nbeerbower commited on
Commit
a29dec6
1 Parent(s): abc7fc4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +124 -195
README.md CHANGED
@@ -1,199 +1,128 @@
1
  ---
2
  library_name: transformers
3
- tags: []
 
 
 
 
4
  ---
5
 
6
- # Model Card for Model ID
7
-
8
- <!-- Provide a quick summary of what the model is/does. -->
9
-
10
-
11
-
12
- ## Model Details
13
-
14
- ### Model Description
15
-
16
- <!-- Provide a longer summary of what this model is. -->
17
-
18
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
-
20
- - **Developed by:** [More Information Needed]
21
- - **Funded by [optional]:** [More Information Needed]
22
- - **Shared by [optional]:** [More Information Needed]
23
- - **Model type:** [More Information Needed]
24
- - **Language(s) (NLP):** [More Information Needed]
25
- - **License:** [More Information Needed]
26
- - **Finetuned from model [optional]:** [More Information Needed]
27
-
28
- ### Model Sources [optional]
29
-
30
- <!-- Provide the basic links for the model. -->
31
-
32
- - **Repository:** [More Information Needed]
33
- - **Paper [optional]:** [More Information Needed]
34
- - **Demo [optional]:** [More Information Needed]
35
-
36
- ## Uses
37
-
38
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
-
40
- ### Direct Use
41
-
42
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
-
44
- [More Information Needed]
45
-
46
- ### Downstream Use [optional]
47
-
48
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
-
50
- [More Information Needed]
51
-
52
- ### Out-of-Scope Use
53
-
54
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
-
56
- [More Information Needed]
57
-
58
- ## Bias, Risks, and Limitations
59
-
60
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
-
62
- [More Information Needed]
63
-
64
- ### Recommendations
65
-
66
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
-
68
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
-
70
- ## How to Get Started with the Model
71
-
72
- Use the code below to get started with the model.
73
-
74
- [More Information Needed]
75
-
76
- ## Training Details
77
-
78
- ### Training Data
79
-
80
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
-
82
- [More Information Needed]
83
-
84
- ### Training Procedure
85
-
86
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
-
88
- #### Preprocessing [optional]
89
-
90
- [More Information Needed]
91
-
92
-
93
- #### Training Hyperparameters
94
-
95
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
-
97
- #### Speeds, Sizes, Times [optional]
98
-
99
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
-
101
- [More Information Needed]
102
-
103
- ## Evaluation
104
-
105
- <!-- This section describes the evaluation protocols and provides the results. -->
106
-
107
- ### Testing Data, Factors & Metrics
108
-
109
- #### Testing Data
110
-
111
- <!-- This should link to a Dataset Card if possible. -->
112
-
113
- [More Information Needed]
114
-
115
- #### Factors
116
-
117
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
-
119
- [More Information Needed]
120
-
121
- #### Metrics
122
-
123
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
-
125
- [More Information Needed]
126
-
127
- ### Results
128
-
129
- [More Information Needed]
130
-
131
- #### Summary
132
-
133
-
134
-
135
- ## Model Examination [optional]
136
-
137
- <!-- Relevant interpretability work for the model goes here -->
138
-
139
- [More Information Needed]
140
-
141
- ## Environmental Impact
142
-
143
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
-
145
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
-
147
- - **Hardware Type:** [More Information Needed]
148
- - **Hours used:** [More Information Needed]
149
- - **Cloud Provider:** [More Information Needed]
150
- - **Compute Region:** [More Information Needed]
151
- - **Carbon Emitted:** [More Information Needed]
152
-
153
- ## Technical Specifications [optional]
154
-
155
- ### Model Architecture and Objective
156
-
157
- [More Information Needed]
158
-
159
- ### Compute Infrastructure
160
-
161
- [More Information Needed]
162
-
163
- #### Hardware
164
-
165
- [More Information Needed]
166
-
167
- #### Software
168
-
169
- [More Information Needed]
170
-
171
- ## Citation [optional]
172
-
173
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
-
175
- **BibTeX:**
176
-
177
- [More Information Needed]
178
-
179
- **APA:**
180
-
181
- [More Information Needed]
182
-
183
- ## Glossary [optional]
184
-
185
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
-
187
- [More Information Needed]
188
-
189
- ## More Information [optional]
190
-
191
- [More Information Needed]
192
-
193
- ## Model Card Authors [optional]
194
-
195
- [More Information Needed]
196
-
197
- ## Model Card Contact
198
-
199
- [More Information Needed]
 
