The model has been trained on source code in Python, Java, and JavaScript. The predominant language in source is English although other languages are also present. As such the model is capable to generate code snippets provided some context but the generated code is not guaranteed to work as intended. It can be inefficient, contain bugs or exploits.
+
+# Training
+
+## Model
+
+- **Architecture:** GPT-2 model with multi-query attention and Fill-in-the-Middle objective
+- **Pretraining steps:** 600K
+- **Pretraining tokens:** 236 billion
+- **Precision:** float16
+
+## Hardware
+
+- **GPUs:** 96 Tesla V100
+- **Training time:** 6.2 days
+- **Total FLOPS:** 2.1 x 10e21
+
+## Software
+
+- **Orchestration:** [Megatron-LM](https://github.com/bigcode-project/Megatron-LM)
+- **Neural networks:** [PyTorch](https://github.com/pytorch/pytorch)
+- **FP16 if applicable:** [apex](https://github.com/NVIDIA/apex)
+
+# License
+The model is licenses under the CodeML Open RAIL-M v0.1 license. You can find the full license [here](https://huggingface.co/spaces/bigcode/license).
--- a/config.json
+++ b/config.json
@@ -0,0 +1,32 @@
+{
+  "activation_function": "gelu_pytorch_tanh",
+  "architectures": [
+    "GPTBigCodeForCausalLM"
+  ],
+  "attention_softmax_in_fp32": true,
+  "multi_query": true,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 49152,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 49152,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt_bigcode",
+  "n_embd": 2048,
+  "n_head": 16,
+  "n_inner": 8192,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "resid_pdrop": 0.1,
+  "runner_max_sequence_length": null,
+  "scale_attention_softmax_in_fp32": true,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": true,
+  "vocab_size": 49280
+}
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b332f1400e8e536f079ad599119ccc8ba50783c5aa5f1a9923ef08c014dbabc5
+size 2249803464
--- a/pytorch_model.bin
+++ b/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50d0abae8bfd19082f125e7a40567cba71de296637802eb70157fe55fa66923f
+size 2249864093
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,9 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim-prefix>",
+    "<fim-middle>",
+    "<fim-suffix>",
+    "<fim-pad>"
+  ]
+}
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae12bb8202bf603f0938d4016358964e0ef41d89f4c7358cebc2aaab55306d93
+size 2081116
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,7 @@
+{
+  "errors": "replace",
+  "tokenizer_class": "GPT2TokenizerFast",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048
+}
				`@@ -0,0 +1 @@`
				`{"framework": "pytorch", "task": "text-generation", "allow_remote": true}`