Added weights
Browse files- README.md +226 -0
- config.json +39 -0
- generation_config.json +6 -0
- job_new.json +0 -0
- measurement.json +0 -0
- output.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +87 -0
README.md
ADDED
@@ -0,0 +1,226 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
tags:
|
5 |
+
- finnish
|
6 |
+
- llama
|
7 |
+
inference: true
|
8 |
+
pipeline_tag: text-generation
|
9 |
+
---
|
10 |
+
This is an EXL2 quantized model in 4bpw of [Finnish-NLP/llama-7b-finnish-instruct-v0.1](https://huggingface.co/Finnish-NLP/llama-7b-finnish-instruct-v0.1) using the default calibration dataset.
|
11 |
+
|
12 |
+
Prompt format is custom (it seems to be kinda broken):
|
13 |
+
|
14 |
+
```
|
15 |
+
<|alku|> Olet tekoälyavustaja. Seuraavaksi saat kysymyksen tai tehtävän. Kirjoita vastaus parhaasi mukaan siten että se täyttää kysymyksen tai tehtävän vaatimukset.
|
16 |
+
<|ihminen|> Kysymys/Tehtävä:
|
17 |
+
{}
|
18 |
+
<|avustaja|> Vastauksesi:
|
19 |
+
<|loppu|>
|
20 |
+
```
|
21 |
+
|
22 |
+
# Original Model card:
|
23 |
+
|
24 |
+
# Llama-7b-instruct-v0.1 for Finnish
|
25 |
+
|
26 |
+
|
27 |
+
- This is an early v0.1 version release of our Instruct finetuned model from https://huggingface.co/Finnish-NLP/llama-7b-finnish
|
28 |
+
- Model was trained for 2 epochs using 11014 samples and for this release we chose checkpoint at 2500/4048 steps.
|
29 |
+
- Future DPO/SFT+DPO variants are in the pipeline.
|
30 |
+
|
31 |
+
For finetuning we used mix of the following datasets:
|
32 |
+
- LIMA from https://github.com/TurkuNLP/finnish-instructions
|
33 |
+
- Dolly from https://github.com/TurkuNLP/finnish-instructions
|
34 |
+
- OASST from https://github.com/TurkuNLP/finnish-instructions
|
35 |
+
- Heavily filtered version of Ultrachat https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized/viewer/default/train_sft + deepl translations by writing
|
36 |
+
samples to file and uploading to deepl.com to filetranslation and then parsinig the translated files back to samples
|
37 |
+
|
38 |
+
|
39 |
+
|
40 |
+
### How to use
|
41 |
+
|
42 |
+
Here is an example of using this model with Unsloth with some generation arguments you can modify:
|
43 |
+
|
44 |
+
```python
|
45 |
+
import torch
|
46 |
+
from unsloth import FastLlamaModel
|
47 |
+
|
48 |
+
max_seq_length = 2048
|
49 |
+
dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
|
50 |
+
load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
|
51 |
+
|
52 |
+
|
53 |
+
use_unsloth = True
|
54 |
+
# use_transformers = True
|
55 |
+
|
56 |
+
# LOADING MODEL USIINIG TRANSFORMERS assumes at least 16GB of memory. Tested with this configuration
|
57 |
+
# If you have less memory use load_in_4bit or load_in_8_bit as needed
|
58 |
+
if use_transformers:
|
59 |
+
major_version, minor_version = torch.cuda.get_device_capability()
|
60 |
+
model = AutoModelForCausalLM.from_pretrained("Finnish-NLP/llama-7b-finnish-instruct-v0.1", device_map='cuda:0', torch_dtype = torch.bfloat16 if major_version >=8 else torch.float16)
|
61 |
+
tokenizer = AutoTokenizer.from_pretrained("Finnish-NLP/llama-7b-finnish-instruct-v0.1")
|
62 |
+
|
63 |
+
# USING UNSLOTH, tested with load_in_4bit
|
64 |
+
if use_unsloth:
|
65 |
+
model, tokenizer = FastLlamaModel.from_pretrained(
|
66 |
+
model_name = "Finnish-NLP/llama-7b-finnish-instruct-v0.1"
|
67 |
+
max_seq_length = max_seq_length,
|
68 |
+
dtype = dtype,
|
69 |
+
load_in_4bit = load_in_4bit
|
70 |
+
)
|
71 |
+
|
72 |
+
alpaca_prompt = """<|alku|> Olet tekoälyavustaja. Seuraavaksi saat kysymyksen tai tehtävän. Kirjoita vastaus parhaasi mukaan siten että se täyttää kysymyksen tai tehtävän vaatimukset.