1
  ---
2
  library_name: transformers
3
+ license: apache-2.0
4
+ base_model:
5
+ - flammenai/flammen22-mistral-7B
6
+ datasets:
7
+ - flammenai/casual-conversation-DPO
8
  ---
9
 
10
+ ![image/png](https://huggingface.co/nbeerbower/flammen13X-mistral-7B/resolve/main/flammen13x.png)
11
+
12
+ # flammen22C-mistral-7B
13
+
14
+ A Mistral 7B LLM built from merging pretrained models and finetuning on [flammenai/casual-conversation-DPO](https://huggingface.co/datasets/flammenai/casual-conversation-DPO).
15
+ Flammen specializes in exceptional character roleplay, creative writing, and general intelligence
16
+
17
+ ### Method
18
+
19
+ Finetuned using an A100 on Google Colab.
20
+
21
+ [Fine-tune a Mistral-7b model with Direct Preference Optimization](https://towardsdatascience.com/fine-tune-a-mistral-7b-model-with-direct-preference-optimization-708042745aac) - [Maxime Labonne](https://huggingface.co/mlabonne)
22
+
23
+ ### Configuration
24
+
25
+ System prompt, dataset formatting:
26
+
27
+ ```python
28
+ def chatml_format(example):
29
+ # Initialize formatted system message
30
+ system = ""
31
+ message = {"role": "system", "content": "You are an AI character talking to a human. Engage in casual conversation."}
32
+ system = tokenizer.apply_chat_template([message], tokenize=False)
33
+
34
+ # Format instruction
35
+ message = {"role": "user", "content": example['prompt']}
36
+ prompt = tokenizer.apply_chat_template([message], tokenize=False, add_generation_prompt=True)
37
+
38
+ # Format chosen answer
39
+ chosen = example['chosen'] + "<|im_end|>\n"
40
+
41
+ # Format rejected answer
42
+ rejected = example['rejected'] + "<|im_end|>\n"
43
+
44
+ return {
45
+ "prompt": system + prompt,
46
+ "chosen": chosen,
47
+ "rejected": rejected,
48
+ }
49
+
50
+ dataset = load_dataset("flammenai/casual-conversation-DPO")['train']
51
+
52
+ # Save columns
53
+ original_columns = dataset.column_names
54
+
55
+ # Tokenizer
56
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
57
+ tokenizer.pad_token = tokenizer.eos_token
58
+ tokenizer.padding_side = "left"
59
+
60
+ # Format dataset
61
+ dataset = dataset.map(
62
+ chatml_format,
63
+ remove_columns=original_columns
64
+ )
65
+ ```
66
+
67
+ LoRA, model, and training settings:
68
+
69
+ ```python
70
+ # LoRA configuration
71
+ peft_config = LoraConfig(
72
+ r=16,
73
+ lora_alpha=16,
74
+ lora_dropout=0.05,
75
+ bias="none",
76
+ task_type="CAUSAL_LM",
77
+ target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']
78
+ )
79
+
80
+ # Model to fine-tune
81
+ model = AutoModelForCausalLM.from_pretrained(
82
+ model_name,
83
+ torch_dtype=torch.bfloat16,
84
+ load_in_4bit=True
85
+ )
86
+ model.config.use_cache = False
87
+
88
+ # Reference model
89
+ ref_model = AutoModelForCausalLM.from_pretrained(
90
+ model_name,
91
+ torch_dtype=torch.bfloat16,
92
+ load_in_4bit=True
93
+ )
94
+
95
+ # Training arguments
96
+ training_args = TrainingArguments(
97
+ per_device_train_batch_size=4,
98
+ gradient_accumulation_steps=4,
99
+ gradient_checkpointing=True,
100
+ learning_rate=5e-5,
101
+ lr_scheduler_type="cosine",
102
+ max_steps=2000,
103
+ save_strategy="no",
104
+ logging_steps=1,
105
+ output_dir=new_model,
106
+ optim="paged_adamw_32bit",
107
+ warmup_steps=100,
108
+ bf16=True,
109
+ report_to="wandb",
110
+ )
111
+
112
+ # Create DPO trainer
113
+ dpo_trainer = DPOTrainer(
114
+ model,
115
+ ref_model,
116
+ args=training_args,
117
+ train_dataset=dataset,
118
+ tokenizer=tokenizer,
119
+ peft_config=peft_config,
120
+ beta=0.1,
121
+ max_prompt_length=2048,
122
+ max_length=4096,
123
+ force_use_ref_model=True
124
+ )
125
+
126
+ # Fine-tune model with DPO
127
+ dpo_trainer.train()
128
+ ```