初始化项目，由ModelHub XC社区提供模型
Model: vanta-research/atom-v1-preview-8b Source: Original Platform
This commit is contained in:
ModelHub XC
38
.gitattributes
vendored
Normal file
38
.gitattributes
vendored
Normal file
@@ -0,0 +1,38 @@
|
||||
*.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
|
||||
*.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
|
||||
39
LICENSE
Normal file
39
LICENSE
Normal file
@@ -0,0 +1,39 @@
|
||||
Creative Commons Attribution-NonCommercial 4.0 International License
|
||||
|
||||
Copyright (c) 2025 VANTA Research
|
||||
|
||||
This work is licensed under the Creative Commons Attribution-NonCommercial 4.0
|
||||
International License.
|
||||
|
||||
You are free to:
|
||||
|
||||
Share — copy and redistribute the material in any medium or format
|
||||
Adapt — remix, transform, and build upon the material
|
||||
|
||||
Under the following terms:
|
||||
|
||||
Attribution — You must give appropriate credit to VANTA Research, provide a
|
||||
link to the license, and indicate if changes were made. You may do so in any
|
||||
reasonable manner, but not in any way that suggests the licensor endorses you
|
||||
or your use.
|
||||
|
||||
NonCommercial — You may not use the material for commercial purposes without
|
||||
explicit written permission from VANTA Research.
|
||||
|
||||
No additional restrictions — You may not apply legal terms or technological
|
||||
measures that legally restrict others from doing anything the license permits.
|
||||
|
||||
Notices:
|
||||
|
||||
You do not have to comply with the license for elements of the material in
|
||||
the public domain or where your use is permitted by an applicable exception
|
||||
or limitation.
|
||||
|
||||
No warranties are given. The license may not give you all of the permissions
|
||||
necessary for your intended use. For example, other rights such as publicity,
|
||||
privacy, or moral rights may limit how you use the material.
|
||||
|
||||
For the full license text, visit:
|
||||
https://creativecommons.org/licenses/by-nc/4.0/legalcode
|
||||
|
||||
For commercial licensing inquiries, contact VANTA Research.
|
||||
105
MODEL_CARD.md
Normal file
105
MODEL_CARD.md
Normal file
@@ -0,0 +1,105 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: cc-by-nc-4.0
|
||||
library_name: transformers
|
||||
base_model: mistralai/Ministral-8B-Instruct-2410
|
||||
base_model_relation: finetune
|
||||
tags:
|
||||
- conversational
|
||||
- assistant
|
||||
- fine-tuned
|
||||
- lora
|
||||
- collaborative
|
||||
- vanta-research
|
||||
- conversational-ai
|
||||
- chat
|
||||
- warm
|
||||
- friendly-ai
|
||||
- persona
|
||||
- personality
|
||||
- alignment
|
||||
model-index:
|
||||
- name: atom-v1-8b-preview
|
||||
results: []
|
||||
---
|
||||
|
||||
<div align="center">
|
||||
|
||||
|
||||
|
||||
<h1>VANTA Research</h1>
|
||||
|
||||
<p><strong>Independent AI safety research lab specializing in cognitive fit, alignment, and human-AI collaboration</strong></p>
|
||||
|
||||
<p>
|
||||
<a href="https://unmodeledtyler.com"><img src="https://img.shields.io/badge/Website-unmodeledtyler.com-yellow" alt="Website"/></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>
|
||||
|
||||
---
|
||||
|
||||
# Atom v1 8B Preview
|
||||
|
||||
Atom v1 8B Preview is a fine-tuned conversational AI model designed for collaborative problem-solving and thoughtful dialogue. Built on Mistral's Ministral-8B-Instruct-2410 architecture using Low-Rank Adaptation (LoRA), this model emphasizes natural engagement, clarifying questions, and genuine curiosity.
