初始化项目，由ModelHub XC社区提供模型

Model: OEvortex/HelpingAI-Lite
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 +1,140 @@
+---
+datasets:
+- cerebras/SlimPajama-627B
+- HuggingFaceH4/ultrachat_200k
+- bigcode/starcoderdata
+- HuggingFaceH4/ultrafeedback_binarized
+language:
+- en
+metrics:
+- accuracy
+- speed
+library_name: transformers
+tags:
+- coder
+- Text-Generation
+- Transformers
+- HelpingAI
+license: mit
+widget:
+- text: |
+    <|system|>
+    You are a chatbot who can code!</s>
+    <|user|>
+    Write me a function to search for OEvortex on youtube use Webbrowser .</s>
+    <|assistant|>
+- text: |
+    <|system|>
+    You are a chatbot who can be a teacher!</s>
+    <|user|>
+    Explain me working of AI .</s>
+    <|assistant|>
+model-index:
+- name: HelpingAI-Lite
+  results:
+  - task:
+      type: text-generation
+    metrics:
+    - name: Epoch
+      type: Training Epoch
+      value: 3
+    - name: Eval Logits/Chosen
+      type: Evaluation Logits for Chosen Samples
+      value: -2.707406759262085
+    - name: Eval Logits/Rejected
+      type: Evaluation Logits for Rejected Samples
+      value: -2.65652441978546
+    - name: Eval Logps/Chosen
+      type: Evaluation Log-probabilities for Chosen Samples
+      value: -370.129670421875
+    - name: Eval Logps/Rejected
+      type: Evaluation Log-probabilities for Rejected Samples
+      value: -296.073825390625
+    - name: Eval Loss
+      type: Evaluation Loss
+      value: 0.513750433921814
+    - name: Eval Rewards/Accuracies
+      type: Evaluation Rewards and Accuracies
+      value: 0.738095223903656
+    - name: Eval Rewards/Chosen
+      type: Evaluation Rewards for Chosen Samples
+      value: -0.0274422804903984
+    - name: Eval Rewards/Margins
+      type: Evaluation Rewards Margins
+      value: 1.008722543614307
+    - name: Eval Rewards/Rejected
+      type: Evaluation Rewards for Rejected Samples
+      value: -1.03616464138031
+    - name: Eval Runtime
+      type: Evaluation Runtime
+      value: 93.5908
+    - name: Eval Samples
+      type: Number of Evaluation Samples
+      value: 2000
+    - name: Eval Samples per Second
+      type: Evaluation Samples per Second
+      value: 21.37
+    - name: Eval Steps per Second
+      type: Evaluation Steps per Second
+      value: 0.673
+---
+
+# HelpingAI-Lite
+# Subscribe to my YouTube channel
+[Subscribe](https://youtube.com/@OEvortex)
+
+GGUF version [here](https://huggingface.co/OEvortex/HelpingAI-Lite-GGUF)
+
+HelpingAI-Lite is a lite version of the HelpingAI model that can assist with coding tasks. It's trained on a diverse range of datasets and fine-tuned to provide accurate and helpful responses.
+
+## License
+
+This model is licensed under MIT.
+
+## Datasets
+
+The model was trained on the following datasets:
+- cerebras/SlimPajama-627B
+- bigcode/starcoderdata
+- HuggingFaceH4/ultrachat_200k
+- HuggingFaceH4/ultrafeedback_binarized
+
+## Language
+
+The model supports English language.
+
+## Usage
+
+# CPU and GPU code
+
+```python
+from transformers import pipeline
+from accelerate import Accelerator
+
+# Initialize the accelerator
+accelerator = Accelerator()
+
+# Initialize the pipeline
+pipe = pipeline("text-generation", model="OEvortex/HelpingAI-Lite", device=accelerator.device)
+
+# Define the messages
+messages = [
+    {
+        "role": "system",
+        "content": "You are a chatbot who can help code!",
+    },
+    {
+        "role": "user",
+        "content": "Write me a function to calculate the first 10 digits of the fibonacci sequence in Python and print it out to the CLI.",
+    },
+]
+
+# Prepare the prompt
+prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+
+# Generate predictions
+outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+
+# Print the generated text
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e6001da2106d4757498752a021df6c2bdc332c650aae4bae6b0c004dcf14933
+size 2200119864

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|user|>' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ '<|system|>' + message['content'] + eos_token }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>'  + message['content'] + eos_token }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}