license: llama3.1
library_name: transformers
base_model: meta-llama/Meta-Llama-3.1-70B-Instruct
pipeline_tag: text-generation
model-index:
- name: ref_70_e3
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 62.94
name: strict accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mattshumer/ref_70_e3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 49.27
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mattshumer/ref_70_e3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 0
name: exact match
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mattshumer/ref_70_e3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 11.41
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mattshumer/ref_70_e3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 13
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mattshumer/ref_70_e3
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 47.81
name: accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mattshumer/ref_70_e3
name: Open LLM Leaderboard
Reflection Llama-3.1 70B
| IMPORTANT — This is the new, working version of the Reflection Llama 3.1 70B model. Please use this version.
Reflection Llama-3.1 70B is (currently) the world's top open-source LLM, trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.
The model was trained on synthetic data generated by Glaive. If you're training a model, Glaive is incredible — use them.
Benchmarks
All benchmarks tested have been checked for contamination by running LMSys's LLM Decontaminator. When benchmarking, we isolate the <output> and benchmark on solely that section.
Trained from Llama 3.1 70B Instruct, you can sample from Reflection Llama-3.1 70B using the same code, pipelines, etc. as any other Llama model. It even uses the stock Llama 3.1 chat template format (though, we've trained in a few new special tokens to aid in reasoning and reflection).
During sampling, the model will start by outputting reasoning inside <thinking> and </thinking> tags, and then once it is satisfied with its reasoning, it will output the final answer inside <output> and </output> tags. Each of these tags are special tokens, trained into the model.
This enables the model to separate its internal thoughts and reasoning from its final answer, improving the experience for the user.
Inside the <thinking> section, the model may output one or more <reflection> tags, which signals the model has caught an error in its reasoning and will attempt to correct it before providing a final answer.
System Prompt
The system prompt used for training this model is:
You are a world-class AI system, capable of complex reasoning and reflection. Reason through the query inside <thinking> tags, and then provide your final response inside <output> tags. If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags.
We recommend using this exact system prompt to get the best results from Reflection Llama-3.1 70B. You may also want to experiment combining this system prompt with your own custom instructions to customize the behavior of the model.
Chat Format
As mentioned above, the model uses the standard Llama 3.1 chat format. Here’s an example:
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
You are a world-class AI system, capable of complex reasoning and reflection. Reason through the query inside <thinking> tags, and then provide your final response inside <output> tags. If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags.<|eot_id|><|start_header_id|>user<|end_header_id|>
what is 2+2?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Tips for Performance
- We are initially recommending a
temperatureof.7and atop_pof.95. - For increased accuracy, append
Think carefully.at the end of your messages.
Dataset / Report
Both the dataset and a brief report detailing how we trained this model will be released next week, alongside our Reflection 405B model that we expect will be the top-performing LLM in the world, including closed-source models.
Thanks to Jason Kuperberg and Josh Bickett from the HyperWrite team for reviewing drafts of the report we'll be releasing next week.
Also, we know right now the model is split into a ton of files. We'll condense this soon to make the model easier to download and work with!
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 30.74 |
| IFEval (0-Shot) | 62.94 |
| BBH (3-Shot) | 49.27 |
| MATH Lvl 5 (4-Shot) | 0.00 |
| GPQA (0-shot) | 11.41 |
| MuSR (0-shot) | 13.00 |
| MMLU-PRO (5-shot) | 47.81 |