Nous-Hermes-2-SUS-Chat-34B-Slerp/README.md

license, tags, license_name, license_link, model-index

license	tags	license_name	license_link	model-index
other	merge	yi-34b	https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE	name results Nous-Hermes-2-SUS-Chat-34B-Slerp 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 66.72 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp 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 84.97 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp 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 77.0 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp 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 59.23 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp 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 83.58 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp 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 72.86 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Slerp Open LLM Leaderboard

Nous-Hermes-2-SUS-Chat-34B-Slerp

This is the model for Nous-Hermes-2-SUS-Chat-34B-Slerp. I used mergekit to merge models.

Prompt Templates

You can use these prompt templates, but I recommend using ChatML.

ChatML (NousResearch/Nous-Hermes-2-Yi-34B):

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

Human - Asistant (SUSTech/SUS-Chat-34B):

### Human: {user}

### Assistant: {asistant}

Yaml Config

slices:
- sources:
    - model: Nous-Hermes-2-Yi-34B
      layer_range: [0, 60]
    - model: SUS-Chat-34B
      layer_range: [0, 60]

merge_method: slerp
base_model: Yi-34B

parameters:
t:
  - filter: self_attn
    value: [0, 0.5, 0.3, 0.7, 1]
  - filter: mlp
    value: [1, 0.5, 0.7, 0.3, 0]
  - value: 0.5
tokenizer_source: union
dtype: bfloat16

Quantizationed versions

Quantizationed versions of this model is available thanks to TheBloke.

GPTQ

• TheBloke/Nous-Hermes-2-SUS-Chat-34B-Slerp-GPTQ

GGUF

• TheBloke/Nous-Hermes-2-SUS-Chat-34B-Slerp-GGUF

AWQ

• TheBloke/Nous-Hermes-2-SUS-Chat-34B-Slerp-AWQ

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	74.06
AI2 Reasoning Challenge (25-Shot)	66.72
HellaSwag (10-Shot)	84.97
MMLU (5-Shot)	77.00
TruthfulQA (0-shot)	59.23
Winogrande (5-shot)	83.58
GSM8k (5-shot)	72.86