MaziyarPanahi commited on
Commit
4aef754
1 Parent(s): ab7c113

Create README.md (#2)

Browse files

- Create README.md (cf5eaff380463030048a8b5d7a62bb44145e4d15)

Files changed (1) hide show
  1. README.md +159 -0
README.md ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-70B-Instruct
3
+ library_name: transformers
4
+ tags:
5
+ - axolotl
6
+ - finetune
7
+ - dpo
8
+ - facebook
9
+ - meta
10
+ - pytorch
11
+ - llama
12
+ - llama-3
13
+ - chatml
14
+ language:
15
+ - en
16
+ pipeline_tag: text-generation
17
+ license: llama3
18
+ license_name: llama3
19
+ license_link: LICENSE
20
+ inference: false
21
+ model_creator: MaziyarPanahi
22
+ model_name: Llama-3-70B-Instruct-DPO-v0.4
23
+ quantized_by: MaziyarPanahi
24
+ datasets:
25
+ - Intel/orca_dpo_pairs
26
+ ---
27
+
28
+ <img src="./llama-3-merges.webp" alt="Llama-3 DPO Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
29
+
30
+
31
+ # MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4
32
+
33
+ This model is a fine-tune (DPO) of `meta-llama/Meta-Llama-3-70B-Instruct` model.
34
+
35
+ # Quantized GGUF
36
+
37
+ 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)
38
+
39
+ # Prompt Template
40
+
41
+ This model uses `ChatML` prompt template:
42
+
43
+ ```
44
+ <|im_start|>system
45
+ {System}
46
+ <|im_end|>
47
+ <|im_start|>user
48
+ {User}
49
+ <|im_end|>
50
+ <|im_start|>assistant
51
+ {Assistant}
52
+ ````
53
+
54
+ # How to use
55
+
56
+ You can use this model by using `MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4` as the model name in Hugging Face's
57
+ transformers library.
58
+
59
+ ```python
60
+ from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
61
+ from transformers import pipeline
62
+ import torch
63
+
64
+ model_id = "MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4"
65
+
66
+ model = AutoModelForCausalLM.from_pretrained(
67
+ model_id,
68
+ torch_dtype=torch.bfloat16,
69
+ device_map="auto",
70
+ trust_remote_code=True,
71
+ # attn_implementation="flash_attention_2"
72
+ )
73
+
74
+ tokenizer = AutoTokenizer.from_pretrained(
75
+ model_id,
76
+ trust_remote_code=True
77
+ )
78
+
79
+ streamer = TextStreamer(tokenizer)
80
+
81
+ pipeline = pipeline(
82
+ "text-generation",
83
+ model=model,
84
+ tokenizer=tokenizer,
85
+ model_kwargs={"torch_dtype": torch.bfloat16},
86
+ streamer=streamer
87
+ )
88
+
89
+ # Then you can use the pipeline to generate text.
90
+
91
+ messages = [
92
+ {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
93
+ {"role": "user", "content": "Who are you?"},
94
+ ]
95
+
96
+ prompt = tokenizer.apply_chat_template(
97
+ messages,
98
+ tokenize=False,
99
+ add_generation_prompt=True
100
+ )
101
+
102
+ terminators = [
103
+ tokenizer.eos_token_id,
104
+ tokenizer.convert_tokens_to_ids("<|im_end|>"),
105
+ tokenizer.convert_tokens_to_ids("<|eot_id|>") # safer to have this too
106
+ ]
107
+
108
+ outputs = pipeline(
109
+ prompt,
110
+ max_new_tokens=2048,
111
+ eos_token_id=terminators,
112
+ do_sample=True,
113
+ temperature=0.6,
114
+ top_p=0.95,
115
+ )
116
+ print(outputs[0]["generated_text"][len(prompt):])
117
+ ```
118
+
119
+ ## Sample Response
120
+
121
+ ```
122
+ <|im_start|>system
123
+ You are a helpful assistant.<|im_end|>
124
+ <|im_start|>user
125
+ describe about pros and cons of docker system.<|im_end|>
126
+ <|im_start|>assistant
127
+ ```
128
+
129
+ ```
130
+ Here are the pros and cons of the Docker system:
131
+
132
+ **Pros:**
133
+
134
+ 1. **Lightweight**: Docker containers are lightweight and use fewer resources compared to traditional virtual machines.
135
+ 2. **Isolation**: Docker provides a high level of isolation between containers, ensuring that each application runs independently without interfering with others.
136
+ 3. **Portability**: Docker containers are highly portable and can run on any system that supports Docker, without requiring specific dependencies or configurations.
137
+ 4. **Efficient Use of Resources**: Docker containers can share the same kernel and use fewer resources, making them more efficient than traditional virtual machines.
138
+ 5. **Fast Deployment**: Docker containers can be spun up quickly, making it ideal for rapid deployment and scaling of applications.
139
+ 6. **Easy Maintenance**: Docker provides a simple way to manage and update applications, with features like rolling updates and rollbacks.
140
+ 7. **Security**: Docker provides a secure environment for applications, with features like network isolation and encryption.
141
+ 8. **Large Ecosystem**: Docker has a large and active ecosystem, with a wide range of tools and plugins available for various tasks.
142
+ 9. **Version Control**: Docker provides an easy way to manage different versions of an application, with features like version tagging and rollbacks.
143
+ 10. **Cost-Effective**: Docker can help reduce costs by minimizing the need for virtual machines and reducing the overhead of resource allocation.
144
+
145
+ **Cons:**
146
+
147
+ 1. **Steep Learning Curve**: Docker has a complex architecture and requires a good understanding of containerization, networking, and storage.
148
+ 2. **Overhead**: While Docker containers are lightweight, they still require some overhead in terms of resources and management.
149
+ 3. **Security Risks**: If not properly configured, Docker containers can introduce security risks, such as unauthorized access to the host system.
150
+ 4. **Limited Support for GUI Applications**: Docker is primarily designed for running command-line applications, and running GUI applications can be challenging.
151
+ 5. **Networking Complexity**: Docker's networking model can be complex, especially in large-scale deployments.
152
+ 6. **Storage Complexity**: Docker's storage model can be complex, especially when dealing with persistent data.
153
+ 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.
154
+ 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.
155
+ 9. **Orchestration Complexity**: Docker provides a built-in orchestration tool, Docker Swarm, but it can be complex to set up and manage.
156
+ 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.
157
+
158
+ 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.
159
+ ```