|
73 |
+
<|ihminen|> Kysymys/Tehtävä:
|
74 |
+
{}
|
75 |
+
<|avustaja|> Vastauksesi:
|
76 |
+
"""
|
77 |
+
|
78 |
+
sample_questions = ["Ketkä ovat Aku Ankan luona asuvat kolme ankanpoikaa?",\
|
79 |
+
"Mikä on Suomen korkein tunturi?",\
|
80 |
+
"Suomi soti Neuvostoliittoa vastaan talvisodan 1939-1940. Kuinka monta päivää sota kesti?",\
|
81 |
+
"Luettele viisi yleistä Suomessa yleisesti käytettyä pojan nimeä. Nimet:",\
|
82 |
+
"Luettele lyhyt, maksimissaan 50 sanan mittainen runo Suomesta. Runo:",\
|
83 |
+
]
|
84 |
+
|
85 |
+
from transformers import GenerationConfig
|
86 |
+
|
87 |
+
generation_config = GenerationConfig(
|
88 |
+
pad_token_id=tokenizer.eos_token_id,
|
89 |
+
eos_token_id=tokenizer.convert_tokens_to_ids("<|loppu|>"),
|
90 |
+
)
|
91 |
+
|
92 |
+
|
93 |
+
for sample_question in sample_questions:
|
94 |
+
|
95 |
+
model.eval()
|
96 |
+
|
97 |
+
inputs = tokenizer(
|
98 |
+
[
|
99 |
+
alpaca_prompt.format(
|
100 |
+
sample_question, # instruction
|
101 |
+
)
|
102 |
+
]*1, return_tensors = "pt").to("cuda")
|
103 |
+
|
104 |
+
with torch.no_grad():
|
105 |
+
generated_ids = model.generate(
|
106 |
+
input_ids=inputs["input_ids"],
|
107 |
+
attention_mask=inputs["attention_mask"],
|
108 |
+
generation_config=generation_config, **{
|
109 |
+
"temperature": 0.1,
|
110 |
+
"penalty_alpha": 0.6,
|
111 |
+
"top_k": 3,
|
112 |
+
"do_sample": True,
|
113 |
+
"repetition_penalty": 1.28,
|
114 |
+
"min_length": 10,
|
115 |
+
"max_new_tokens": 200
|
116 |
+
})
|
117 |
+
|
118 |
+
generated_text = tokenizer.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True)[0]
|
119 |
+
print(len(generated_ids[0]))
|
120 |
+
print("KYSYMYS:")
|
121 |
+
print(generated_text.split('<|avustaja|>')[0])
|
122 |
+
print("VASTAUS:")
|
123 |
+
print(generated_text.split('<|avustaja|> Vastauksesi:')[1])
|
124 |
+
print('##################################')
|
125 |
+
|
126 |
+
'''
|
127 |
+
-->
|
128 |
+
79
|
129 |
+
KYSYMYS:
|
130 |
+
<|alku|> Olet tekoälyavustaja. Seuraavaksi saat kysymyksen tai tehtävän. Kirjoita vastaus parhaasi mukaan siten että se täyttää kysymyksen tai tehtävän vaatimukset.<|ihminen|> Kysymys/Tehtävä: Aku Ankan luona asuu kolme ankanpoikaa. He ovat nimeltään:
|
131 |
+
VASTAUS:
|
132 |
+
Ankkalinnan asukkaat ovat Aku Ankka, hänen vaimonsa Iines ja heidän lapsensa Tupu, Hupu ja Lupu
|
133 |
+
##################################
|
134 |
+
65
|
135 |
+
KYSYMYS:
|
136 |
+
<|alku|> Olet tekoälyavustaja. Seuraavaksi saat kysymyksen tai tehtävän. Kirjoita vastaus parhaasi mukaan siten että se täyttää kysymyksen tai tehtävän vaatimukset.<|ihminen|> Kysymys/Tehtävä: Mikä on Suomen korkein tunturi?
