初始化项目，由ModelHub XC社区提供模型
Model: AdamLucek/Orpo-Llama-3.2-1B-15k Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.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
|
||||
78
README.md
Normal file
78
README.md
Normal file
@@ -0,0 +1,78 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: mit
|
||||
datasets:
|
||||
- mlabonne/orpo-dpo-mix-40k
|
||||
base_model:
|
||||
- meta-llama/Llama-3.2-1B
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# Orpo-Llama-3.2-1B-15k
|
||||
|
||||
AdamLucek/Orpo-Llama-3.2-1B-15k is an [ORPO](https://arxiv.org/abs/2403.07691) fine tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on a subset of 15,000 shuffled entries of [mlabonne/orpo-dpo-mix-40k](https://huggingface.co/datasets/mlabonne/orpo-dpo-mix-40k).
|
||||
|
||||
Trained for 7 hours on an L4 GPU with [this training script](https://colab.research.google.com/drive/1KV9AFAfhQCSjF8Ej4rI2ejDmx5AUnqHq?usp=sharing), modified from [Maxime Labonne's original guide](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html)
|
||||
|
||||
For full model details, refer to the base model page [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B)
|
||||
|
||||
## Evaluations
|
||||
|
||||
In comparsion to [AdamLucek/Orpo-Llama-3.2-1B-40k](https://huggingface.co/AdamLucek/Orpo-Llama-3.2-1B-40k) using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness).
|
||||
|
||||
| Benchmark | 15k Accuracy | 15k Normalized | 40k Accuracy | 40k Normalized | Notes |
|
||||
|----------------|--------------|----------------|--------------|----------------|-------------------------------------------|
|
||||
| AGIEval | 22.14% | 21.01% | 23.57% | 23.26% | 0-Shot Average across multiple reasoning tasks |
|
||||
| GPT4ALL | 51.15% | 54.38% | 51.63% | 55.00% | 0-Shot Average across all categories |
|
||||
| TruthfulQA | 42.79% | N/A | 42.14% | N/A | MC2 accuracy |
|
||||
| MMLU | 31.22% | N/A | 31.01% | N/A | 5-Shot Average across all categories |
|
||||
| Winogrande | 61.72% | N/A | 61.12% | N/A | 0-shot evaluation |
|
||||
| ARC Challenge | 32.94% | 36.01% | 33.36% | 37.63% | 0-shot evaluation |
|
||||
| ARC Easy | 64.52% | 60.40% | 65.91% | 60.90% | 0-shot evaluation |
|
||||
| BoolQ | 50.24% | N/A | 52.29% | N/A | 0-shot evaluation |
|
||||
| PIQA | 75.46% | 74.37% | 75.63% | 75.19% | 0-shot evaluation |
|
||||
| HellaSwag | 48.56% | 64.71% | 48.46% | 64.50% | 0-shot evaluation |
|
||||
|
||||
## Using this Model
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer
|
||||
import transformers
|
||||
import torch
|
||||
|
||||
# Load Model and Pipeline
|
||||
model = "AdamLucek/Orpo-Llama-3.2-1B-15k"
|
||||
|
||||
pipeline = transformers.pipeline(
|
||||
"text-generation",
|
||||
model=model,
|
||||
torch_dtype=torch.float16,
|
||||
device_map="auto",
|
||||
)
|
||||
|
||||
# Load Tokenizer
|
||||
tokenizer = AutoTokenizer.from_pretrained(model)
|
||||
|
||||
# Generate Message
|
||||
messages = [{"role": "user", "content": "What is a language model?"}]
|
||||
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
||||
print(outputs[0]["generated_text"])
|
||||
```
|
||||
|
||||
## Training Statistics
|
||||
|
||||
<div style="display: grid; grid-template-columns: repeat(2, 1fr); gap: 5px; max-width: 1000px;">
|
||||
<div>
|
||||
<img src="https://cdn-uploads.huggingface.co/production/uploads/65ba68a15d2ef0a4b2c892b4/p_GHj_vst0xnC7tBznwRk.png" alt="Panel 1" style="width: 100%; height: auto;">
|
||||
</div>
|
||||
<div>
|
||||
<img src="https://cdn-uploads.huggingface.co/production/uploads/65ba68a15d2ef0a4b2c892b4/AT6XO0WuHOWICT5omJ1L5.png" alt="Panel 2" style="width: 100%; height: auto;">
|
||||
</div>
|
||||
<div>
|
||||
<img src="https://cdn-uploads.huggingface.co/production/uploads/65ba68a15d2ef0a4b2c892b4/XOXtthQ1RWxzcIP6V8-o_.png" alt="Panel 3" style="width: 100%; height: auto;">
|
||||
</div>
|
||||
<div>
|
||||
<img src="https://cdn-uploads.huggingface.co/production/uploads/65ba68a15d2ef0a4b2c892b4/WmV9BWOBxElAvZ3aClgUu.png" alt="Panel 4" style="width: 100%; height: auto;">
|
||||
</div>
|
||||
</div>
|
||||
37
config.json
Normal file
37
config.json
Normal file
@@ -0,0 +1,37 @@
|
||||
{
|
||||
"_name_or_path": "meta-llama/Llama-3.2-1B",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128256,
|
||||
"eos_token_id": 128257,
|
||||
"head_dim": 64,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8192,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 16,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 128257,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 32.0,
|
||||
"high_freq_factor": 4.0,
|
||||
"low_freq_factor": 1.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "llama3"
|
||||
},
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.45.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 128258
|
||||
}
|
||||
10
generation_config.json
Normal file
10
generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 128256,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 128257,
|
||||
"pad_token_id": 128257,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.45.2"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:39a2e96bf15ed175eb84db4cca9257d53a922460075323bc8325670bfc4ea185
|
||||
size 2471653656
|
||||
21
special_tokens_map.json
Normal file
21
special_tokens_map.json
Normal file
@@ -0,0 +1,21 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
{
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
{
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
],
|
||||
"bos_token": "<|im_start|>",
|
||||
"eos_token": "<|im_end|>",
|
||||
"pad_token": "<|im_end|>"
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:510d12ec255f4cb0304aa5428d699c354c1a49696b427a2748a7b03bb7bbb575
|
||||
size 17210296
|
||||
2083
tokenizer_config.json
Normal file
2083
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user