Minami-su's picture
Adding Evaluation Results
af0293a verified
|
raw
history blame
5.67 kB
metadata
language:
  - en
  - zh
license: other
library_name: transformers
tags:
  - llama
  - qwen
  - qwen1.5
  - qwen2
license_name: qwen
license_link: >-
  https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT
pipeline_tag: text-generation
inference: false
model-index:
  - name: Qwen1.5-7B-Chat_llamafy
    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: 57.59
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Minami-su/Qwen1.5-7B-Chat_llamafy
          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: 78.52
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Minami-su/Qwen1.5-7B-Chat_llamafy
          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: 61.18
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Minami-su/Qwen1.5-7B-Chat_llamafy
          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: 57.59
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Minami-su/Qwen1.5-7B-Chat_llamafy
          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: 66.46
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Minami-su/Qwen1.5-7B-Chat_llamafy
          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: 14.63
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Minami-su/Qwen1.5-7B-Chat_llamafy
          name: Open LLM Leaderboard

This is the LLaMAfied version of Qwen1.5-7B-Chat model by Alibaba Cloud. The original codebase can be found at: (https://github.com/hiyouga/LLaMA-Factory/blob/main/tests/llamafy_qwen.py). I have made modifications to make it compatible with qwen1.5. This model is converted with https://github.com/Minami-su/character_AI_open/blob/main/llamafy_qwen_v2.py

Usage:


from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
tokenizer = AutoTokenizer.from_pretrained("Minami-su/Qwen1.5-7B-Chat_llamafy")
model = AutoModelForCausalLM.from_pretrained("Minami-su/Qwen1.5-7B-Chat_llamafy", torch_dtype="auto", device_map="auto")
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

messages = [
    {"role": "user", "content": "Who are you?"}
]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
inputs = inputs.to("cuda")
generate_ids = model.generate(inputs,max_length=2048, streamer=streamer)

Test

load in 4bit

hf-causal (pretrained=Qwen1.5-7B-Chat), limit: None, provide_description: False, num_fewshot: 0, batch_size: 8
|    Task     |Version| Metric |Value |   |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge|      0|acc     |0.4155|±  |0.0144|
|             |       |acc_norm|0.4480|±  |0.0145|
|truthfulqa_mc|      1|mc1     |0.3513|±  |0.0167|
|             |       |mc2     |0.5165|±  |0.0159|
|winogrande   |      0|acc     |0.6330|±  |0.0135|

load in 4bit

hf-causal (pretrained=Qwen1.5-7B-Chat_llamafy), limit: None, provide_description: False, num_fewshot: 0, batch_size: 8
|    Task     |Version| Metric |Value |   |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge|      0|acc     |0.4172|±  |0.0144|
|             |       |acc_norm|0.4488|±  |0.0145|
|truthfulqa_mc|      1|mc1     |0.3501|±  |0.0167|
|             |       |mc2     |0.5164|±  |0.0159|
|winogrande   |      0|acc     |0.6306|±  |0.0136|
# [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_Minami-su__Qwen1.5-7B-Chat_llamafy)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |56.00|
|AI2 Reasoning Challenge (25-Shot)|57.59|
|HellaSwag (10-Shot)              |78.52|
|MMLU (5-Shot)                    |61.18|
|TruthfulQA (0-shot)              |57.59|
|Winogrande (5-shot)              |66.46|
|GSM8k (5-shot)                   |14.63|