初始化项目，由ModelHub XC社区提供模型

Model: winglian/basilisk-4b
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 +1,70 @@
+---
+datasets:
+- Open-Orca/OpenOrca
+library_name: transformers
+tags:
+- llama
+---
+# Basilisk 4B
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+
+Built on `winglian/llama-2-4b`, a 4B parameter Llama-2 model, this model is finetuned with open orca CoT data.
+
+
+```
+hf-causal-experimental (pretrained=winglian/basilisk-4b,use_accelerate=True,trust_remote_code=True), limit: None, provide_description: False, num_fewshot: 0, batch_size: None
+|                      Task                      |Version|       Metric        |Value |   |Stderr|
+|------------------------------------------------|------:|---------------------|-----:|---|-----:|
+|agieval_aqua_rat                                |      0|acc                  |0.2362|_  |0.0267|
+|                                                |       |acc_norm             |0.2283|_  |0.0264|
+|agieval_logiqa_en                               |      0|acc                  |0.2688|_  |0.0174|
+|                                                |       |acc_norm             |0.2811|_  |0.0176|
+|agieval_lsat_ar                                 |      0|acc                  |0.2130|_  |0.0271|
+|                                                |       |acc_norm             |0.1913|_  |0.0260|
+|agieval_lsat_lr                                 |      0|acc                  |0.2255|_  |0.0185|
+|                                                |       |acc_norm             |0.2745|_  |0.0198|
+|agieval_lsat_rc                                 |      0|acc                  |0.2305|_  |0.0257|
+|                                                |       |acc_norm             |0.2491|_  |0.0264|
+|agieval_sat_en                                  |      0|acc                  |0.3641|_  |0.0336|
+|                                                |       |acc_norm             |0.3495|_  |0.0333|
+|agieval_sat_en_without_passage                  |      0|acc                  |0.2427|_  |0.0299|
+|                                                |       |acc_norm             |0.2427|_  |0.0299|
+|agieval_sat_math                                |      0|acc                  |0.2318|_  |0.0285|
+|                                                |       |acc_norm             |0.2091|_  |0.0275|
+|bigbench_causal_judgement                       |      0|multiple_choice_grade|0.5000|_  |0.0364|
+|bigbench_date_understanding                     |      0|multiple_choice_grade|0.3930|_  |0.0255|
+|bigbench_disambiguation_qa                      |      0|multiple_choice_grade|0.2674|_  |0.0276|
+|bigbench_geometric_shapes                       |      0|multiple_choice_grade|0.1838|_  |0.0205|
+|                                                |       |exact_str_match      |0.0279|_  |0.0087|
+|bigbench_logical_deduction_five_objects         |      0|multiple_choice_grade|0.2380|_  |0.0191|
+|bigbench_logical_deduction_seven_objects        |      0|multiple_choice_grade|0.1843|_  |0.0147|
+|bigbench_logical_deduction_three_objects        |      0|multiple_choice_grade|0.3800|_  |0.0281|
+|bigbench_movie_recommendation                   |      0|multiple_choice_grade|0.3480|_  |0.0213|
+|bigbench_navigate                               |      0|multiple_choice_grade|0.5000|_  |0.0158|
+|bigbench_reasoning_about_colored_objects        |      0|multiple_choice_grade|0.3680|_  |0.0108|
+|bigbench_ruin_names                             |      0|multiple_choice_grade|0.2746|_  |0.0211|
+|bigbench_salient_translation_error_detection    |      0|multiple_choice_grade|0.2806|_  |0.0142|
+|bigbench_snarks                                 |      0|multiple_choice_grade|0.4972|_  |0.0373|
+|bigbench_sports_understanding                   |      0|multiple_choice_grade|0.4939|_  |0.0159|
+|bigbench_temporal_sequences                     |      0|multiple_choice_grade|0.2740|_  |0.0141|
+|bigbench_tracking_shuffled_objects_five_objects |      0|multiple_choice_grade|0.1904|_  |0.0111|
+|bigbench_tracking_shuffled_objects_seven_objects|      0|multiple_choice_grade|0.1394|_  |0.0083|
+|bigbench_tracking_shuffled_objects_three_objects|      0|multiple_choice_grade|0.3800|_  |0.0281|
+
+hf-causal-experimental (pretrained=winglian/basilisk-4b,use_accelerate=True,trust_remote_code=True), limit: None, provide_description: False, num_fewshot: 0, batch_size: 12
+|    Task     |Version| Metric |Value |   |Stderr|
+|-------------|------:|--------|-----:|---|-----:|
+|arc_challenge|      0|acc     |0.3285|_  |0.0137|
+|             |       |acc_norm|0.3532|_  |0.0140|
+|arc_easy     |      0|acc     |0.6364|_  |0.0099|
+|             |       |acc_norm|0.6035|_  |0.0100|
+|boolq        |      1|acc     |0.7196|_  |0.0079|
+|hellaswag    |      0|acc     |0.4239|_  |0.0049|
+|             |       |acc_norm|0.5473|_  |0.0050|
+|openbookqa   |      0|acc     |0.2220|_  |0.0186|
+|             |       |acc_norm|0.3320|_  |0.0211|
+|piqa         |      0|acc     |0.6937|_  |0.0108|
+|             |       |acc_norm|0.6921|_  |0.0108|
+|winogrande   |      0|acc     |0.5399|_  |0.0140|
+```

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "winglian/llama-2-4b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "dropout_attn": 0,
+  "dropout_mlp": 0.001,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32002
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.34.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8b1d304ab46e72899788bad80f3f9c6413250abef8dce66e8b7eeeb15381133
+size 7000644361

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,66 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a4d59665e469a2426f2e12442b74bbb7c8468ad9012c8c80b7217d296502bd7
+size 5819