Initial commit: Uploading project files
Browse files- Dubs/v0.0.2/P_C/checkpoint-110500/README.md +202 -0
- Dubs/v0.0.2/P_C/checkpoint-110500/adapter_config.json +32 -0
- Dubs/v0.0.2/P_C/checkpoint-110500/adapter_model.safetensors +3 -0
- Dubs/v0.0.2/P_C/checkpoint-110500/added_tokens.json +13 -0
- Dubs/v0.0.2/P_C/checkpoint-110500/optimizer.pt +3 -0
- Dubs/v0.0.2/P_C/checkpoint-110500/rng_state.pth +3 -0
- Dubs/v0.0.2/P_C/checkpoint-110500/scheduler.pt +3 -0
- Dubs/v0.0.2/P_C/checkpoint-110500/special_tokens_map.json +30 -0
- Dubs/v0.0.2/P_C/checkpoint-110500/tokenizer.json +0 -0
- Dubs/v0.0.2/P_C/checkpoint-110500/tokenizer.model +3 -0
- Dubs/v0.0.2/P_C/checkpoint-110500/tokenizer_config.json +132 -0
- Dubs/v0.0.2/P_C/checkpoint-110500/trainer_state.json +0 -0
- Dubs/v0.0.2/P_C/checkpoint-110500/training_args.bin +3 -0
- Dubs/v0.0.2/P_C/runs/Dec12_18-26-58_a2e074eee72a/events.out.tfevents.1734028640.a2e074eee72a.103.0 +3 -0
- Dubs/v0.0.2/P_C/runs/Dec12_18-26-58_a2e074eee72a/events.out.tfevents.1734062008.a2e074eee72a.103.1 +3 -0
- Dubs/v0.0.2/P_C/runs/Dec13_07-35-37_a2e074eee72a/events.out.tfevents.1734076130.a2e074eee72a.246.0 +3 -0
- Dubs/v0.0.2/adapter/README.md +202 -0
- Dubs/v0.0.2/adapter/adapter_config.json +32 -0
- Dubs/v0.0.2/adapter/adapter_model.safetensors +3 -0
- Dubs/v0.0.2/adapter/added_tokens.json +13 -0
- Dubs/v0.0.2/adapter/special_tokens_map.json +30 -0
- Dubs/v0.0.2/adapter/tokenizer.json +0 -0
- Dubs/v0.0.2/adapter/tokenizer.model +3 -0
- Dubs/v0.0.2/adapter/tokenizer_config.json +132 -0
- Dubs/v0.0.2/full_model/added_tokens.json +13 -0
- Dubs/v0.0.2/full_model/config.json +139 -0
- Dubs/v0.0.2/full_model/generation_config.json +11 -0
- Dubs/v0.0.2/full_model/model-00001-of-00002.safetensors +3 -0
- Dubs/v0.0.2/full_model/model-00002-of-00002.safetensors +3 -0
- Dubs/v0.0.2/full_model/model.safetensors.index.json +202 -0
- Dubs/v0.0.2/full_model/special_tokens_map.json +24 -0
- Dubs/v0.0.2/full_model/tokenizer.json +0 -0
- Dubs/v0.0.2/full_model/tokenizer.model +3 -0
- Dubs/v0.0.2/full_model/tokenizer_config.json +132 -0
Dubs/v0.0.2/P_C/checkpoint-110500/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: /content/Ai_Reboot/Dubs/v0.0.1/full_model
|
3 |
+
library_name: peft
|
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 |
+
|
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]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.14.0
|
Dubs/v0.0.2/P_C/checkpoint-110500/adapter_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": null,
|
5 |
+
"bias": "none",
|
6 |
+
"eva_config": null,
|
7 |
+
"exclude_modules": null,
|
8 |
+
"fan_in_fan_out": false,
|
9 |
+
"inference_mode": true,
|
10 |
+
"init_lora_weights": true,
|
11 |
+
"layer_replication": null,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 32,
|
16 |
+
"lora_bias": false,
|
17 |
+
"lora_dropout": 0.1,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 128,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"self_attn.qkv_proj",
|
27 |
+
"self_attn.o_proj"
|
28 |
+
],
|
29 |
+
"task_type": "CAUSAL_LM",
|
30 |
+
"use_dora": false,
|
31 |
+
"use_rslora": false
|
32 |
+
}
|
Dubs/v0.0.2/P_C/checkpoint-110500/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6e172631ef0846f006fc71a5abbedc6a0fbd584fcac8db7a1eb073ecbe87f6f
|
3 |
+
size 302009760
|
Dubs/v0.0.2/P_C/checkpoint-110500/added_tokens.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|assistant|>": 32001,
|
3 |
+
"<|endoftext|>": 32000,
|
4 |
+
"<|end|>": 32007,
|
5 |
+
"<|placeholder1|>": 32002,
|
6 |
+
"<|placeholder2|>": 32003,
|
7 |
+
"<|placeholder3|>": 32004,
|
8 |
+
"<|placeholder4|>": 32005,
|
9 |
+
"<|placeholder5|>": 32008,
|
10 |
+
"<|placeholder6|>": 32009,
|
11 |
+
"<|system|>": 32006,
|
12 |
+
"<|user|>": 32010
|
13 |
+
}
|
Dubs/v0.0.2/P_C/checkpoint-110500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f1018e177e17643bbdc00008697f05734fc57724556faf5c6ffb911e2a4c503
|
3 |
+
size 604059642
|
Dubs/v0.0.2/P_C/checkpoint-110500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9e653d75495813d9511315609a824df76517dcae2e218b6fcf042c7339b5ffa
|
3 |
+
size 14244
|
Dubs/v0.0.2/P_C/checkpoint-110500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5442b8284fe19b0ce834e345da5bd8fbeb57a04d2ae2ae4f8556bad3ffc48b92
|
3 |
+
size 1064
|
Dubs/v0.0.2/P_C/checkpoint-110500/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
Dubs/v0.0.2/P_C/checkpoint-110500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
Dubs/v0.0.2/P_C/checkpoint-110500/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
Dubs/v0.0.2/P_C/checkpoint-110500/tokenizer_config.json
ADDED
