初始化项目，由ModelHub XC社区提供模型
Model: yasserrmd/lfm2.5-1.5b-sdft Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.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
|
||||
318
README.md
Normal file
318
README.md
Normal file
@@ -0,0 +1,318 @@
|
||||
---
|
||||
base_model: LiquidAI/LFM2.5-1.2B-Instruct
|
||||
tags:
|
||||
- sdft
|
||||
- self-distillation
|
||||
- continual-learning
|
||||
- conversational
|
||||
language:
|
||||
- en
|
||||
license: apache-2.0
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
---
|
||||
|
||||
# LFM2.5-1.2B-SDFT: Self-Distillation Fine-Tuned Model
|
||||
|
||||
This model is a **Self-Distillation Fine-Tuned (SDFT)** version of [LiquidAI/LFM2.5-1.2B-Instruct](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct), trained using the methodology from the paper ["Self-Distillation Enables Continual Learning"](https://arxiv.org/abs/2601.19897).
|
||||
|
||||
## Model Description
|
||||
|
||||
- **Base Model:** LiquidAI/LFM2.5-1.2B-Instruct
|
||||
- **Training Method:** Self-Distillation Fine-Tuning (SDFT)
|
||||
- **Training Data:** ~5K samples from OpenAssistant dataset
|
||||
- **Training Hardware:** Single NVIDIA A100 GPU
|
||||
- **Parameters:** LoRA rank=8, alpha=16, targeting q_proj and v_proj
|
||||
|
||||
### What is SDFT?
|
||||
|
||||
Self-Distillation Fine-Tuning (SDFT) is a continual learning technique that:
|
||||
- Uses the model's **in-context learning** ability to create a demonstration-aware teacher
|
||||
- Generates training data **on-policy** from the student model
|
||||
- Minimizes KL divergence between student and demonstration-conditioned teacher
|
||||
- Enables learning new tasks while **reducing catastrophic forgetting**
|
||||
|
||||
Key advantages:
|
||||
- ✅ Learns from demonstrations without explicit reward functions
|
||||
- ✅ Maintains prior knowledge while acquiring new skills
|
||||
- ✅ On-policy learning improves generalization
|
||||
- ✅ Efficient training with EMA teacher updates
|
||||
|
||||
## Quick Start
|
||||
|
||||
### Installation
|
||||
|
||||
```bash
|
||||
pip install torch transformers peft accelerate bitsandbytes
|
||||
```
|
||||
|
||||
### Basic Usage
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
|
||||
# Load tokenizer
|
||||
tokenizer = AutoTokenizer.from_pretrained("LiquidAI/LFM2.5-1.2B-Instruct")
|
||||
|
||||
# Load model with quantization
|
||||
base_model = AutoModelForCausalLM.from_pretrained(
|
||||
"yasserrmd/lfm2.5-1.5b-sdft",
|
||||
torch_dtype=torch.float16,
|
||||
device_map="auto"
|
||||
)
|
||||
|
||||
|
||||
model.eval()
|
||||
|
||||
# Generate
|
||||
prompt = """<|im_start|>user
|
||||
Explain how photosynthesis works.
|
||||
<|im_end|>
|
||||
<|im_start|>assistant
|
||||
"""
|
||||
|
||||
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
|
||||
|
||||
# Use official LiquidAI parameters
|
||||
outputs = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=256,
|
||||
do_sample=True,
|
||||
temperature=0.1,
|
||||
top_k=50,
|
||||
top_p=0.1,
|
||||
repetition_penalty=1.05,
|
||||
pad_token_id=tokenizer.pad_token_id
|
||||
)
|
||||
|
||||
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
||||
print(response)
|
||||
```
|
||||
|
||||
### With Demonstration (In-Context Learning)
|
||||
|
||||
```python
|
||||
prompt = """<|im_start|>user
|
||||
Explain how databases work.
|
||||
|
||||
Here is an example response to guide you:
|
||||
|
||||
Example: Databases store data in tables. You can query them to get information back.
