README.md

license	tags	license_name	license_link	model-index
other	yi moe	yi-license	https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE	name results Bagel-Hermes-2x34b task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 69.8 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Bagel-Hermes-2x34b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 85.26 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Bagel-Hermes-2x34b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 77.24 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Bagel-Hermes-2x34b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 64.82 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Bagel-Hermes-2x34b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 84.77 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Bagel-Hermes-2x34b Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 68.69 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Bagel-Hermes-2x34b Open LLM Leaderboard

Bagel-Hermes-2x34B

This is the model for Bagel-Hermes-2x34B. I used this repo to make this MOE model.

Prompt Template(s):

Since bagel-dpo-34b-v0.2 uses many prompt templates, and Nous-Hermes-2-Yi-34B uses ChatML, you can utilize ChatML and other prompt templates provided by bagel.

Note: I currently do not know which prompt template is best.

ChatML:

<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{user}<|im_end|>
<|im_start|>assistant
{asistant}<|im_end|>

Alpaca (sort of)

Below is an instruction that describes a task.  Write a response that appropriately completes the request.

### Instruction:
{system}
{instruction}

### Response:

Vicuna

{system}
USER: {instruction}
ASSISTANT: 

Visit bagel-dpo-34b-v0.2 to try more prompt templates.

Yaml Config to reproduce

base_model: nontoxic-bagel-34b-v0.2
gate_mode: hidden
dtype: bfloat16

experts:
  - source_model: bagel-dpo-34b-v0.2
    positive_prompts: ["question answering", "Q:", science", "biology", "chemistry", "physics"]

  - source_model: Nous-Hermes-2-Yi-34B
    positive_prompts: ["chat", "math", "reason", "mathematics", "solve", "count", "python", "javascript", "programming", "algorithm", "tell me", "assistant"]

Quantizationed versions

Quantizationed versions of this model is available thanks to TheBloke.

GPTQ

• TheBloke/Bagel-Hermes-2x34B-GPTQ

GGUF

• TheBloke/Bagel-Hermes-2x34B-GGUF

AWQ

• TheBloke/Bagel-Hermes-2x34B-AWQ

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	75.10
AI2 Reasoning Challenge (25-Shot)	69.80
HellaSwag (10-Shot)	85.26
MMLU (5-Shot)	77.24
TruthfulQA (0-shot)	64.82
Winogrande (5-shot)	84.77
GSM8k (5-shot)	68.69

If you would like to support me:

☕ Buy Me a Coffee