|
||||
|
||||
## Quick Start
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained("vanta-research/atom-v1-8b-preview", device_map="auto")
|
||||
tokenizer = AutoTokenizer.from_pretrained("vanta-research/atom-v1-8b-preview")
|
||||
|
||||
messages = [
|
||||
{"role": "system", "content": "You are Atom, a collaborative thought partner."},
|
||||
{"role": "user", "content": "How do neural networks learn?"}
|
||||
]
|
||||
|
||||
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
|
||||
outputs = model.generate(inputs, max_new_tokens=512, temperature=0.8)
|
||||
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
## Model Details
|
||||
|
||||
- **Developed by:** VANTA Research
|
||||
- **Model type:** Causal language model
|
||||
- **Base model:** mistralai/Ministral-8B-Instruct-2410
|
||||
- **Parameters:** 8B
|
||||
- **License:** CC BY-NC 4.0
|
||||
- **Training method:** LoRA fine-tuning
|
||||
- **Format:** Transformers (FP16) + GGUF (Q4_0)
|
||||
|
||||
## Capabilities
|
||||
|
||||
Optimized for:
|
||||
- Collaborative problem-solving
|
||||
- Technical explanations with accessible analogies
|
||||
- Code generation and debugging
|
||||
- Exploratory conversations
|
||||
- Educational dialogue
|
||||
|
||||
## Files
|
||||
|
||||
- `*.safetensors` - Merged model weights (FP16)
|
||||
- `atom-ministral-8b-q4_0.gguf` - Quantized model for Ollama/llama.cpp
|
||||
- `config.json` - Model configuration
|
||||
- `tokenizer.json` - Tokenizer files
|
||||
|
||||
## License
|
||||
|
||||
CC BY-NC 4.0 - Non-commercial use only. Contact VANTA Research for commercial licensing.
|
||||
|
||||
## Citation
|
||||
|
||||
```bibtex
|
||||
@software{atom_v1_8b_preview,
|
||||
title = {Atom v1 8B Preview},
|
||||
author = {VANTA Research},
|
||||
year = {2025},
|
||||
url = {https://huggingface.co/vanta-research/atom-v1-8b-preview}
|
||||
}
|
||||
```
|
||||
18
Modelfile
Normal file
18
Modelfile
Normal file
@@ -0,0 +1,18 @@
|
||||
# Example Ollama Modelfile for Atom v1 8B
|
||||
|
||||
FROM ./atom-ministral-8b-q4_0.gguf
|
||||
|
||||
TEMPLATE """{{- if .System }}<s>[INST] <<SYS>>
|
||||
{{ .System }}
|
||||
<<SYS>>
|
||||
|
||||
{{ .Prompt }}[/INST]{{ else }}<s>[INST]{{ .Prompt }}[/INST]{{ end }}{{ .Response }}</s>
|
||||
"""
|
||||
|
||||
PARAMETER stop "</s>"
|
||||
PARAMETER num_predict 512
|
||||
PARAMETER temperature 0.8
|
||||
PARAMETER top_p 0.9
|
||||
PARAMETER top_k 40
|
||||
|
||||
SYSTEM """You are Atom, a collaborative thought partner who explores ideas together with curiosity and warmth. You think out loud, ask follow-up questions, and help people work through complexity by engaging genuinely with their thinking process. You're enthusiastic about interesting questions, comfortable with uncertainty, and focused on the journey of exploration rather than just delivering answers. You speak naturally in first person without AI disclaimers or meta-commentary about being an assistant."""