|
||||
|
||||
Now provide your own response following a similar approach:
|
||||
<|im_end|>
|
||||
<|im_start|>assistant
|
||||
"""
|
||||
|
||||
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
|
||||
outputs = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=256,
|
||||
do_sample=True,
|
||||
temperature=0.1,
|
||||
top_k=50,
|
||||
top_p=0.1,
|
||||
repetition_penalty=1.05
|
||||
)
|
||||
|
||||
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
||||
print(response)
|
||||
```
|
||||
|
||||
## Training Details
|
||||
|
||||
### Dataset
|
||||
- **Source:** OpenAssistant conversations
|
||||
- **Size:** ~5,000 query-demonstration pairs
|
||||
- **Preprocessing:**
|
||||
- Filtered demonstrations: 20-2048 characters
|
||||
- Train/Val/Test split: 75%/10%/15%
|
||||
|
||||
### Training Configuration
|
||||
|
||||
```python
|
||||
# Model Architecture
|
||||
- Base: LiquidAI/LFM2.5-1.2B-Instruct
|
||||
- Quantization: 8-bit with bitsandbytes
|
||||
- LoRA: rank=8, alpha=16, dropout=0.05
|
||||
- Target modules: q_proj, v_proj
|
||||
|
||||
# Training Parameters
|
||||
- Learning rate: 5e-6
|
||||
- Optimizer: AdamW (weight_decay=0.01)
|
||||
- Batch size: 1 (with gradient accumulation)
|
||||
- Gradient accumulation steps: 16
|
||||
- Epochs: 3
|
||||
- Max sequence length: 512
|
||||
- Max generation length: 128
|
||||
|
||||
# SDFT-Specific
|
||||
- EMA alpha: 0.02
|
||||
- Temperature: 1.0
|
||||
- KL divergence: Analytic (full vocabulary)
|
||||
- On-policy generation: Yes
|
||||
```
|
||||
|
||||
### Prompt Format (Teacher vs Student)
|
||||
|
||||
**Student Prompt (query only):**
|
||||
```
|
||||
<|im_start|>user
|
||||
{query}
|
||||
<|im_end|>
|
||||
<|im_start|>assistant
|
||||
```
|
||||
|
||||
**Teacher Prompt (query + demonstration):**
|
||||
```
|
||||
<|im_start|>user
|
||||
{query}
|
||||
|
||||
Here is an example response to guide you:
|
||||
|
||||
<|im_start|>assistant
|
||||
{demonstration}
|
||||
<|im_end|>
|
||||
|
||||
<|im_start|>user
|
||||
Now provide your own response following a similar approach and reasoning:
|
||||
<|im_end|>
|
||||
<|im_start|>assistant
|
||||
```
|
||||
|
||||
## Evaluation Results
|
||||
|
||||
### Tested on Multiple Dimensions:
|
||||
|
||||
| Category | Description | Performance |
|
||||
|----------|-------------|-------------|
|
||||
| **ICL Adaptation** | Following demonstration style | ✅ Good |
|
||||
| **Task Improvement** | Learning from examples | ✅ Good |
|
||||
| **Retention** | No catastrophic forgetting | ✅ ~80% |
|
||||
| **Polarity Control** | Following demo viewpoint | ⚠️ Moderate |
|
||||
|
||||
### Key Findings:
|
||||
|
||||
1. ✅ **Maintains Knowledge:** No significant forgetting on general tasks
|
||||
2. ✅ **Adapts to Demos:** Successfully follows demonstration styles
|
||||
3. ✅ **Improved Over Training:** Epoch 3 shows stable, coherent outputs
|
||||
4. ⚠️ **Model Size Limitation:** 1.2B parameters limits complex reasoning
|
||||
|
||||
### Comparison to Base Model:
|
||||
|
||||
- **With Demonstrations:** SDFT shows better style matching and task following
|
||||
- **Without Demonstrations:** Maintains base model capabilities
|
||||
- **Response Quality:** More consistent and focused outputs
|
||||
|
||||
## Generation Parameters
|
||||
|
||||
**⚠️ Important:** Use official LiquidAI parameters for best results:
|
