bwx-7B-hf

Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

This is an experimental product that can be used to create new LLM bassed on Chinese language.

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

• Developed by: yjf9966
• Model type: LLaMA with enhanced tokenizer-size-49954
• Language(s) (NLP): Chinese
• License: Apache-2.0
• Finetuned from model: Chinese-LLaMA-Alpaca

Model Sources [optional]

<!-- Provide the basic links for the model. -->

• Repository: https://huggingface.co/BlueWhaleX/bwx-7B-HF

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

You can use the raw model for next sentence prediction, but it's mostly intended to be fine-tuned on a downstream task. Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked) to make decisions, such as sequence classification, token classification or question answering.

Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

Even if the training data used for this model could be characterized as fairly neutral, this model can have biased predictions. It also inherits some of the bias of its dataset model.

Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import LlamaForCausalLM, LlamaTokenizer
import torch

base_model_name = "BlueWhaleX/bwx-7B-hf"
load_type = torch.float16
device = None

generation_config = dict(
    temperature=0.2,
    top_k=40,
    top_p=0.9,
    do_sample=True,
    num_beams=1,
    repetition_penalty=1.3,
    max_new_tokens=400
    )

prompt_input = (
    "Below is an instruction that describes a task. "
    "Write a response that appropriately completes the request.\n\n"
    "### Instruction:\n\n{instruction}\n\n### Response:\n\n"
)
if torch.cuda.is_available():
    device = torch.device(0)
else:
    device = torch.device('cpu')

def generate_prompt(instruction, input=None):
    if input:
        instruction = instruction + '\n' + input
    return prompt_input.format_map({'instruction': instruction})

tokenizer = LlamaTokenizer.from_pretrained(base_model_name)
model = LlamaForCausalLM.from_pretrained(
        base_model_name,
        load_in_8bit=False,
        torch_dtype=load_type,
        low_cpu_mem_usage=True,
        device_map='auto',
        )

model_vocab_size = model.get_input_embeddings().weight.size(0)
tokenzier_vocab_size = len(tokenizer)
if model_vocab_size != tokenzier_vocab_size:
    model.resize_token_embeddings(tokenzier_vocab_size)

raw_input_text = input("Input:")
input_text = generate_prompt(instruction=raw_input_text)
inputs = tokenizer(input_text, return_tensors="pt") 
generation_output = model.generate(
input_ids=inputs["input_ids"].to(device),
    attention_mask=inputs['attention_mask'].to(device),
    eos_token_id=tokenizer.eos_token_id,
    pad_token_id=tokenizer.pad_token_id,
    **generation_config
)
s = generation_output[0]
output = tokenizer.decode(s, skip_special_tokens=True)
response = output.split("### Response:")[1].strip()
print("Response: ", response)
print("\n")

Training Details

Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

Preprocessing [optional]

80% for train dataset and 20% for test dataset

Training Hyperparameters

• Training regime: fp16 mixed precision, lr=1e-4, lora_rank=8, lora_alpha=32 <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

Evaluation

Testing Data

<!-- This should link to a Data Card if possible. -->

20% of the BAAI/COIG-PC dataset.

Input:王国维说：“自周之衰，文王、周公势力之瓦解也，国民之智力成熟于内，政治之纷乱乘之于外，上无统一之制度，下迫于社会之要求，于是诸于九流各创其学说。” 他意在说明 A. 分封制的崩溃 B. 商鞅变法的作用 C. 兼并战争的后果 D. 百家争鸣的原因
Response:  本题考查对材料的理解。A错误；B正确；C和D与材料无关。故选BC两项即可


Input:经济基础是指一定社会发展阶段占统治地位的生产关系各个方面的总和。解决了地方经济问题， 也就解 决了地方割据问题， 为此， 宋太祖采取的措施是（ ） A ． 地方设转运使， 财赋收归中央 B ． 派文臣担任各地州县的长官 C ． 派文臣管理地方政事 D ． 采取分化事权办法， 削弱相权
Response:  A： 本题考查对宋太祖治下地方问题的认识。 A : 依据材料可知, 在北宋时期 , 由于地主阶级的发展壮大以及商业、手工业等新兴行业出现 , 这一时期出现的地方割据现象严重威胁着国家的统一与稳定 . 因此 , 为了解决这个问题， 需要加强中央集权 ; 故选 A


Input:go\\n/**\\n * Definition for a binary tree node.\\n * type TreeNode struct {\\n *     Val int\\n *     Left *TreeNode\\n *     Right *TreeNode\\n * }\\n */\\nfunc maxDepth(root *TreeNode) int {\\n\\tif root == nil {\\n\\t\\treturn 0\\n\\t}\\n\\tl, r := maxDepth(root.Left), maxDepth(root.Right)\\n\\treturn 1 + max(l, r)\\n}\\n\\nfunc max(a, b int) int {\\n\\tif a > b {\\n\\t\\treturn a\\n\\t}\\n\\treturn b\\n}\\n
Response:  ```python
def max_depth(root):  # The function takes in a single parameter `root` and returns its maximum depth value as output.
    if not root or len(root.children()) == 0:
        return 0
    l = max_depth(root.left)
    r = max_depth(root.right)
    return 1 + (max(l, r))

class TreeNode:
    def __init__(self, val=None, left=10, right=0):
        self.val = val
        self.left = None
        self.right = None

Citation

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

@software{bwx-7B-HF,
      title={An Enchanced Chinese Language Model based on the Chinese-LLaMA-Alpaca}, 
      url={https://huggingface.co/BlueWhaleX/bwx-7B-HF},
      year={2023}
}