CoolFace
Modelpublic

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

sourceHugging Faceotherupdated 3y agoView on Hugging Face
1likes8.6kdownloads
Model Card

image/png

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

yaml

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
GGUF
AWQ

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

MetricValue
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