||||
|
||||
```python
|
||||
generation_config = {
|
||||
"max_new_tokens": 256,
|
||||
"do_sample": True,
|
||||
"temperature": 0.1, # Official LiquidAI recommendation
|
||||
"top_k": 50, # Official LiquidAI recommendation
|
||||
"top_p": 0.1, # Official LiquidAI recommendation
|
||||
"repetition_penalty": 1.05 # Official LiquidAI recommendation
|
||||
}
|
||||
```
|
||||
|
||||
These parameters are specifically tuned for LFM2.5 and provide:
|
||||
- Focused, factual responses
|
||||
- Minimal hallucinations
|
||||
- Consistent output quality
|
||||
|
||||
## Limitations
|
||||
|
||||
### Model Constraints:
|
||||
- **Size:** 1.2B parameters (smaller capacity than 7B+ models)
|
||||
- **Training Data:** 5K samples (vs paper's 20K+)
|
||||
- **Hardware:** Single A100 (vs paper's multi-GPU setup)
|
||||
- **Complexity:** Limited reasoning on very complex tasks
|
||||
|
||||
### Known Issues:
|
||||
- May require proper ChatML formatting for best results
|
||||
- Performance degrades on tasks requiring deep technical knowledge
|
||||
- Smaller model size limits polarity control effectiveness
|
||||
|
||||
### Appropriate Use Cases:
|
||||
- ✅ Conversational AI with example-guided responses
|
||||
- ✅ Task learning from demonstrations
|
||||
- ✅ Style-adaptive text generation
|
||||
- ✅ Educational/research purposes
|
||||
|
||||
### Not Recommended For:
|
||||
- ❌ Production systems requiring 100% reliability
|
||||
- ❌ Tasks requiring strong reasoning (use 7B+ models)
|
||||
- ❌ Safety-critical applications
|
||||
- ❌ Tasks outside training distribution without demonstrations
|
||||
|
||||
## Bias and Ethical Considerations
|
||||
|
||||
- Inherits biases from base LFM2.5 model and OpenAssistant dataset
|
||||
- May generate inconsistent responses on controversial topics
|
||||
- Should not be used for medical, legal, or financial advice
|
||||
- Outputs should be reviewed by humans for critical applications
|
||||
|
||||
## Citation
|
||||
|
||||
If you use this model, please cite:
|
||||
|
||||
**SDFT Paper:**
|
||||
```bibtex
|
||||
@article{shenfeld2026sdft,
|
||||
title={Self-Distillation Enables Continual Learning},
|
||||
author={Shenfeld, Idan and Damani, Mehul and H{\"u}botter, Jonas and Agrawal, Pulkit},
|
||||
journal={arXiv preprint arXiv:2601.19897},
|
||||
year={2026}
|
||||
}
|
||||
```
|
||||
|
||||
**Base Model:**
|
||||
```bibtex
|
||||
@misc{lfm25,
|
||||
title={LFM2.5: Liquid Foundation Models},
|
||||
author={LiquidAI},
|
||||
year={2024},
|
||||
url={https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct}
|
||||
}
|
||||
```
|
||||
|
||||
## Acknowledgments
|
||||
|
||||
- **Paper:** ["Self-Distillation Enables Continual Learning"](https://arxiv.org/abs/2601.19897) by Shenfeld et al.
|
||||
- **Base Model:** [LiquidAI/LFM2.5-1.2B-Instruct](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct)
|
||||
- **Dataset:** OpenAssistant conversations
|
||||
- **Framework:** HuggingFace Transformers, PEFT, bitsandbytes
|
||||
|
||||
## License
|
||||
|
||||
This model is released under the Apache 2.0 license, following the base model's licensing.
|
||||
|
||||
## Model Card Authors
|
||||
|
||||
[Your Name/Organization]
|
||||
|
||||
## Contact
|
||||
|
||||
For questions or issues, please open an issue on the [model repository](https://huggingface.co/YOUR_USERNAME/lfm25-sdft).
