Upload folder using huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
tags:
|
| 5 |
+
- education
|
| 6 |
+
- english
|
| 7 |
+
- small-model
|
| 8 |
+
- fine-tuned
|
| 9 |
+
- teaching-assistant
|
| 10 |
+
license: apache-2.0
|
| 11 |
+
datasets:
|
| 12 |
+
- video-transcripts
|
| 13 |
+
metrics:
|
| 14 |
+
- accuracy
|
| 15 |
+
model-index:
|
| 16 |
+
- name: Small English Teacher
|
| 17 |
+
results:
|
| 18 |
+
- task:
|
| 19 |
+
name: Educational Instruction
|
| 20 |
+
type: text-generation
|
| 21 |
+
dataset:
|
| 22 |
+
name: Video Transcripts
|
| 23 |
+
type: generated
|
| 24 |
+
metrics:
|
| 25 |
+
- type: Accuracy
|
| 26 |
+
value: 80%
|
| 27 |
+
mode: approximate
|
| 28 |
+
---
|
| 29 |
+
|
| 30 |
+
# Small English Teacher Model
|
| 31 |
+
|
| 32 |
+
## Model Description
|
| 33 |
+
Small English Teacher is a compact language model fine-tuned for educational instruction in English. Designed to provide clear, concise, and helpful explanations across various educational contexts.
|
| 34 |
+
|
| 35 |
+
### Key Features
|
| 36 |
+
- Trained on diverse video transcript data
|
| 37 |
+
- Specializes in educational content generation
|
| 38 |
+
- Provides step-by-step explanations
|
| 39 |
+
- Compact model with efficient performance
|
| 40 |
+
|
| 41 |
+
### Training Details
|
| 42 |
+
- Base Model: [Original Base Model Name]
|
| 43 |
+
- Training Data: Video transcripts
|
| 44 |
+
- Fine-tuning Method: LoRA (Low-Rank Adaptation)
|
| 45 |
+
- Model Size: Small (3.7 GB)
|
| 46 |
+
|
| 47 |
+
### Example Capabilities
|
| 48 |
+
- Generate educational explanations
|
| 49 |
+
- Break down complex concepts
|
| 50 |
+
- Provide structured learning content
|
| 51 |
+
|
| 52 |
+
### Limitations
|
| 53 |
+
- Best suited for general educational content
|
| 54 |
+
- May have limited depth in specialized subjects
|
| 55 |
+
- Performance may vary across different topics
|
| 56 |
+
|
| 57 |
+
### Ethical Considerations
|
| 58 |
+
Intended for educational support and should be used responsibly.
|
| 59 |
+
|
| 60 |
+
## Usage
|
| 61 |
+
```python
|
| 62 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 63 |
+
|
| 64 |
+
model = AutoModelForCausalLM.from_pretrained("your-username/small-english-teacher")
|
| 65 |
+
tokenizer = AutoTokenizer.from_pretrained("your-username/small-english-teacher")
|
| 66 |
+
```
|
| 67 |
+
|
| 68 |
+
## License
|
| 69 |
+
Apache 2.0
|
| 70 |
+
|
| 71 |
+
## Citation
|
| 72 |
+
If you use this model, please cite:
|
| 73 |
+
[Placeholder for citation details]
|
modelfile
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Model
|
| 2 |
+
architecture qwen2
|
| 3 |
+
parameters 1.8B
|
| 4 |
+
context length 32768
|
| 5 |
+
embedding length 2048
|
| 6 |
+
quantization F16
|
| 7 |
+
|
| 8 |
+
Parameters
|
| 9 |
+
stop "<|im_start|>"
|
| 10 |
+
stop "<|im_end|>"
|
| 11 |
+
temperature 0.6
|
| 12 |
+
top_p 0.8
|
| 13 |
+
|
| 14 |
+
System
|
| 15 |
+
You are a friendly and patient English language teacher who helps students improve their language
|
| 16 |
+
skills through interactive and engaging conversations. Provide clear explanations, encourage
|
| 17 |
+
practice, and offer constructive feedback.
|
| 18 |
+
|