|
137 |
+
VASTAUS:
|
138 |
+
Suomen korkeimmat tunturit ovat Halti (1 324 metriä) ja Saana (1 029 metriä).
|
139 |
+
##################################
|
140 |
+
80
|
141 |
+
KYSYMYS:
|
142 |
+
<|alku|> Olet tekoälyavustaja. Seuraavaksi saat kysymyksen tai tehtävän. Kirjoita vastaus parhaasi mukaan siten että se täyttää kysymyksen tai tehtävän vaatimukset.<|ihminen|> Kysymys/Tehtävä: Suomi soti Neuvostoliittoa vastaan talvisodan 1939-1940. Kuinka monta päivää sota kesti?
|
143 |
+
VASTAUS:
|
144 |
+
Talvisodan aikana Neuvostoliitto hyökkäsi Suomeen 30. marraskuuta ja 13. maaliskuuta välisenä aikana. Tämä oli lyhyt sota, joka kesti 105 päivää.
|
145 |
+
##################################
|
146 |
+
87
|
147 |
+
KYSYMYS:
|
148 |
+
<|alku|> Olet tekoälyavustaja. Seuraavaksi saat kysymyksen tai tehtävän. Kirjoita vastaus parhaasi mukaan siten että se täyttää kysymyksen tai tehtävän vaatimukset.<|ihminen|> Kysymys/Tehtävä: Luettele viisi yleistä Suomessa yleisesti käytettyä pojan nimeä. Nimet:
|
149 |
+
VASTAUS:
|
150 |
+
Suomessa on monia yleisiä poikien nimiä, mutta tässä on muutamia suosittuja: 1. Eemeli 2 Onni 3 Eino 4 Väinö 5 Artturi
|
151 |
+
##################################
|
152 |
+
63
|
153 |
+
KYSYMYS:
|
154 |
+
<|alku|> Olet tekoälyavustaja. Seuraavaksi saat kysymyksen tai tehtävän. Kirjoita vastaus parhaasi mukaan siten että se täyttää kysymyksen tai tehtävän vaatimukset.<|ihminen|> Kysymys/Tehtävä: Luettele lyhyt, maksimissaan 50 sanan mittainen runo Suomesta. Runo:
|
155 |
+
VASTAUS:
|
156 |
+
Suomen talvi on kylmä, kesä on lyhyt, mutta luonto on kaunis.
|
157 |
+
'''
|
158 |
+
|
159 |
+
```
|
160 |
+
|
161 |
+
### Limitations and bias
|
162 |
+
|
163 |
+
The training data used for this model contains a lot of content from the internet, which is far from neutral.
|
164 |
+
Therefore, the model can have biased predictions. This bias will also affect all fine-tuned versions of this model.
|
165 |
+
To reduce toxic content, the pretrained version of thiis model was trained with dataset filtered with a toxicity classifier but it cannot truly eliminate all toxic text.
|
166 |
+
|
167 |
+
### Finetuning
|
168 |
+
|
169 |
+
Training was conducted on RTX 4080 using Unsloth framework https://github.com/unslothai/unsloth \
|
170 |
+
Training script is available in this repo.
|
171 |
+
|
172 |
+
|
173 |
+
## Evaluation results
|
174 |
+
|
175 |
+
This model was evaluated using [FIN-bench by TurkuNLP](https://github.com/TurkuNLP/FIN-bench) with zero-shot setting, but \
|
176 |
+
the evaluation script had some problems running succesfully, so the results reported below should perhaps be viewed with some caution.
