File size: 9,494 Bytes
4aef754 5ac1cdf 4aef754 5ac1cdf 4aef754 5ac1cdf 4aef754 25de977 4aef754 25de977 4aef754 5ac1cdf |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 |
---
language:
- en
license: llama3
library_name: transformers
tags:
- axolotl
- finetune
- dpo
- facebook
- meta
- pytorch
- llama
- llama-3
- chatml
base_model: meta-llama/Meta-Llama-3-70B-Instruct
datasets:
- argilla/ultrafeedback-binarized-preferences
pipeline_tag: text-generation
license_name: llama3
license_link: LICENSE
inference: false
model_creator: MaziyarPanahi
quantized_by: MaziyarPanahi
model-index:
- name: Llama-3-70B-Instruct-DPO-v0.4
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 72.61
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 86.03
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 80.5
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 63.26
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 83.58
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 87.34
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4
name: Open LLM Leaderboard
---
<img src="./llama-3-merges.webp" alt="Llama-3 DPO Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
# MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4
This model is a fine-tune (DPO) of `meta-llama/Meta-Llama-3-70B-Instruct` model.
# ⚡ Quantized GGUF
All GGUF models are available here: [MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4-GGUF)
# 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__Llama-3-70B-Instruct-DPO-v0.4)
| Metric |Value|
|---------------------------------|----:|
|Avg. |78.89|
|AI2 Reasoning Challenge (25-Shot)|72.61|
|HellaSwag (10-Shot) |86.03|
|MMLU (5-Shot) |80.50|
|TruthfulQA (0-shot) |63.26|
|Winogrande (5-shot) |83.58|
|GSM8k (5-shot) |87.34|
**Top 10 models on the Leaderboard**
<img src="./llama-3-70b-top-10.png" alt="Llama-3-70B finet-tuned models" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
# Prompt Template
This model uses `ChatML` prompt template:
```
<|im_start|>system
{System}
<|im_end|>
<|im_start|>user
{User}
<|im_end|>
<|im_start|>assistant
{Assistant}
````
# How to use
You can use this model by using `MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4` as the model name in Hugging Face's
transformers library.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
from transformers import pipeline
import torch
model_id = "MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4"
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
trust_remote_code=True,
# attn_implementation="flash_attention_2"
)
tokenizer = AutoTokenizer.from_pretrained(
model_id,
trust_remote_code=True
)
streamer = TextStreamer(tokenizer)
pipeline = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
model_kwargs={"torch_dtype": torch.bfloat16},
streamer=streamer
)
# Then you can use the pipeline to generate text.
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
prompt = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|im_end|>"),
tokenizer.convert_tokens_to_ids("<|eot_id|>") # safer to have this too
]
outputs = pipeline(
prompt,
max_new_tokens=2048,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.95,
)
print(outputs[0]["generated_text"][len(prompt):])
```
## Sample Response
```
<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
describe about pros and cons of docker system.<|im_end|>
<|im_start|>assistant
```
```
Here are the pros and cons of the Docker system:
**Pros:**
1. **Lightweight**: Docker containers are lightweight and use fewer resources compared to traditional virtual machines.
2. **Isolation**: Docker provides a high level of isolation between containers, ensuring that each application runs independently without interfering with others.
3. **Portability**: Docker containers are highly portable and can run on any system that supports Docker, without requiring specific dependencies or configurations.
4. **Efficient Use of Resources**: Docker containers can share the same kernel and use fewer resources, making them more efficient than traditional virtual machines.
5. **Fast Deployment**: Docker containers can be spun up quickly, making it ideal for rapid deployment and scaling of applications.
6. **Easy Maintenance**: Docker provides a simple way to manage and update applications, with features like rolling updates and rollbacks.
7. **Security**: Docker provides a secure environment for applications, with features like network isolation and encryption.
8. **Large Ecosystem**: Docker has a large and active ecosystem, with a wide range of tools and plugins available for various tasks.
9. **Version Control**: Docker provides an easy way to manage different versions of an application, with features like version tagging and rollbacks.
10. **Cost-Effective**: Docker can help reduce costs by minimizing the need for virtual machines and reducing the overhead of resource allocation.
**Cons:**
1. **Steep Learning Curve**: Docker has a complex architecture and requires a good understanding of containerization, networking, and storage.
2. **Overhead**: While Docker containers are lightweight, they still require some overhead in terms of resources and management.
3. **Security Risks**: If not properly configured, Docker containers can introduce security risks, such as unauthorized access to the host system.
4. **Limited Support for GUI Applications**: Docker is primarily designed for running command-line applications, and running GUI applications can be challenging.
5. **Networking Complexity**: Docker's networking model can be complex, especially in large-scale deployments.
6. **Storage Complexity**: Docker's storage model can be complex, especially when dealing with persistent data.
7. **Limited Support for Legacy Applications**: Docker is designed for modern, cloud-native applications, and may not be suitable for legacy applications that rely on older technologies.
8. **Dependence on Docker Hub**: Docker relies heavily on Docker Hub, which can be a single point of failure if the hub is down or experiencing issues.
9. **Orchestration Complexity**: Docker provides a built-in orchestration tool, Docker Swarm, but it can be complex to set up and manage.
10. **Vendor Lock-in**: Docker is a proprietary technology, and while it has a large ecosystem, it can be difficult to switch to alternative containerization platforms.
Overall, Docker provides a powerful and flexible way to deploy and manage applications, but it requires careful planning, configuration, and management to ensure optimal performance and security.
```
|