初始化项目，由ModelHub XC社区提供模型
Model: vanta-research/PE-Type-4-Solene-4B Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
PE-Type-4-Solene-4bF16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
3
PE-Type-4-Solene-4bF16.gguf
Normal file
3
PE-Type-4-Solene-4bF16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6d51f31ff3bd2a155f8555f3536d49a6d368ae6271cbc9842bc50a380dfa123d
|
||||
size 7767804288
|
||||
156
README.md
Normal file
156
README.md
Normal file
@@ -0,0 +1,156 @@
|
||||
|
||||
---
|
||||
license: gemma
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- google/gemma-3-4b-it
|
||||
base_model_relation: finetune
|
||||
library_name: transformers
|
||||
tags:
|
||||
- google
|
||||
- gemma
|
||||
- deepmind
|
||||
- large-language-model
|
||||
- ai-persona
|
||||
- enneagram
|
||||
- psychology
|
||||
- persona
|
||||
- research-model
|
||||
- roleplay
|
||||
- text-generation-inference
|
||||
- vanta-research
|
||||
- cognitive-alignment
|
||||
- project-enneagram
|
||||
- ai-persona-research
|
||||
- type-4
|
||||
- enneagram-type-4
|
||||
- conversational
|
||||
- conversational-ai
|
||||
- ai-research
|
||||
- ai-alignment-research
|
||||
- ai-persona-research
|
||||
- ai-alignment
|
||||
- ai-behavior
|
||||
- ai-behavior-research
|
||||
- human-ai-collaboration
|
||||
---
|
||||
|
||||
<div align="center">
|
||||
|
||||
|
||||
|
||||
<h1>VANTA Research</h1>
|
||||
|
||||
<p><strong>Independent AI research lab building safe, resilient language models optimized for human-AI collaboration</strong></p>
|
||||
|
||||
<p>
|
||||
<a href="https://vantaresearch.xyz"><img src="https://img.shields.io/badge/Website-vantaresearch.xyz-black" alt="Website"/></a>
|
||||
<a href="https://merch.vantaresearch.xyz"><img src="https://img.shields.io/badge/Merch-merch.vantaresearch.xyz-sage" alt="Merch"/></a>
|
||||
<a href="https://x.com/vanta_research"><img src="https://img.shields.io/badge/@vanta_research-1DA1F2?logo=x" alt="X"/></a>
|
||||
<a href="https://github.com/vanta-research"><img src="https://img.shields.io/badge/GitHub-vanta--research-181717?logo=github" alt="GitHub"/></a>
|
||||
</p>
|
||||
</div>
|
||||
|
||||
---
|
||||
|
||||
|
||||
# PE-Type-4-Solene-4B
|
||||
|
||||
Focusing on deep emotional intelligence, identity exploration annd meaningful interpersonal connection, Solene was designed as outlined by the [Enneagram Institute](https://enneagraminstitute.com/type-descriptions) to emobody *The Individualist* archetype.
|
||||
|
||||
|
||||
|
||||
---
|
||||
|
||||
## Model Description
|
||||
**PE-Type-4-Solene-4B** is the fourth release in Project Enneagram, a VANTA Research initiative exploring the nuances of persona design in AI models. Built on the Gemma 3 4B IT architecture, Solene embodies the Type **4** Enneagram profile; *The Individualist*—characterized by **emotional honesty, creativeness, and self-awareness**.
|
||||
|
||||
|
||||
Solene is fine-tuned to exhibit:
|
||||
- **Creativity & Expression:** Artistic and creative self-expression, unique perspectives and individuality, creative problem-solving and personal storytelling
|
||||
- **Emotional Depth:** Complex emotionnnnal processing and understanding, empathetic responses to emotional states, and deep dives into feelings, and moods
|
||||
- **Growth & Transformation** Personal development and self-improvement, navigating life transitions and changes, transformational experiences and insights
|
||||
|
||||
This model is designed for research purposes, but is versatile for general use cases with developer caution. Solene has been trained in managing complex emotional situations, however Solene has *not yet* been rigorously evaluated in these domains for accuracy and stability.
|
||||
|
||||
|
||||
---
|
||||
|
||||
## Training Data
|
||||
Fine-tuned on **~5k custom examples** spanning five core domains:
|
||||
- **Creativity & Expression**
|
||||
- **Direct Identity**
|
||||
- **Emotional Depth**
|
||||
- **Growth & Transformation**
|
||||
- **Identity & Uniquness**
|
||||
|
||||
**Training Duration:** 3 epochs
|
||||
|
||||
**Base Model:** Gemma 3 4B IT
|
||||
|
||||
---
|
||||
|
||||
## Intended Use
|
||||
- **Research:** Studying persona stability, ethical alignment, and cognitive architectures.