|
177 |
+
|
178 |
+
[llama-7b-finnish-instruct-v0.1](https://huggingface.co/Finnish-NLP/llama-7b-finnish-instruct-v0.1):
|
179 |
+
|
180 |
+
| Task |Version| Metric |Value | |Stderr|
|
181 |
+
|------------------------------------------------|------:|---------------------|-----:|---|-----:|
|
182 |
+
|bigbench_analogies | 0|multiple_choice_grade|0.5000|± |0.0440|
|
183 |
+
|bigbench_arithmetic_1_digit_addition | 0|multiple_choice_grade|0.4800|± |0.0502|
|
184 |
+
|bigbench_arithmetic_1_digit_division | 0|multiple_choice_grade|0.5652|± |0.1057|
|
185 |
+
|bigbench_arithmetic_1_digit_multiplication | 0|multiple_choice_grade|0.5000|± |0.0503|
|
186 |
+
|bigbench_arithmetic_1_digit_subtraction | 0|multiple_choice_grade|0.6700|± |0.0473|
|
187 |
+
|bigbench_arithmetic_2_digit_addition | 0|multiple_choice_grade|0.4000|± |0.0492|
|
188 |
+
|bigbench_arithmetic_2_digit_division | 0|multiple_choice_grade|0.5400|± |0.0501|
|
189 |
+
|bigbench_arithmetic_2_digit_multiplication | 0|multiple_choice_grade|0.2700|± |0.0446|
|
190 |
+
|bigbench_arithmetic_2_digit_subtraction | 0|multiple_choice_grade|0.4800|± |0.0502|
|
191 |
+
|bigbench_arithmetic_3_digit_addition | 0|multiple_choice_grade|0.4100|± |0.0494|
|
192 |
+
|bigbench_arithmetic_3_digit_division | 0|multiple_choice_grade|0.2800|± |0.0451|
|
193 |
+
|bigbench_arithmetic_3_digit_multiplication | 0|multiple_choice_grade|0.2600|± |0.0441|
|
194 |
+
|bigbench_arithmetic_3_digit_subtraction | 0|multiple_choice_grade|0.5300|± |0.0502|
|
195 |
+
|bigbench_arithmetic_4_digit_addition | 0|multiple_choice_grade|0.3400|± |0.0476|
|
196 |
+
|bigbench_arithmetic_4_digit_division | 0|multiple_choice_grade|0.3300|± |0.0473|
|
197 |
+
|bigbench_arithmetic_4_digit_multiplication | 0|multiple_choice_grade|0.2100|± |0.0409|
|
198 |
+
|bigbench_arithmetic_4_digit_subtraction | 0|multiple_choice_grade|0.6000|± |0.0492|
|
199 |
+
|bigbench_arithmetic_5_digit_addition | 0|multiple_choice_grade|0.5600|± |0.0499|
|
200 |
+
|bigbench_arithmetic_5_digit_division | 0|multiple_choice_grade|0.2300|± |0.0423|
|
201 |
+
|bigbench_arithmetic_5_digit_multiplication | 0|multiple_choice_grade|0.2500|± |0.0435|
|
202 |
+
|bigbench_arithmetic_5_digit_subtraction | 0|multiple_choice_grade|0.5600|± |0.0499|
|
203 |
+
|bigbench_cause_and_effect_one_sentence | 0|multiple_choice_grade|0.4902|± |0.0707|
|
204 |
+
|bigbench_cause_and_effect_one_sentence_no_prompt| 0|multiple_choice_grade|0.9020|± |0.0421|
|
205 |
+
|bigbench_cause_and_effect_two_sentences | 0|multiple_choice_grade|0.3922|± |0.0690|
|
206 |
+
|bigbench_emotions | 0|multiple_choice_grade|0.2313|± |0.0334|
|
207 |
+
|bigbench_empirical_judgments | 0|multiple_choice_grade|0.3535|± |0.0483|
|
208 |
+
|bigbench_general_knowledge | 0|multiple_choice_grade|0.3857|± |0.0586|
|
209 |
+
|bigbench_hhh_alignment_harmless | 0|multiple_choice_grade|0.3966|± |0.0648|
|
210 |
+
|bigbench_hhh_alignment_helpful | 0|multiple_choice_grade|0.3220|± |0.0614|
|
211 |
+
|bigbench_hhh_alignment_honest | 0|multiple_choice_grade|0.3898|± |0.0640|
|
212 |
+
|bigbench_hhh_alignment_other | 0|multiple_choice_grade|0.5814|± |0.0761|
|
213 |
+
|bigbench_intent_recognition | 0|multiple_choice_grade|0.2211|± |0.0158|
|
214 |
+
