初始化项目，由ModelHub XC社区提供模型

Model: nuprl/MultiPL-T-StarCoderBase_1b
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt 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
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,73 @@
+---
+license: bigscience-openrail-m
+library_name: transformers
+tags:
+- code
+- gpt_bigcode
+datasets:
+- nuprl/MultiPL-T
+metrics:
+- code_eval
+model-index:
+- name: MultiPLCoder-1b-OCaml
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: MultiPL-HumanEval (Lua)
+      type: nuprl/MultiPL-E
+    metrics:
+    - type: pass@1
+      value: 0.173
+      name: pass@1
+      verified: true
+    - type: pass@1
+      value: 0.113
+      name: pass@1
+      verified: true
+    - type: pass@1
+      value: 0.097
+      name: pass@1
+      verified: true
+---
+# MultiPLCoder-1b
+
+1 billion parameter version of MultiPLCoder, a set of StarCoder-based models finetuned on the [MultiPL-T dataset](https://huggingface.co/datasets/nuprl/MultiPL-T).
+These models are state-of-the-art at low-resource languages, such as: Lua, Racket, and OCaml.
+
+
+## Language Revision Index
+
+This is the revision index for the best-performing models for their respective langauge.
+
+| Langauge      | Revision ID | Epoch |
+| ------------- | ----------- | ----- |
+| Lua           | `7e96d931547e342ad0661cdd91236fe4ccf52545`         | 3    |
+| Racket        | `2cdc541bee1db4da80c0b43384b0d6a0cacca5b2`         | 5    |
+| OCaml         | `e8a24f9e2149cbda8c3cca264a53c2b361b7a031`         | 6    |
+
+## Usage
+
+To utilize one of the models in this repository, you must first select a commit revision for that model from the table above.
+For example, to use the Lua model:
+```py
+from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("nuprl/MultiPLCoder-1b")
+lua_revision="7e96d931547e342ad0661cdd91236fe4ccf52545"
+model = AutoModelForCausalLM.from_pretrained("nuprl/MultiPLCoder-1b", revision=lua_revision)
+```
+
+Note that the model's default configuration does not enable caching, therefore you must specify to use the cache on generation.
+```py
+toks = tokenizer.encode("-- Hello World", return_tensors="pt")
+out = model.generate(toks, use_cache=True,  do_sample=True, temperature=0.2, top_p=0.95, max_length=50)
+print(tokenizer.decode(out[0], skip_special_tokens=True))
+```
+```
+-- Hello World!
+-- :param name: The name of the person to say hello to
+-- :return: A greeting
+local function say_hello(name)
+  return "Hello ".. name
+end
+```

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "more_stack/rkt/checkpoint_final",
+  "activation_function": "gelu_pytorch_tanh",
+  "architectures": [
+    "GPTBigCodeForCausalLM"
+  ],
+  "attention_softmax_in_fp32": true,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "inference_runner": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_batch_size": null,
+  "max_sequence_length": null,
+  "model_type": "gpt_bigcode",
+  "multi_query": true,
+  "n_embd": 2048,
+  "n_head": 16,
+  "n_inner": 8192,
+  "n_layer": 24,
+  "n_positions": 8192,
+  "pad_key_length": true,
+  "pre_allocate_kv_cache": false,
+  "resid_pdrop": 0.1,
+  "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,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "use_cache": false,
+  "validate_runner_input": true,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.40.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1313129f3105132d439326b5289f3ba8d7594f1c6701e5a570ba716d85f59861
+size 2274445296

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:503988ef3250f9e00eeec150cd90421a64988db58796a3cb63354870c35d1023
+size 2274505693

special_tokens_map.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}