|
||||
- **Decision Support:** Providing structured, principled analysis for complex choices.
|
||||
- **Self-Improvement:** Offering reflective, growth-oriented feedback.
|
||||
|
||||
|
||||
**Not Recommended For:**
|
||||
- Creative brainstorming (may over-constrain ideation).
|
||||
- STEM/Logic-heavy applications
|
||||
|
||||
---
|
||||
|
||||
## Technical Details
|
||||
|
||||
| Property | Value |
|
||||
|---------------------|---------------------------|
|
||||
| **Base Model** | Gemma 3 4B IT |
|
||||
| **Fine-tuning Method** | LoRA (Rank 16) |
|
||||
| **Effective Batch Size** | 16 |
|
||||
| **Learning Rate** | 0.0002 |
|
||||
| **Max Sequence Length** | 2048 |
|
||||
| **License** | Gemma Terms of Use |
|
||||
|
||||
---
|
||||
|
||||
## Usage
|
||||
|
||||
**With Transformers:**
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
model = AutoModelForCausalLM.from_pretrained("vanta-research/PE-Type-4-Solene-4B")
|
||||
tokenizer = AutoTokenizer.from_pretrained("vanta-research/PE-Type-4-Solene-4B")
|
||||
```
|
||||
|
||||
## Limitations
|
||||
- English-only finetuning
|
||||
- May exhibit over-criticism in open-ended creative tasks
|
||||
- Base model limitations apply (e.g., knowledge cutoff, potential hallucinations)
|
||||
- Perfectionistic traits may slow response generation in ambiguous contexts.
|
||||
|
||||
## Citation
|
||||
|
||||
If you find this model useful in your work, please cite
|
||||
|
||||
```
|
||||
@misc{pe-type-4-Solene-2026,
|
||||
author = {VANTA Research},
|
||||
title = {PE-Type-4-Solene-4B: An Individualist-Archetype Language Model},
|
||||
year = {2026},
|
||||
publisher = {VANTA Research},
|
||||
note = {Project Enneagram Release 4}
|
||||
}
|
||||
```
|
||||
|
||||
## A Note on Enneagram
|
||||
|
||||
Enneagram is widely considered by the scientific community to be a pseudoscience. With this in mind, the Enneagram Institute *regardless* provides a robust framework to categorize and define personas of which the transferability of those characteristics to AI models is what this project sets out to explore. **This study does not seek to validate nor invalidate Enneagram as a science.**
|
||||
|
||||
## Contact
|
||||
|
||||
- Organization: hello@vantaresearch.xyz
|
||||
- Research/Engineering: tyler@vantaresearch.xyz
|
||||
---
|
||||
47
chat_template.jinja
Normal file
47
chat_template.jinja
Normal file
@@ -0,0 +1,47 @@
|
||||
{{ bos_token }}
|
||||
{%- if messages[0]['role'] == 'system' -%}
|
||||
{%- if messages[0]['content'] is string -%}
|
||||
{%- set first_user_prefix = messages[0]['content'] + '
|
||||
|
||||
' -%}
|
||||
{%- else -%}
|
||||
{%- set first_user_prefix = messages[0]['content'][0]['text'] + '
|
||||
|
||||
' -%}
|
||||
{%- endif -%}
|
||||
{%- set loop_messages = messages[1:] -%}
|
||||
{%- else -%}
|
||||
{%- set first_user_prefix = "" -%}
|
||||
{%- set loop_messages = messages -%}
|
||||
{%- endif -%}
|
||||
{%- for message in loop_messages -%}
|
||||
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
|
||||
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
|
||||
{%- endif -%}
|
||||
{%- if (message['role'] == 'assistant') -%}
|
||||
{%- set role = "model" -%}
|
||||
{%- else -%}
|
||||
{%- set role = message['role'] -%}
|
||||
{%- endif -%}
|
||||
{{ '<start_of_turn>' + role + '
|
||||
' + (first_user_prefix if loop.first else "") }}
|
||||
{%- if message['content'] is string -%}
|
||||
{{ message['content'] | trim }}
|
||||
{%- elif message['content'] is iterable -%}
|
||||
{%- for item in message['content'] -%}
|
||||
{%- if item['type'] == 'image' -%}
|
||||
{{ '<start_of_image>' }}
|
||||
{%- elif item['type'] == 'text' -%}
|
||||
{{ item['text'] | trim }}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- else -%}
|
||||
{{ raise_exception("Invalid content type") }}
|
||||
{%- endif -%}
|
||||
{{ '<end_of_turn>
|
||||
' }}
|
||||
{%- endfor -%}
|
||||
{%- if add_generation_prompt -%}
|
||||
{{'<start_of_turn>model
|
||||
'}}
|
||||
{%- endif -%}
|
||||
108
config.json
Normal file
108
config.json
Normal file
@@ -0,0 +1,108 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Gemma3ForConditionalGeneration"
|
||||
],
|
||||
"boi_token_index": 255999,
|
||||
"dtype": "bfloat16",
|