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": true,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|endoftext|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|assistant|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": true,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<|placeholder1|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": true,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "<|placeholder2|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": true,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "<|placeholder3|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": true,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "<|placeholder4|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": true,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "<|system|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": true,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<|end|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": true,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "<|placeholder5|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": true,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"32009": {
|
103 |
+
"content": "<|placeholder6|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": true,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"32010": {
|
111 |
+
"content": "<|user|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": true,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
}
|
118 |
+
},
|
119 |
+
"bos_token": "<s>",
|
120 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
121 |
+
"clean_up_tokenization_spaces": false,
|
122 |
+
"eos_token": "<|endoftext|>",
|
123 |
+
"extra_special_tokens": {},
|
124 |
+
"legacy": false,
|
125 |
+
"model_max_length": 131072,
|
126 |
+
"pad_token": "<|endoftext|>",
|
127 |
+
"padding_side": "right",
|
128 |
+
"sp_model_kwargs": {},
|
129 |
+
"tokenizer_class": "LlamaTokenizer",
|
130 |
+
"unk_token": "<unk>",
|
131 |
+
"use_default_system_prompt": false
|
132 |
+
}
|
Dubs/v0.0.2/P_C/checkpoint-110500/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
Dubs/v0.0.2/P_C/checkpoint-110500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a995f08932ce32ef111d360bd1232195cd9afc3abe84bde6820dcbc5d049dbb1
|
3 |
+
size 5624
|
Dubs/v0.0.2/P_C/runs/Dec12_18-26-58_a2e074eee72a/events.out.tfevents.1734028640.a2e074eee72a.103.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae624ac5174cbc32127fa2c584ec2231140c7b26b82f8672809d66c2a23f1716
|
3 |
+
size 956721
|
Dubs/v0.0.2/P_C/runs/Dec12_18-26-58_a2e074eee72a/events.out.tfevents.1734062008.a2e074eee72a.103.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:044cd4d4b34a098c1dd8feceba7bd97eebe71b04f4144b58ac4e33da737e0b19
|
3 |
+
size 378656
|
Dubs/v0.0.2/P_C/runs/Dec13_07-35-37_a2e074eee72a/events.out.tfevents.1734076130.a2e074eee72a.246.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb6381580b6eb3a6efbac8b074e6b962aaa597bff7f8b53ffb937c6daf445422
|
3 |
+
size 9115
|
Dubs/v0.0.2/adapter/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: /content/Ai_Reboot/Dubs/v0.0.1/full_model
|
3 |
+
library_name: peft
|
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 |
+
|
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]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.14.0
|
Dubs/v0.0.2/adapter/adapter_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": null,
|
5 |
+
"bias": "none",
|
6 |
+
"eva_config": null,
|
7 |
+
"exclude_modules": null,
|
8 |
+
"fan_in_fan_out": false,
|
9 |
+
"inference_mode": true,
|
10 |
+
"init_lora_weights": true,
|
11 |
+
"layer_replication": null,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 32,
|
16 |
+
"lora_bias": false,
|
17 |
+
"lora_dropout": 0.1,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 128,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"self_attn.qkv_proj",
|
27 |
+
"self_attn.o_proj"
|
28 |
+
],
|
29 |
+
"task_type": "CAUSAL_LM",
|
30 |
+
"use_dora": false,
|
31 |
+
"use_rslora": false
|
32 |
+
}
|
Dubs/v0.0.2/adapter/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ab4cb467fe5f7883fe36dbd1667b85727921c4be938fbd21df15296fb4b8ba0
|
3 |
+
size 302009760
|
Dubs/v0.0.2/adapter/added_tokens.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|assistant|>": 32001,
|
3 |
+
"<|endoftext|>": 32000,
|
4 |
+
"<|end|>": 32007,
|
5 |
+
"<|placeholder1|>": 32002,
|
6 |
+
"<|placeholder2|>": 32003,
|
7 |
+
"<|placeholder3|>": 32004,
|
8 |
+
"<|placeholder4|>": 32005,
|
9 |
+
"<|placeholder5|>": 32008,
|
10 |
+
"<|placeholder6|>": 32009,
|
11 |
+
"<|system|>": 32006,
|
12 |
+
"<|user|>": 32010
|
13 |
+
}
|
Dubs/v0.0.2/adapter/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
Dubs/v0.0.2/adapter/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
Dubs/v0.0.2/adapter/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
Dubs/v0.0.2/adapter/tokenizer_config.json
ADDED
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": true,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|endoftext|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|assistant|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": true,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<|placeholder1|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": true,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "<|placeholder2|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": true,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "<|placeholder3|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": true,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "<|placeholder4|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": true,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "<|system|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": true,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<|end|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": true,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "<|placeholder5|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": true,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"32009": {
|
103 |
+
"content": "<|placeholder6|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": true,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"32010": {
|
111 |
+
"content": "<|user|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": true,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
}
|
118 |
+
},
|
119 |
+
"bos_token": "<s>",
|
120 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
121 |
+
"clean_up_tokenization_spaces": false,
|
122 |
+
"eos_token": "<|endoftext|>",
|
123 |
+
"extra_special_tokens": {},
|
124 |
+
"legacy": false,
|
125 |
+
"model_max_length": 131072,
|
126 |
+
"pad_token": "<|endoftext|>",
|
127 |
+
"padding_side": "right",
|
128 |
+
"sp_model_kwargs": {},
|
129 |
+
"tokenizer_class": "LlamaTokenizer",
|
130 |
+
"unk_token": "<unk>",
|
131 |
+
"use_default_system_prompt": false
|
132 |
+
}
|
Dubs/v0.0.2/full_model/added_tokens.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|assistant|>": 32001,
|
3 |
+
"<|endoftext|>": 32000,
|
4 |
+
"<|end|>": 32007,
|
5 |
+
"<|placeholder1|>": 32002,
|
6 |
+
"<|placeholder2|>": 32003,
|
7 |
+
"<|placeholder3|>": 32004,
|
8 |
+
"<|placeholder4|>": 32005,
|
9 |
+
"<|placeholder5|>": 32008,
|
10 |
+
"<|placeholder6|>": 32009,
|
11 |
+
"<|system|>": 32006,
|
12 |
+
"<|user|>": 32010
|
13 |
+
}
|
Dubs/v0.0.2/full_model/config.json
ADDED
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Dubs_0.0.2",
|
3 |
+
"architectures": [
|
4 |
+
"Phi3ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config",
|
10 |
+
"AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM"
|
11 |
+
},
|
12 |
+
"bos_token_id": 1,
|
13 |
+
"description": "Finetuned on RayBernard/leetcode and MAsad789565/Coding_GPT4_Data",
|
14 |
+
"embd_pdrop": 0.0,
|
15 |
+
"eos_token_id": 32000,
|
16 |
+
"hidden_act": "silu",
|
17 |
+
"hidden_size": 3072,
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 8192,
|
20 |
+
"max_position_embeddings": 131072,
|
21 |
+
"model_type": "phi3",
|
22 |
+
"num_attention_heads": 32,
|
23 |
+
"num_hidden_layers": 32,
|
24 |
+
"num_key_value_heads": 32,
|
25 |
+
"original_max_position_embeddings": 4096,
|
26 |
+
"pad_token_id": 32000,
|
27 |
+
"resid_pdrop": 0.0,
|
28 |
+
"rms_norm_eps": 1e-05,
|
29 |
+
"rope_scaling": {
|
30 |
+
"long_factor": [
|
31 |
+
1.0700000524520874,
|
32 |
+
1.1200000047683716,
|
33 |
+
1.149999976158142,
|
34 |
+
1.4199999570846558,
|
35 |
+
1.5699999332427979,
|
36 |
+
1.7999999523162842,
|
37 |
+
2.129999876022339,
|
38 |
+
2.129999876022339,
|
39 |
+
3.009999990463257,
|
40 |
+
5.910000324249268,
|
41 |
+
6.950000286102295,
|
42 |
+
9.070000648498535,
|
43 |
+
9.930000305175781,
|
44 |
+
10.710000038146973,
|
45 |
+
11.130000114440918,
|
46 |
+
14.609999656677246,
|
47 |
+
15.409998893737793,
|
48 |
+
19.809999465942383,
|
49 |
+
37.279998779296875,
|
50 |
+
38.279998779296875,
|
51 |
+
38.599998474121094,
|
52 |
+
40.12000274658203,
|
53 |
+
46.20000457763672,
|
54 |
+
50.940006256103516,
|
55 |
+
53.66000747680664,
|
56 |
+
54.9373893737793,
|
57 |
+
56.89738845825195,
|
58 |
+
57.28738784790039,
|
59 |
+
59.98738479614258,
|
60 |
+
60.86738586425781,
|
61 |
+
60.887386322021484,
|
62 |
+
61.71739196777344,
|
63 |
+
62.91739273071289,
|
64 |
+
62.957393646240234,
|
65 |
+
63.41739273071289,
|
66 |
+
63.8173942565918,
|
67 |
+
63.83739471435547,
|
68 |
+
63.897396087646484,
|
69 |
+
63.93739700317383,
|
70 |
+
64.06739807128906,
|
71 |
+
64.11434936523438,
|
72 |
+
64.12435150146484,
|
73 |
+
64.15435028076172,
|
74 |
+
64.19435119628906,
|
75 |
+
64.24435424804688,
|
76 |
+
64.57435607910156,
|
77 |
+
64.69000244140625,
|
78 |
+
64.76000213623047
|
79 |
+
],
|
80 |
+
"short_factor": [
|
81 |
+
1.1,
|
82 |
+
1.1,
|
83 |
+
1.1,
|
84 |
+
1.3000000000000003,
|
85 |
+
1.3500000000000003,
|
86 |
+
1.3500000000000003,
|
87 |
+
1.4000000000000004,
|
88 |
+
1.5500000000000005,
|
89 |
+
2.000000000000001,
|
90 |
+
2.000000000000001,
|
91 |
+
2.000000000000001,
|
92 |
+
2.000000000000001,
|
93 |
+
2.000000000000001,
|
94 |
+
2.000000000000001,
|
95 |
+
2.000000000000001,
|
96 |
+
2.000000000000001,
|
97 |
+
2.000000000000001,
|
98 |
+
2.000000000000001,
|
99 |
+
2.000000000000001,
|
100 |
+
2.000000000000001,
|
101 |
+
2.000000000000001,
|
102 |
+
2.000000000000001,
|
103 |
+
2.000000000000001,
|
104 |
+
2.000000000000001,
|
105 |
+
2.000000000000001,
|
106 |
+
2.0500000000000007,
|
107 |
+
2.0500000000000007,
|
108 |
+
2.0500000000000007,
|
109 |
+
2.0500000000000007,
|
110 |
+
2.0500000000000007,
|
111 |
+
2.0500000000000007,
|
112 |
+
2.1000000000000005,
|
113 |
+
2.1000000000000005,
|
114 |
+
2.1500000000000004,
|
115 |
+
2.25,
|
116 |
+
2.25,
|
117 |
+
2.25,
|
118 |
+
2.25,
|
119 |
+
2.25,
|
120 |
+
2.3999999999999995,
|
121 |
+
2.4499999999999993,
|
122 |
+
2.499999999999999,
|
123 |
+
2.6999999999999984,
|
124 |
+
2.6999999999999984,
|
125 |
+
2.7499999999999982,
|
126 |
+
2.799999999999998,
|
127 |
+
2.8999999999999977,
|
128 |
+
3.049999999999997
|
129 |
+
],
|
130 |
+
"type": "longrope"
|
131 |
+
},
|
132 |
+
"rope_theta": 10000.0,
|
133 |
+
"sliding_window": 262144,
|
134 |
+
"tie_word_embeddings": false,
|
135 |
+
"torch_dtype": "float16",
|
136 |
+
"transformers_version": "4.47.0",
|
137 |
+
"use_cache": true,
|
138 |
+
"vocab_size": 32064
|
139 |
+
}
|
Dubs/v0.0.2/full_model/generation_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": [
|
5 |
+
32000,
|
6 |
+
32001,
|
7 |
+
32007
|
8 |
+
],
|
9 |
+
"pad_token_id": 32000,
|
10 |
+
"transformers_version": "4.47.0"
|
11 |
+
}
|
Dubs/v0.0.2/full_model/model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91b31a3ce5fa4205069b877b3fa1fddb062da5ab32ae148eddfa0796079be8da
|
3 |
+
size 4972489200
|
Dubs/v0.0.2/full_model/model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4134ffe1adc5710e27927489ff6021862bef37f388f1d96210a66b6240142cad
|
3 |
+
size 2669692488
|
Dubs/v0.0.2/full_model/model.safetensors.index.json
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 7642159104
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
11 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
12 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
13 |
+
"model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
14 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
15 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
16 |
+
"model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
17 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
18 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
19 |
+
"model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
20 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
21 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
22 |
+
"model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
23 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
24 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
25 |
+
"model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
26 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
27 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
28 |
+
"model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
29 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
30 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
31 |
+
"model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
32 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
33 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
34 |
+
"model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
35 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
36 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
37 |
+
"model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
38 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
39 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
40 |
+
"model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
41 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
42 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
43 |
+
"model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
44 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
45 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
46 |
+
"model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
47 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
48 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
49 |
+
"model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
50 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
51 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
52 |
+
"model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
53 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
54 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
55 |
+
"model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
56 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
57 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
58 |
+
"model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
59 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
60 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
61 |
+
"model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
62 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
63 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
64 |
+
"model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
65 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
66 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
67 |
+
"model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
68 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
69 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
70 |
+
"model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
71 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
72 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
73 |
+
"model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
74 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
75 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
76 |
+
"model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
77 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
78 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
79 |
+
"model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
80 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
81 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
82 |
+
"model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
83 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
84 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
85 |
+
"model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
86 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
87 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
88 |
+
"model.layers.20.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
89 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
90 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
91 |
+
"model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
92 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
93 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
94 |
+
"model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
95 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
96 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
97 |
+
"model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
98 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
99 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
100 |
+
"model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
101 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
102 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
103 |
+
"model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
104 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
105 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
106 |
+
"model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
107 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
108 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
109 |
+
"model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
110 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
111 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
112 |
+
"model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
113 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
114 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
115 |
+
"model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
116 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
117 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
118 |
+
"model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
119 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
120 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
121 |
+
"model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
122 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
123 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
124 |
+
"model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
125 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
126 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
127 |
+
"model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
128 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
129 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
130 |
+
"model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
131 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
132 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
133 |
+
"model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
134 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
135 |
+
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
136 |
+
"model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
137 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
138 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
139 |
+
"model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
140 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
141 |
+
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
142 |
+
"model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
143 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
144 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
145 |
+
"model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
146 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
147 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
148 |
+
"model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
149 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
150 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
151 |
+
"model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
152 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
153 |
+
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
154 |
+
"model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
155 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
156 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
157 |
+
"model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
158 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
159 |
+
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
160 |
+
"model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
161 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
162 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
163 |
+
"model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
164 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
165 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
166 |
+
"model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
167 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
168 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
169 |
+
"model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
170 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
171 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
172 |
+
"model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
173 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
174 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
175 |
+
"model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
176 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
177 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
178 |
+
"model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
179 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
180 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
181 |
+
"model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
182 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
183 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
184 |
+
"model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
185 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
186 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
187 |
+
"model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
188 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
189 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
190 |
+
"model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
191 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
192 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
193 |
+
"model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
194 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
195 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
196 |
+
"model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
197 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
198 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
199 |
+
"model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
200 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
201 |
+
}
|
202 |
+
}
|
Dubs/v0.0.2/full_model/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|endoftext|>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
Dubs/v0.0.2/full_model/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
Dubs/v0.0.2/full_model/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
Dubs/v0.0.2/full_model/tokenizer_config.json
ADDED
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": true,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|endoftext|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|assistant|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": true,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<|placeholder1|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": true,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "<|placeholder2|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": true,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "<|placeholder3|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": true,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "<|placeholder4|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": true,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "<|system|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": true,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<|end|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": true,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "<|placeholder5|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": true,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"32009": {
|
103 |
+
"content": "<|placeholder6|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": true,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"32010": {
|
111 |
+
"content": "<|user|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": true,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
}
|
118 |
+
},
|
119 |
+
"bos_token": "<s>",
|
120 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
121 |
+
"clean_up_tokenization_spaces": false,
|
122 |
+
"eos_token": "<|endoftext|>",
|
123 |
+
"extra_special_tokens": {},
|
124 |
+
"legacy": false,
|
125 |
+
"model_max_length": 131072,
|
126 |
+
"pad_token": "<|endoftext|>",
|
127 |
+
"padding_side": "right",
|
128 |
+
"sp_model_kwargs": {},
|
129 |
+
"tokenizer_class": "LlamaTokenizer",
|
130 |
+
"unk_token": "<unk>",
|
131 |
+
"use_default_system_prompt": false
|
132 |
+
}
|