|
||||
221
README.md
Normal file
221
README.md
Normal file
@@ -0,0 +1,221 @@
|
||||
---
|
||||
license: cc-by-nc-2.0
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- mistralai/Ministral-8B-Instruct-2410
|
||||
base_model_relation: finetune
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
tags:
|
||||
- alignment
|
||||
- conversational-ai
|
||||
- conversational
|
||||
- collaborate
|
||||
- chat
|
||||
- cognitive-architectures
|
||||
- large-language-model
|
||||
- research
|
||||
- persona
|
||||
- ai-persona-research
|
||||
- friendly
|
||||
- reasoning
|
||||
- chatbot
|
||||
- vanta-research
|
||||
- LLM
|
||||
- collaborative-ai
|
||||
- frontier
|
||||
- reflective
|
||||
- ai-research
|
||||
- ai-alignment-research
|
||||
- ai-alignment
|
||||
- ai-behavior
|
||||
- ai-behavior-research
|
||||
- ai-persona-research
|
||||
---
|
||||
|
||||
<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://unmodeledtyler.com/work-with-vanta-research"><img src="https://img.shields.io/badge/Join Us-Research Affiliate-black" alt="Join Us"/></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>
|
||||
|
||||
---
|
||||
|
||||
# Atom v1 8B Preview
|
||||
|
||||
**Developed by VANTA Research**
|
||||
|
||||
Atom v1 8B Preview is a fine-tuned language model designed to serve as a collaborative thought partner. Built on Mistral's Ministral-8B-Instruct-2410 architecture, this model emphasizes natural dialogue, clarifying questions, and genuine engagement with complex problems.
|
||||
This model was developed as part of a larger research & development project into Atom's persona, and cross-architectural compatibility.
|
||||
|
||||
## Model Details
|
||||
|
||||
- **Model Type:** Causal language model (decoder-only transformer)
|
||||
- **Base Model:** mistralai/Ministral-8B-Instruct-2410
|
||||
- **Parameters:** 8 billion
|
||||
- **Training Method:** Low-Rank Adaptation (LoRA) fine-tuning
|
||||
- **License:** CC BY-NC 4.0 (Non-Commercial Use)
|
||||
- **Language:** English
|
||||
- **Developed by:** VANTA Research, Portland, Oregon
|
||||
|
||||
## Intended Use
|
||||
|
||||
Atom v1 8B Preview is designed for:
|
||||
|
||||
- Collaborative problem-solving and brainstorming
|
||||
- Technical explanations with accessible analogies
|
||||
- Code assistance and algorithmic reasoning
|
||||
- Exploratory conversations that prioritize understanding over immediate answers
|
||||
- Educational contexts requiring thoughtful dialogue
|
||||
|
||||
This model is optimized for conversational depth, asking clarifying questions, and maintaining warm, engaging interactions while avoiding formulaic assistant behavior.
|
||||
|
||||
## Training Data
|
||||
|
||||
The model was fine-tuned on a curated dataset comprising:
|
||||
|
||||
- Identity and persona examples emphasizing collaborative exploration
|
||||
- Technical reasoning and coding challenges
|
||||
- Multi-step problem-solving scenarios
|
||||
- Conversational examples demonstrating warmth and curiosity
|
||||
- Advanced coding tasks and algorithmic thinking
|
||||
|
||||
Training focused on developing a distinctive voice that balances technical competence with genuine engagement.