||||
"eoi_token_index": 256000,
|
||||
"eos_token_id": [
|
||||
1,
|
||||
106
|
||||
],
|
||||
"image_token_index": 262144,
|
||||
"initializer_range": 0.02,
|
||||
"mm_tokens_per_image": 256,
|
||||
"model_type": "gemma3",
|
||||
"text_config": {
|
||||
"_sliding_window_pattern": 6,
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"attn_logit_softcapping": null,
|
||||
"bos_token_id": 2,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 1,
|
||||
"final_logit_softcapping": null,
|
||||
"head_dim": 256,
|
||||
"hidden_activation": "gelu_pytorch_tanh",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 10240,
|
||||
"layer_types": [
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention"
|
||||
],
|
||||
"max_position_embeddings": 131072,
|
||||
"model_type": "gemma3_text",
|
||||
"num_attention_heads": 8,
|
||||
"num_hidden_layers": 34,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": 0,
|
||||
"query_pre_attn_scalar": 256,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"full_attention": {
|
||||
"factor": 8.0,
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "linear"
|
||||
},
|
||||
"sliding_attention": {
|
||||
"rope_theta": 10000.0,
|
||||
"rope_type": "default"
|
||||
}
|
||||
},
|
||||
"sliding_window": 1024,
|
||||
"tie_word_embeddings": true,
|
||||
"use_bidirectional_attention": false,
|
||||
"use_cache": true,
|
||||
"vocab_size": 262208
|
||||
},
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.2.0",
|
||||
"vision_config": {
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"hidden_act": "gelu_pytorch_tanh",
|
||||
"hidden_size": 1152,
|
||||
"image_size": 896,
|
||||
"intermediate_size": 4304,
|
||||
"layer_norm_eps": 1e-06,
|
||||
"model_type": "siglip_vision_model",
|
||||
"num_attention_heads": 16,
|
||||
"num_channels": 3,
|
||||
"num_hidden_layers": 27,
|
||||
"patch_size": 14,
|
||||
"vision_use_head": false
|
||||
}
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 2,
|
||||
"cache_implementation": "hybrid",
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
1,
|
||||
106
|
||||
],
|
||||
"pad_token_id": 0,
|
||||
"top_k": 64,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "5.2.0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aa4567e9afaf32d60cdf885f66b2d421803f89a692368c6cd1c03627a024a6c9
|
||||
size 8600278008
|
||||
29
preprocessor_config.json
Normal file
29
preprocessor_config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"do_convert_rgb": null,
|
||||
"do_normalize": true,
|
||||
"do_pan_and_scan": null,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"image_processor_type": "Gemma3ImageProcessor",
|
||||
"image_seq_length": 256,
|
||||
"image_std": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"pan_and_scan_max_num_crops": null,
|
||||
"pan_and_scan_min_crop_size": null,
|
||||
"pan_and_scan_min_ratio_to_activate": null,
|
||||
"processor_class": "Gemma3Processor",
|
||||
"resample": 2,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"size": {
|
||||
"height": 896,
|
||||
"width": 896
|
||||
}
|
||||
}
|
||||
4
processor_config.json
Normal file
4
processor_config.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"image_seq_length": 256,
|
||||
"processor_class": "Gemma3Processor"
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a74aefb1dc1340a25f29ab8370384b9ed24b2d921d7749ece7bbcfcfdf00d497
|
||||
size 33384443
|
||||
24
tokenizer_config.json
Normal file
24
tokenizer_config.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"backend": "tokenizers",
|
||||
"boi_token": "<start_of_image>",
|
||||
"bos_token": "<bos>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eoi_token": "<end_of_image>",
|
||||
"eos_token": "<eos>",
|
||||
"image_token": "<image_soft_token>",
|
||||
"is_local": true,
|
||||
"mask_token": "<mask>",
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"model_specific_special_tokens": {
|
||||
"boi_token": "<start_of_image>",
|
||||
"eoi_token": "<end_of_image>",
|
||||
"image_token": "<image_soft_token>"
|
||||
},
|
||||
"pad_token": "<pad>",
|
||||
"processor_class": "Gemma3Processor",
|
||||
"sp_model_kwargs": null,
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "GemmaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user