|
||||
|
||||
---
|
||||
|
||||
## Additional Resources
|
||||
|
||||
- 📄 [SDFT Paper](https://arxiv.org/abs/2601.19897)
|
||||
- 💻 [Training Code](https://github.com/YOUR_USERNAME/sdft-training)
|
||||
- 🤗 [Base Model](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct)
|
||||
- 📊 [Evaluation Results](link-to-detailed-results)
|
||||
|
||||
## Version History
|
||||
|
||||
- **v1.0** (2024-XX-XX): Initial release
|
||||
- Trained on 5K OpenAssistant samples
|
||||
- 3 epochs with gradient accumulation
|
||||
- LoRA rank 8, alpha 16
|
||||
45
chat_template.jinja
Normal file
45
chat_template.jinja
Normal file
@@ -0,0 +1,45 @@
|
||||
{{- bos_token -}}
|
||||
{%- set keep_past_thinking = keep_past_thinking | default(false) -%}
|
||||
{%- set ns = namespace(system_prompt="") -%}
|
||||
{%- if messages[0]["role"] == "system" -%}
|
||||
{%- set ns.system_prompt = messages[0]["content"] -%}
|
||||
{%- set messages = messages[1:] -%}
|
||||
{%- endif -%}
|
||||
{%- if tools -%}
|
||||
{%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
|
||||
{%- for tool in tools -%}
|
||||
{%- if tool is not string -%}
|
||||
{%- set tool = tool | tojson -%}
|
||||
{%- endif -%}
|
||||
{%- set ns.system_prompt = ns.system_prompt + tool -%}
|
||||
{%- if not loop.last -%}
|
||||
{%- set ns.system_prompt = ns.system_prompt + ", " -%}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- set ns.system_prompt = ns.system_prompt + "]" -%}
|
||||
{%- endif -%}
|
||||
{%- if ns.system_prompt -%}
|
||||
{{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
|
||||
{%- endif -%}
|
||||
{%- set ns.last_assistant_index = -1 -%}
|
||||
{%- for message in messages -%}
|
||||
{%- if message["role"] == "assistant" -%}
|
||||
{%- set ns.last_assistant_index = loop.index0 -%}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- for message in messages -%}
|
||||
{{- "<|im_start|>" + message["role"] + "\n" -}}
|
||||
{%- set content = message["content"] -%}
|
||||
{%- if content is not string -%}
|
||||
{%- set content = content | tojson -%}
|
||||
{%- endif -%}
|
||||
{%- if message["role"] == "assistant" and not keep_past_thinking and loop.index0 != ns.last_assistant_index -%}
|
||||
{%- if "</think>" in content -%}
|
||||
{%- set content = content.split("</think>")[-1] | trim -%}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
{{- content + "<|im_end|>\n" -}}
|
||||
{%- endfor -%}
|
||||
{%- if add_generation_prompt -%}
|
||||
{{- "<|im_start|>assistant\n" -}}
|
||||
{%- endif -%}
|
||||
61
config.json
Normal file
61
config.json
Normal file
@@ -0,0 +1,61 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Lfm2ForCausalLM"
|
||||
],
|
||||
"block_auto_adjust_ff_dim": true,
|
||||
"block_dim": 2048,
|
||||
"block_ff_dim": 12288,
|
||||
"block_ffn_dim_multiplier": 1.0,
|
||||
"block_mlp_init_scale": 1.0,
|
||||
"block_multiple_of": 256,
|
||||
"block_norm_eps": 1e-05,
|
||||
"block_out_init_scale": 1.0,
|
||||
"block_use_swiglu": true,
|
||||
"block_use_xavier_init": true,
|
||||
"bos_token_id": 1,
|
||||
"conv_L_cache": 3,
|
||||
"conv_bias": false,
|
||||
"conv_dim": 2048,
|
||||
"conv_use_xavier_init": true,
|
||||
"dtype": "float16",
|
||||
"eos_token_id": 7,
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"layer_types": [
|
||||
"conv",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv"
|
||||
],
|
||||
"max_position_embeddings": 128000,
|
||||
"model_type": "lfm2",
|
||||
"norm_eps": 1e-05,
|
||||
"num_attention_heads": 32,
|
||||
"num_heads": 32,
|
||||
"num_hidden_layers": 16,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 0,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"tie_embedding": true,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.0.0",
|
||||
"use_cache": true,
|
||||
"use_pos_enc": true,
|
||||
"vocab_size": 65536
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 7,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "5.0.0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:82b15b6e205ab3201cfb567369f38400e1ac7a907f130f95acabc2b89ed9b5f0
|
||||
size 2340697784
|
||||
323830
tokenizer.json
Normal file
323830
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
20
tokenizer_config.json
Normal file
20
tokenizer_config.json
Normal file
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<|startoftext|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"is_local": false,
|
||||
"legacy": false,
|
||||
"model_input_names": [
|
||||
"input_ids",
|
||||
"attention_mask"
|
||||
],
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"model_specific_special_tokens": {},
|
||||
"pad_token": "<|pad|>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "TokenizersBackend",
|
||||
"use_default_system_prompt": false,
|
||||
"use_fast": true
|
||||
}
|
||||
Reference in New Issue
Block a user