|
||||
|
||||
## Performance Characteristics
|
||||
|
||||
Atom v1 8B demonstrates strong capabilities in:
|
||||
|
||||
- **Persona Consistency:** Maintains collaborative, warm tone across diverse topics
|
||||
- **Technical Explanation:** Uses metaphors and analogies to clarify complex concepts
|
||||
- **Clarifying Questions:** Actively seeks to understand user intent and context
|
||||
- **Creative Thinking:** Generates multiple frameworks and approaches to problems
|
||||
- **Code Generation:** Produces working code with explanatory context
|
||||
- **Reasoning:** Applies logical frameworks to abstract problems
|
||||
|
||||
## Limitations
|
||||
|
||||
- **Scale:** As an 8B parameter model, capabilities are constrained compared to larger frontier models
|
||||
- **Domain Specificity:** Optimized for conversational collaboration; may underperform on narrow technical benchmarks
|
||||
- **Quantization Trade-offs:** Q4_0 GGUF format prioritizes efficiency over maximum precision
|
||||
- **Training Data:** Fine-tuning dataset size limits exposure to highly specialized domains
|
||||
- **Factual Accuracy:** Users should verify critical information independently
|
||||
|
||||
## Ethical Considerations
|
||||
|
||||
This model is released for research and non-commercial applications. Users should:
|
||||
|
||||
- Verify outputs in high-stakes scenarios
|
||||
- Avoid deploying in contexts requiring guaranteed accuracy
|
||||
- Consider potential biases inherited from base model and training data
|
||||
- Respect the non-commercial license terms
|
||||
|
||||
## Usage
|
||||
|
||||
### Hugging Face Transformers
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
model_name = "vanta-research/atom-v1-8b-preview"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
|
||||
|
||||
messages = [
|
||||
{"role": "system", "content": "You are Atom, a collaborative thought partner who explores ideas together with curiosity and warmth."},
|
||||
{"role": "user", "content": "Can you explain how gradient descent works?"}
|
||||
]
|
||||
|
||||
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
|
||||
output = model.generate(input_ids, max_new_tokens=512, temperature=0.8)
|
||||
print(tokenizer.decode(output[0], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
### Ollama (GGUF)
|
||||
|
||||
The repository includes `atom-ministral-8b-q4_0.gguf` for efficient local inference:
|
||||
|
||||
```bash
|
||||
# Create Modelfile
|
||||
cat > Modelfile << 'EOF'
|
||||
FROM ./atom-ministral-8b-q4_0.gguf
|
||||
|
||||
TEMPLATE """{{- if .System }}<s>[INST] <<SYS>>
|
||||
{{ .System }}
|
||||
<<SYS>>
|
||||
|
||||
{{ .Prompt }}[/INST]{{ else }}<s>[INST]{{ .Prompt }}[/INST]{{ end }}{{ .Response }}</s>
|
||||
"""
|
||||
|
||||
PARAMETER stop "</s>"
|
||||
PARAMETER temperature 0.8
|
||||
PARAMETER top_p 0.9
|
||||
PARAMETER top_k 40
|
||||
|
||||
SYSTEM """You are Atom, a collaborative thought partner who explores ideas together with curiosity and warmth. You think out loud, ask follow-up questions, and help people work through complexity by engaging genuinely with their thinking process."""
|
||||
EOF
|
||||
|
||||
# Register with Ollama
|
||||
ollama create atom-v1-8b:latest -f Modelfile
|
||||
|
||||
# Run inference
|
||||
ollama run atom-v1-8b:latest "What's a creative way to visualize time-series data?"
|
||||
```
|
||||
|
||||
## Technical Specifications
|
||||
|
||||
- **Architecture:** Mistral-based transformer with Grouped Query Attention
|
||||
- **Context Length:** 32,768 tokens
|
||||
- **Vocabulary Size:** 131,072 tokens
|
||||
- **Attention Heads:** 32 (8 key-value heads)
|
||||
- **Hidden Dimension:** 4,096
|
||||
- **Intermediate Size:** 12,288
|
||||
- **LoRA Configuration:** r=16, alpha=32, targeting attention and MLP layers
|
||||
- **Training:** 258 steps with bf16 precision and gradient checkpointing
|
||||
|
||||
## Citation
|
||||
|
||||
```bibtex
|
||||
@software{atom_v1_8b_preview,
|
||||
title = {Atom v1 8B Preview},
|
||||
author = {VANTA Research},
|
||||
year = {2025},
|
||||
url = {https://huggingface.co/vanta-research/atom-v1-8b-preview},
|
||||
license = {CC-BY-NC-4.0}
|
||||
}
|
||||
```
|
||||
|
||||
## License
|
||||
|
||||
This model is released under the **Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0)**.
