初始化项目，由ModelHub XC社区提供模型

Model: ericzzz/falcon-rw-1b-instruct-openorca
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 +1,196 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- text-generation-inference
+datasets:
+- Open-Orca/SlimOrca
+pipeline_tag: text-generation
+inference: false
+model-index:
+- name: falcon-rw-1b-instruct-openorca
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 34.56
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericzzz/falcon-rw-1b-instruct-openorca
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 60.93
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericzzz/falcon-rw-1b-instruct-openorca
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 28.77
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericzzz/falcon-rw-1b-instruct-openorca
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 37.42
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericzzz/falcon-rw-1b-instruct-openorca
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 60.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericzzz/falcon-rw-1b-instruct-openorca
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 3.41
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ericzzz/falcon-rw-1b-instruct-openorca
+      name: Open LLM Leaderboard
+---
+
+# 🌟 Falcon-RW-1B-Instruct-OpenOrca
+
+Falcon-RW-1B-Instruct-OpenOrca is a 1B parameter, causal decoder-only model based on [Falcon-RW-1B](https://huggingface.co/tiiuae/falcon-rw-1b) and finetuned on the [Open-Orca/SlimOrca](https://huggingface.co/datasets/Open-Orca/SlimOrca) dataset.
+
+**✨Check out our new conversational model [Falcon-RW-1B-Chat](https://huggingface.co/ericzzz/falcon-rw-1b-chat)!✨**
+
+**📊 Evaluation Results**
+
+Falcon-RW-1B-Instruct-OpenOrca was the #1 ranking model (unfortunately not anymore) on [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) in ~1.5B parameters category! A detailed result can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ericzzz__falcon-rw-1b-instruct-openorca).
+
+| Metric     | falcon-rw-1b-instruct-openorca | falcon-rw-1b |
+|------------|-------------------------------:|-------------:|
+| ARC        |                          34.56 |        35.07 |
+| HellaSwag  |                          60.93 |        63.56 |
+| MMLU       |                          28.77 |        25.28 |
+| TruthfulQA |                          37.42 |        35.96 |
+| Winogrande |                          60.69 |        62.04 |
+| GSM8K      |                           3.41 |         0.53 |
+| **Average**|                      **37.63** |    **37.07** |
+
+**🚀 Motivations**
+1. To create a smaller, open-source, instruction-finetuned, ready-to-use model accessible for users with limited computational resources (lower-end consumer GPUs).
+2. To harness the strength of Falcon-RW-1B, a competitive model in its own right, and enhance its capabilities with instruction finetuning.
+
+## 📖 How to Use
+
+The model operates with a structured prompt format, incorporating `<SYS>`, `<INST>`, and `<RESP>` tags to demarcate different parts of the input. The system message and instruction are placed within these tags, with the `<RESP>` tag triggering the model's response.
+
+**📝 Example Code**
+
+ ```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import transformers
+import torch
+
+model = 'ericzzz/falcon-rw-1b-instruct-openorca'
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    'text-generation',
+    model=model,
+    tokenizer=tokenizer,
+    torch_dtype=torch.bfloat16,
+    device_map='auto',
+)
+
+system_message = 'You are a helpful assistant. Give short answers.'
+instruction = 'What is AI? Give some examples.'
+prompt = f'<SYS> {system_message} <INST> {instruction} <RESP> '
+
+response = pipeline(
+    prompt, 
+    max_length=200,
+    repetition_penalty=1.05
+)
+
+print(response[0]['generated_text'])
+# AI, or Artificial Intelligence, refers to the ability of machines and software to perform tasks that require human intelligence, such as learning, reasoning, and problem-solving. It can be used in various fields like computer science, engineering, medicine, and more. Some common applications include image recognition, speech translation, and natural language processing.
+```
+
+## ⚠️ Limitations
+This model may generate inaccurate or misleading information and is prone to hallucination, creating plausible but false narratives. It lacks the ability to discern factual content from fiction and may inadvertently produce biased, harmful or offensive content. Its understanding of complex, nuanced queries is limited. Users should be aware of this and verify any information obtained from the model.
+
+The model is provided 'as is' without any warranties, and the creators are not liable for any damages arising from its use. Users are responsible for their interactions with the model.
+
+## 📬 Contact
+For further inquiries or feedback, please contact at eric.fu96@aol.com.
+
+## [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ericzzz__falcon-rw-1b-instruct-openorca)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |37.63|
+|AI2 Reasoning Challenge (25-Shot)|34.56|
+|HellaSwag (10-Shot)              |60.93|
+|MMLU (5-Shot)                    |28.77|
+|TruthfulQA (0-shot)              |37.42|
+|Winogrande (5-shot)              |60.69|
+|GSM8k (5-shot)                   | 3.41|
+

config.json

@@ -0,0 +1,27 @@
+{
+  "alibi": true,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bias": true,
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "falcon",
+  "multi_query": false,
+  "new_decoder_architecture": false,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_kv_heads": 32,
+  "parallel_attn": false,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": false,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b25582c1b111330f626777a890da807020b359cdc1eb2871926c1693d25f5e01
+size 2623284688

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}