---
language:
- zh
- en
license: apache-2.0
datasets:
- Azure99/blossom-chat-v3
- Azure99/blossom-math-v4
- Azure99/blossom-wizard-v3
- Azure99/blossom-orca-v3
model-index:
- name: blossom-v5.1-34b
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: ENEM Challenge (No Images)
      type: eduagarcia/enem_challenge
      split: train
      args:
        num_few_shot: 3
    metrics:
    - type: acc
      value: 72.64
      name: accuracy
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Azure99/blossom-v5.1-34b
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BLUEX (No Images)
      type: eduagarcia-temp/BLUEX_without_images
      split: train
      args:
        num_few_shot: 3
    metrics:
    - type: acc
      value: 67.18
      name: accuracy
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Azure99/blossom-v5.1-34b
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: OAB Exams
      type: eduagarcia/oab_exams
      split: train
      args:
        num_few_shot: 3
    metrics:
    - type: acc
      value: 54.44
      name: accuracy
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Azure99/blossom-v5.1-34b
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Assin2 RTE
      type: assin2
      split: test
      args:
        num_few_shot: 15
    metrics:
    - type: f1_macro
      value: 90.88
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Azure99/blossom-v5.1-34b
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Assin2 STS
      type: eduagarcia/portuguese_benchmark
      split: test
      args:
        num_few_shot: 15
    metrics:
    - type: pearson
      value: 82.94
      name: pearson
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Azure99/blossom-v5.1-34b
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: FaQuAD NLI
      type: ruanchaves/faquad-nli
      split: test
      args:
        num_few_shot: 15
    metrics:
    - type: f1_macro
      value: 81.88
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Azure99/blossom-v5.1-34b
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HateBR Binary
      type: ruanchaves/hatebr
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: f1_macro
      value: 85.2
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Azure99/blossom-v5.1-34b
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: PT Hate Speech Binary
      type: hate_speech_portuguese
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: f1_macro
      value: 72.09
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Azure99/blossom-v5.1-34b
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: tweetSentBR
      type: eduagarcia/tweetsentbr_fewshot
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: f1_macro
      value: 72.13
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=Azure99/blossom-v5.1-34b
      name: Open Portuguese LLM Leaderboard
---
# **BLOSSOM-v5.1-34b**

[💻Github](https://github.com/Azure99/BlossomLM) • [🚀Blossom Chat Demo](https://blossom-chat.com/)

### Introduction

Blossom is a conversational large language model, fine-tuned on the Blossom Orca/Wizard/Chat/Math mixed dataset based on the Yi-1.5-34B pre-trained model. Blossom possesses robust general capabilities and context comprehension. Additionally, the high-quality Chinese and English datasets used for training have been made open source.

Training was conducted in two stages. The first stage used 40K Wizard, 40K Orca, 10K Math single-turn instruction datasets, training for 1 epoch; the second stage used 10K Blossom chat multi-turn dialogue dataset, and 10% randomly sampled data from the first stage, training for 3 epochs.

### Inference

Inference is performed in the form of dialogue continuation.

Single-turn dialogue

```
A chat between a human and an artificial intelligence bot. The bot gives helpful, detailed, and polite answers to the human's questions.
|Human|: hello
|Bot|: 
```

Multi-turn dialogue

```
A chat between a human and an artificial intelligence bot. The bot gives helpful, detailed, and polite answers to the human's questions.
|Human|: hello
|Bot|: Hello! How can I assist you today?<|endoftext|>
|Human|: Generate a random number using python
|Bot|: 
```

Note: At the end of the Bot's output in the historical conversation, append a `<|endoftext|>`.


# Open Portuguese LLM Leaderboard Evaluation Results  

Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/Azure99/blossom-v5.1-34b) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)

|          Metric          |  Value  |
|--------------------------|---------|
|Average                   |**75.49**|
|ENEM Challenge (No Images)|    72.64|
|BLUEX (No Images)         |    67.18|
|OAB Exams                 |    54.44|
|Assin2 RTE                |    90.88|
|Assin2 STS                |    82.94|
|FaQuAD NLI                |    81.88|
|HateBR Binary             |    85.20|
|PT Hate Speech Binary     |    72.09|
|tweetSentBR               |    72.13|