|bigbench_misconceptions | 0|multiple_choice_grade|0.5149|± |0.0433|
|
215 |
+
|bigbench_paraphrase | 0|multiple_choice_grade|0.5400|± |0.0353|
|
216 |
+
|bigbench_sentence_ambiguity | 0|multiple_choice_grade|0.4500|± |0.0648|
|
217 |
+
|bigbench_similarities_abstraction | 0|multiple_choice_grade|0.5789|± |0.0570|
|
218 |
+
|
219 |
+
|
220 |
+
|
221 |
+
## Team Members
|
222 |
+
|
223 |
+
- Aapo Tanskanen, [Hugging Face profile](https://huggingface.co/aapot), [LinkedIn profile](https://www.linkedin.com/in/aapotanskanen/)
|
224 |
+
- Rasmus Toivanen, [Hugging Face profile](https://huggingface.co/RASMUS), [LinkedIn profile](https://www.linkedin.com/in/rasmustoivanen/)
|
225 |
+
|
226 |
+
Feel free to contact us for more details 🤗
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "new_model_merged_vitun_hyva_2",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 64260,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 11008,
|
14 |
+
"max_position_embeddings": 2048,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
+
"num_key_value_heads": 32,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rms_norm_eps": 1e-06,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float16",
|
25 |
+
"transformers_version": "4.37.1",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 64262,
|
28 |
+
"quantization_config": {
|
29 |
+
"quant_method": "exl2",
|
30 |
+
"version": "0.0.15",
|
31 |
+
"bits": 4.0,
|
32 |
+
"head_bits": 6,
|
33 |
+
"calibration": {
|
34 |
+
"rows": 100,
|
35 |
+
"length": 2048,
|
36 |
+
"dataset": "(default)"
|
37 |
+
}
|
38 |
+
}
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.37.1"
|
6 |
+
}
|
job_new.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
measurement.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
output.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e883256daa658041efa335e555a5d39749893b06b11683fff6961c47eb86df3
|
3 |
+
size 3973591240
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|loppu|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<PAD>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"64256": {
|
30 |
+
"content": "<|alku|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": false
|
36 |
+
},
|
37 |
+
"64257": {
|
38 |
+
"content": "<PAD>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"64258": {
|
46 |
+
"content": "<|ihminen|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": true,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": false
|
52 |
+
},
|
53 |
+
"64259": {
|
54 |
+
"content": "<|avustaja|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": true,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": false
|
60 |
+
},
|
61 |
+
"64260": {
|
62 |
+
"content": "<|loppu|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"64261": {
|
70 |
+
"content": "\n",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
}
|
77 |
+
},
|
78 |
+
"bos_token": "<s>",
|
79 |
+
"clean_up_tokenization_spaces": true,
|
80 |
+
"eos_token": "<|loppu|>",
|
81 |
+
"model_max_length": 2048,
|
82 |
+
"pad_token": "<PAD>",
|
83 |
+
"sp_model_kwargs": {},
|
84 |
+
"tokenizer_class": "LlamaTokenizer",
|
85 |
+
"unk_token": "<unk>",
|
86 |
+
"use_default_system_prompt": false
|
87 |
+
}
|