Downloads · 30 days
83
0% of all-time downloads
Weyaxi/Cosmosis-3x34B
Cosmosis-3x34B is a text generation model from Weyaxi. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
Downloads · 30 days
83
0% of all-time downloads
All-time downloads
34.5K
Public
Parameters
87.2B
174 GB on disk
Likes
9
Public
Click a slice to open those files.
.safetensors174 GB · 100%
From the Hugging Face model README

This is the model for Cosmosis-3x34B. I used this repo to make this MOE model.
Since bagel-dpo-34b-v0.2 uses many prompt templates, you can utilize prompt templates provided by bagel and other expert's prompt templates.
Note: I currently do not know which prompt template is best.
<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{user}<|im_end|>
<|im_start|>assistant
{asistant}<|im_end|>
Human: {user}
### Assistant: {asistant}
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{system}
{instruction}
### Response:
{system}
USER: {instruction}
ASSISTANT:
Visit bagel-dpo-34b-v0.2 to try more prompt templates.
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"]
negative_prompts: ["math", "reason", "mathematics", "solve", "count", "code", "python", "javascript", "programming", "algorithm"]
- source_model: Nous-Hermes-2-Yi-34B
positive_prompts: ["chat", "math", "reason", "mathematics", "solve", "count", "python", "javascript", "programming", "algorithm", "tell me", "assistant"]
- source_model: SUS-Chat-34B
positive_prompts: ["math", "reason", "mathematics", "solve", "count", "assistant"]
Quantizationed versions of this model is available thanks to TheBloke.
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 75.39 |
| AI2 Reasoning Challenge (25-Shot) | 69.71 |
| HellaSwag (10-Shot) | 85.18 |
| MMLU (5-Shot) | 77.25 |
| TruthfulQA (0-shot) | 63.82 |
| Winogrande (5-shot) | 84.14 |
| GSM8k (5-shot) | 72.25 |
If you would like to support me: