Add LoRA checkpoint 300
Browse files- .gitattributes +1 -0
- checkpoints/checkpoint-300/README.md +209 -0
- checkpoints/checkpoint-300/adapter_config.json +39 -0
- checkpoints/checkpoint-300/adapter_model.safetensors +3 -0
- checkpoints/checkpoint-300/special_tokens_map.json +23 -0
- checkpoints/checkpoint-300/tokenizer.json +3 -0
- checkpoints/checkpoint-300/tokenizer_config.json +183 -0
.gitattributes
CHANGED
@@ -38,3 +38,4 @@ checkpoints/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
38 |
checkpoints/checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
39 |
checkpoints/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
40 |
checkpoints/checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
38 |
checkpoints/checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
39 |
checkpoints/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
40 |
checkpoints/checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
41 |
+
checkpoints/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoints/checkpoint-300/README.md
ADDED
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: openai/gpt-oss-20b
|
3 |
+
library_name: peft
|
4 |
+
pipeline_tag: text-generation
|
5 |
+
tags:
|
6 |
+
- base_model:adapter:openai/gpt-oss-20b
|
7 |
+
- lora
|
8 |
+
- sft
|
9 |
+
- transformers
|
10 |
+
- trl
|
11 |
+
---
|
12 |
+
|
13 |
+
# Model Card for Model ID
|
14 |
+
|
15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
16 |
+
|
17 |
+
|
18 |
+
|
19 |
+
## Model Details
|
20 |
+
|
21 |
+
### Model Description
|
22 |
+
|
23 |
+
<!-- Provide a longer summary of what this model is. -->
|
24 |
+
|
25 |
+
|
26 |
+
|
27 |
+
- **Developed by:** [More Information Needed]
|
28 |
+
- **Funded by [optional]:** [More Information Needed]
|
29 |
+
- **Shared by [optional]:** [More Information Needed]
|
30 |
+
- **Model type:** [More Information Needed]
|
31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
32 |
+
- **License:** [More Information Needed]
|
33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
34 |
+
|
35 |
+
### Model Sources [optional]
|
36 |
+
|
37 |
+
<!-- Provide the basic links for the model. -->
|
38 |
+
|
39 |
+
- **Repository:** [More Information Needed]
|
40 |
+
- **Paper [optional]:** [More Information Needed]
|
41 |
+
- **Demo [optional]:** [More Information Needed]
|
42 |
+
|
43 |
+
## Uses
|
44 |
+
|
45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
46 |
+
|
47 |
+
### Direct Use
|
48 |
+
|
49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
50 |
+
|
51 |
+
[More Information Needed]
|
52 |
+
|
53 |
+
### Downstream Use [optional]
|
54 |
+
|
55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
56 |
+
|
57 |
+
[More Information Needed]
|
58 |
+
|
59 |
+
### Out-of-Scope Use
|
60 |
+
|
61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
62 |
+
|
63 |
+
[More Information Needed]
|
64 |
+
|
65 |
+
## Bias, Risks, and Limitations
|
66 |
+
|
67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
68 |
+
|
69 |
+
[More Information Needed]
|
70 |
+
|
71 |
+
### Recommendations
|
72 |
+
|
73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
74 |
+
|
75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
76 |
+
|
77 |
+
## How to Get Started with the Model
|
78 |
+
|
79 |
+
Use the code below to get started with the model.
|
80 |
+
|
81 |
+
[More Information Needed]
|
82 |
+
|
83 |
+
## Training Details
|
84 |
+
|
85 |
+
### Training Data
|
86 |
+
|
87 |
+
<!-- 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. -->
|
88 |
+
|
89 |
+
[More Information Needed]
|
90 |
+
|
91 |
+
### Training Procedure
|
92 |
+
|
93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
94 |
+
|
95 |
+
#### Preprocessing [optional]
|
96 |
+
|
97 |
+
[More Information Needed]
|
98 |
+
|
99 |
+
|
100 |
+
#### Training Hyperparameters
|
101 |
+
|
102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
103 |
+
|
104 |
+
#### Speeds, Sizes, Times [optional]
|
105 |
+
|
106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
107 |
+
|
108 |
+
[More Information Needed]
|
109 |
+
|
110 |
+
## Evaluation
|
111 |
+
|
112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
113 |
+
|
114 |
+
### Testing Data, Factors & Metrics
|
115 |
+
|
116 |
+
#### Testing Data
|
117 |
+
|
118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
119 |
+
|
120 |
+
[More Information Needed]
|
121 |
+
|
122 |
+
#### Factors
|
123 |
+
|
124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
125 |
+
|
126 |
+
[More Information Needed]
|
127 |
+
|
128 |
+
#### Metrics
|
129 |
+
|
130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
131 |
+
|
132 |
+
[More Information Needed]
|
133 |
+
|
134 |
+
### Results
|
135 |
+
|
136 |
+
[More Information Needed]
|
137 |
+
|
138 |
+
#### Summary
|
139 |
+
|
140 |
+
|
141 |
+
|
142 |
+
## Model Examination [optional]
|
143 |
+
|
144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
145 |
+
|
146 |
+
[More Information Needed]
|
147 |
+
|
148 |
+
## Environmental Impact
|
149 |
+
|
150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
151 |
+
|
152 |
+
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).
|
153 |
+
|
154 |
+
- **Hardware Type:** [More Information Needed]
|
155 |
+
- **Hours used:** [More Information Needed]
|
156 |
+
- **Cloud Provider:** [More Information Needed]
|
157 |
+
- **Compute Region:** [More Information Needed]
|
158 |
+
- **Carbon Emitted:** [More Information Needed]
|
159 |
+
|
160 |
+
## Technical Specifications [optional]
|
161 |
+
|
162 |
+
### Model Architecture and Objective
|
163 |
+
|
164 |
+
[More Information Needed]
|
165 |
+
|
166 |
+
### Compute Infrastructure
|
167 |
+
|
168 |
+
[More Information Needed]
|
169 |
+
|
170 |
+
#### Hardware
|
171 |
+
|
172 |
+
[More Information Needed]
|
173 |
+
|
174 |
+
#### Software
|
175 |
+
|
176 |
+
[More Information Needed]
|
177 |
+
|
178 |
+
## Citation [optional]
|
179 |
+
|
180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
181 |
+
|
182 |
+
**BibTeX:**
|
183 |
+
|
184 |
+
[More Information Needed]
|
185 |
+
|
186 |
+
**APA:**
|
187 |
+
|
188 |
+
[More Information Needed]
|
189 |
+
|
190 |
+
## Glossary [optional]
|
191 |
+
|
192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
193 |
+
|
194 |
+
[More Information Needed]
|
195 |
+
|
196 |
+
## More Information [optional]
|
197 |
+
|
198 |
+
[More Information Needed]
|
199 |
+
|
200 |
+
## Model Card Authors [optional]
|
201 |
+
|
202 |
+
[More Information Needed]
|
203 |
+
|
204 |
+
## Model Card Contact
|
205 |
+
|
206 |
+
[More Information Needed]
|
207 |
+
### Framework versions
|
208 |
+
|
209 |
+
- PEFT 0.17.0
|
checkpoints/checkpoint-300/adapter_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "openai/gpt-oss-20b",
|
5 |
+
"bias": "none",
|
6 |
+
"corda_config": null,
|
7 |
+
"eva_config": null,
|
8 |
+
"exclude_modules": null,
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 32,
|
17 |
+
"lora_bias": false,
|
18 |
+
"lora_dropout": 0.0,
|
19 |
+
"megatron_config": null,
|
20 |
+
"megatron_core": "megatron.core",
|
21 |
+
"modules_to_save": null,
|
22 |
+
"peft_type": "LORA",
|
23 |
+
"qalora_group_size": 16,
|
24 |
+
"r": 16,
|
25 |
+
"rank_pattern": {},
|
26 |
+
"revision": null,
|
27 |
+
"target_modules": [
|
28 |
+
"o_proj",
|
29 |
+
"k_proj",
|
30 |
+
"q_proj",
|
31 |
+
"v_proj"
|
32 |
+
],
|
33 |
+
"target_parameters": null,
|
34 |
+
"task_type": "CAUSAL_LM",
|
35 |
+
"trainable_token_indices": null,
|
36 |
+
"use_dora": false,
|
37 |
+
"use_qalora": false,
|
38 |
+
"use_rslora": false
|
39 |
+
}
|
checkpoints/checkpoint-300/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4d3040c32cf19ae3ac2e94b97c4d270cb09c4b994ff604cc8bd5f4cb983ff59
|
3 |
+
size 31876192
|
checkpoints/checkpoint-300/special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|return|>",
|
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 |
+
}
|
checkpoints/checkpoint-300/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
|
3 |
+
size 27868174
|
checkpoints/checkpoint-300/tokenizer_config.json
ADDED
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"199998": {
|
4 |
+
"content": "<|startoftext|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"199999": {
|
12 |
+
"content": "<|endoftext|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"200000": {
|
20 |
+
"content": "<|reserved_200000|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"200001": {
|
28 |
+
"content": "<|reserved_200001|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"200002": {
|
36 |
+
"content": "<|return|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"200003": {
|
44 |
+
"content": "<|constrain|>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"200004": {
|
52 |
+
"content": "<|reserved_200004|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"200005": {
|
60 |
+
"content": "<|channel|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"200006": {
|
68 |
+
"content": "<|start|>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"200007": {
|
76 |
+
"content": "<|end|>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"200008": {
|
84 |
+
"content": "<|message|>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"200009": {
|
92 |
+
"content": "<|reserved_200009|>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"200010": {
|
100 |
+
"content": "<|reserved_200010|>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"200011": {
|
108 |
+
"content": "<|reserved_200011|>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"200012": {
|
116 |
+
"content": "<|call|>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"200013": {
|
124 |
+
"content": "<|reserved_200013|>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"200014": {
|
132 |
+
"content": "<|reserved_200014|>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"200015": {
|
140 |
+
"content": "<|reserved_200015|>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"200016": {
|
148 |
+
"content": "<|reserved_200016|>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"200017": {
|
156 |
+
"content": "<|reserved_200017|>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"200018": {
|
164 |
+
"content": "<|endofprompt|>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
}
|
171 |
+
},
|
172 |
+
"bos_token": "<|startoftext|>",
|
173 |
+
"clean_up_tokenization_spaces": false,
|
174 |
+
"eos_token": "<|return|>",
|
175 |
+
"extra_special_tokens": {},
|
176 |
+
"model_input_names": [
|
177 |
+
"input_ids",
|
178 |
+
"attention_mask"
|
179 |
+
],
|
180 |
+
"model_max_length": 1000000000000000019884624838656,
|
181 |
+
"pad_token": "<|endoftext|>",
|
182 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
183 |
+
}
|