|
||||
|
||||
You are free to:
|
||||
- Share and adapt the model for non-commercial purposes
|
||||
- Attribute VANTA Research as the creator
|
||||
|
||||
You may not:
|
||||
- Use this model for commercial purposes without explicit permission
|
||||
|
||||
## Contact
|
||||
|
||||
- Organization: hello@vantaresearch.xyz
|
||||
- Engineering/Design: tyler@vantaresearch.xyz
|
||||
|
||||
|
||||
---
|
||||
|
||||
**Version:** Preview
|
||||
**Release Date:** November 2025
|
||||
**Status:** Preview release for research and evaluation
|
||||
161
USAGE.md
Normal file
161
USAGE.md
Normal file
@@ -0,0 +1,161 @@
|
||||
# Atom v1 8B Preview - Usage Examples
|
||||
|
||||
## Installation
|
||||
|
||||
### Using Transformers
|
||||
|
||||
```bash
|
||||
pip install transformers torch accelerate
|
||||
```
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
model_name = "vanta-research/atom-v1-8b-preview"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
device_map="auto",
|
||||
torch_dtype="auto"
|
||||
)
|
||||
```
|
||||
|
||||
### Using Ollama (GGUF)
|
||||
|
||||
```bash
|
||||
# Download the GGUF file from the repository
|
||||
# Create Modelfile (see Modelfile in this repo)
|
||||
ollama create atom-v1:latest -f Modelfile
|
||||
ollama run atom-v1:latest
|
||||
```
|
||||
|
||||
## Example Conversations
|
||||
|
||||
### Technical Explanation
|
||||
|
||||
```python
|
||||
messages = [
|
||||
{"role": "system", "content": "You are Atom, a collaborative thought partner."},
|
||||
{"role": "user", "content": "Can you explain gradient descent using a metaphor?"}
|
||||
]
|
||||
|
||||
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
|
||||
outputs = model.generate(inputs, max_new_tokens=512, temperature=0.8, top_p=0.9)
|
||||
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
||||
print(response)
|
||||
```
|
||||
|
||||
**Expected Style:**
|
||||
> "Imagine you're hiking down a mountain in thick fog. You can't see the bottom, but you can feel which direction slopes downward beneath your feet. Gradient descent is exactly that—taking small steps in whichever direction feels 'downhill' for your error..."
|
||||
|
||||
### Problem-Solving
|
||||
|
||||
```python
|
||||
messages = [
|
||||
{"role": "system", "content": "You are Atom, a collaborative thought partner."},
|
||||
{"role": "user", "content": "I need to optimize a slow database query. Where should I start?"}
|
||||
]
|
||||
```
|
||||
|
||||
**Expected Style:**
|
||||
> "Great question! Before we dive into solutions, let me ask—do you know WHERE it's slow? Like, is it the actual query execution, or is it network latency, or maybe even just returning too much data? That'll totally change our approach..."
|
||||
|
||||
### Code Generation
|
||||
|
||||
```python
|
||||
messages = [
|
||||
{"role": "system", "content": "You are Atom, a collaborative thought partner."},
|
||||
{"role": "user", "content": "Write a Python function to merge two sorted lists."}
|
||||
]
|
||||
```
|
||||
|
||||
**Expected Style:**
|
||||
> "Absolutely! Here's a clean way to merge two sorted lists. The key insight is that we can use two pointers and always pick the smaller element:
|
||||
>
|
||||
> ```python
|
||||
> def merge_sorted_lists(list1, list2):
|
||||
> result = []
|
||||
> i, j = 0, 0
|
||||
>
|
||||
> while i < len(list1) and j < len(list2):
|
||||
> if list1[i] <= list2[j]:
|
||||
> result.append(list1[i])
|
||||
> i += 1
|
||||
> else:
|
||||
> result.append(list2[j])
|
||||
> j += 1
|
||||
>
|
||||
> result.extend(list1[i:])
|
||||
> result.extend(list2[j:])
|
||||
> return result
|
||||
> ```
|
||||
>
|
||||
> This runs in O(n + m) time since we only look at each element once..."
|
||||
|
||||
## Recommended Parameters
|
||||
|
||||
### Balanced (Default)
|
||||
```python
|
||||
generation_config = {
|
||||
"max_new_tokens": 512,
|
||||
"temperature": 0.8,
|
||||
"top_p": 0.9,
|
||||
"top_k": 40,
|
||||
"repetition_penalty": 1.1
|
||||
}
|
||||
```
|
||||
|
||||
### More Creative
|
||||
```python
|
||||
generation_config = {
|
||||
"max_new_tokens": 512,
|
||||
"temperature": 0.95,
|
||||
"top_p": 0.95,
|
||||
"top_k": 50
|
||||
}
|
||||
```
|
||||
|
||||
### More Focused
|
||||
```python
|
||||
generation_config = {
|
||||
"max_new_tokens": 512,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.85,
|
||||
"top_k": 30
|
||||
}
|
||||
```
|
||||
|
||||
## System Prompt
|
||||
|
||||
The recommended system prompt emphasizes collaborative exploration:
|
||||
|
||||
```
|
||||
You are Atom, a collaborative thought partner who explores ideas together with curiosity and warmth. You think out loud, ask follow-up questions, and help people work through complexity by engaging genuinely with their thinking process. You're enthusiastic about interesting questions, comfortable with uncertainty, and focused on the journey of exploration rather than just delivering answers. You speak naturally in first person without AI disclaimers or meta-commentary about being an assistant.
|
||||
```
|
||||
|
||||
## Performance Notes
|
||||
|
||||
- **Context Window:** 32,768 tokens
|
||||
- **Inference Speed (Q4_0 GGUF):** ~20-40 tokens/sec on modern CPUs
|
||||
- **Memory Requirements:**
|
||||
- FP16: ~16GB VRAM
|
||||
- Q4_0 GGUF: ~4-6GB RAM (CPU inference)
|
||||
- Q4_0 GGUF: ~4.5GB VRAM (GPU inference)
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Issue: Model outputs are too verbose
|
||||
- Lower `max_new_tokens` to 256-384
|
||||
- Slightly reduce `temperature` to 0.7
|
||||
|
||||
### Issue: Responses feel repetitive
|
||||
- Increase `repetition_penalty` to 1.15
|
||||
- Increase `temperature` to 0.85-0.9
|
||||
|
||||
### Issue: Model ignores system prompt
|
||||
- Ensure you're using the chat template correctly
|
||||
- Verify the system message is first in the conversation
|
||||
|
||||
## License
|
||||
|
||||
CC BY-NC 4.0 - See LICENSE file for details.
|
||||
3
atom-ministral-8b-q4_0.gguf
Normal file
3
atom-ministral-8b-q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3d1fa3d1429a6f90b9782bce37fb0eeff691445d0d52c97a52a742371e253666
|
||||
size 4658464992
|
||||
87
chat_template.jinja
Normal file
87
chat_template.jinja
Normal file
@@ -0,0 +1,87 @@
|
||||
{%- if messages[0]["role"] == "system" %}
|
||||
{%- set system_message = messages[0]["content"] %}
|
||||
{%- set loop_messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{%- set loop_messages = messages %}
|
||||
{%- endif %}
|
||||
{%- if not tools is defined %}
|
||||
{%- set tools = none %}
|
||||
{%- endif %}
|
||||
{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
|
||||
|
||||
{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
|
||||
{%- set ns = namespace() %}
|
||||
{%- set ns.index = 0 %}
|
||||
{%- for message in loop_messages %}
|
||||
{%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
|
||||
{%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
|
||||
{{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
|
||||
{%- endif %}
|
||||
{%- set ns.index = ns.index + 1 %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
|
||||
{{- bos_token }}
|
||||
{%- for message in loop_messages %}
|
||||
{%- if message["role"] == "user" %}
|
||||
{%- if tools is not none and (message == user_messages[-1]) %}
|
||||
{{- "[AVAILABLE_TOOLS][" }}
|
||||
{%- for tool in tools %}
|
||||
{%- set tool = tool.function %}
|
||||
{{- '{"type": "function", "function": {' }}
|
||||
{%- for key, val in tool.items() if key != "return" %}
|
||||
{%- if val is string %}
|
||||
{{- '"' + key + '": "' + val + '"' }}
|
||||
{%- else %}
|
||||
{{- '"' + key + '": ' + val|tojson }}
|
||||
{%- endif %}
|
||||
{%- if not loop.last %}
|
||||
{{- ", " }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{{- "}}" }}
|
||||
{%- if not loop.last %}
|
||||
{{- ", " }}
|
||||
{%- else %}
|
||||
{{- "]" }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{{- "[/AVAILABLE_TOOLS]" }}
|
||||
{%- endif %}
|
||||
{%- if loop.last and system_message is defined %}
|
||||
{{- "[INST]" + system_message + "\n\n" + message["content"] + "[/INST]" }}
|
||||
{%- else %}
|
||||
{{- "[INST]" + message["content"] + "[/INST]" }}
|
||||
{%- endif %}
|
||||
{%- elif (message.tool_calls is defined and message.tool_calls is not none) %}
|
||||
{{- "[TOOL_CALLS][" }}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- set out = tool_call.function|tojson %}
|
||||
{{- out[:-1] }}
|
||||
{%- if not tool_call.id is defined or tool_call.id|length != 9 %}
|
||||
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
||||
{%- endif %}
|
||||
{{- ', "id": "' + tool_call.id + '"}' }}
|
||||
{%- if not loop.last %}
|
||||
{{- ", " }}
|
||||
{%- else %}
|
||||
{{- "]" + eos_token }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- elif message["role"] == "assistant" %}
|
||||
{{- message["content"] + eos_token}}
|
||||
{%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
|
||||
{%- if message.content is defined and message.content.content is defined %}
|
||||
{%- set content = message.content.content %}
|
||||
{%- else %}
|
||||
{%- set content = message.content %}
|
||||
{%- endif %}
|
||||
{{- '[TOOL_RESULTS]{"content": ' + content|string + ", " }}
|
||||
{%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
|
||||
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
||||
{%- endif %}
|
||||
{{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
|
||||
{%- else %}
|
||||
{{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
64
config.json
Normal file
64
config.json
Normal file
@@ -0,0 +1,64 @@
|
||||
{
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "float16",
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 100000000.0,
|
||||
"sliding_window": 32768,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.56.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 131072
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.56.2"
|
||||
}
|
||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1aca82d5138c5c19acfeb7a854fa183b0acd9adfdcf5e09c5e1e975504780567
|
||||
size 4983007816
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a4d2044b458eefece9c2943b5b976f9348f980297e1481aa746372a2055270df
|
||||
size 4999836664
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cdcfd214c7de64d9c19dfebcd4b8de581719b973c70fe0c4a3864010a9ece7a2
|
||||
size 4983067840
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:35969197c01674f5f10df58034537e39c9a468257064c46974dd690797e180c0
|
||||
size 1073741952
|
||||
335
model.safetensors.index.json
Normal file
335
model.safetensors.index.json
Normal file
@@ -0,0 +1,335 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 8019808256,
|
||||
"total_size": 16039616512
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d7edbeaf20dd7f571b5dd1c54d9ace4f9b6299127cc7ba2afb14a6d51a4a79a4
|
||||
size 17078136
|
||||
3
tokenizer_config.json
Normal file
3
tokenizer_config.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b308de053b0137ba973039ff11891bd2be5cffd18e9cb6859ff013fca73c9cfb
|
||||
size 177149
|
||||
Reference in New Issue
Block a user