Text Classification
Transformers
Safetensors
English
llama
moderation
toxicity
content-moderation
safety
quark
multi-label-classification
jigsaw
hate-speech
italian-ai
text-embeddings-inference
Instructions to use ThingAI/Quark-Mod with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ThingAI/Quark-Mod with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ThingAI/Quark-Mod")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("ThingAI/Quark-Mod") model = AutoModelForSequenceClassification.from_pretrained("ThingAI/Quark-Mod") - Notebooks
- Google Colab
- Kaggle
Upload 6 files
Browse files- chat_template.jinja +8 -0
- config.json +57 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +34 -0
- training_args.bin +3 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{% if message['role'] == 'system' %}<|system|>
|
| 2 |
+
{{ message['content'] }}
|
| 3 |
+
{% elif message['role'] == 'user' %}<|user|>
|
| 4 |
+
{{ message['content'] }}
|
| 5 |
+
{% elif message['role'] == 'assistant' %}<|assistant|>
|
| 6 |
+
{{ message['content'] }}{% if not loop.last %}
|
| 7 |
+
{% endif %}{% endif %}{% endfor %}{% if messages[-1]['role'] != 'assistant' %}<|assistant|>
|
| 8 |
+
{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": true,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}<|system|>\n{{ message['content'] }}\n{% elif message['role'] == 'user' %}<|user|>\n{{ message['content'] }}\n{% elif message['role'] == 'assistant' %}<|assistant|>\n{{ message['content'] }}{% if not loop.last %}\n{% endif %}{% endif %}{% endfor %}{% if messages[-1]['role'] != 'assistant' %}<|assistant|>\n{% endif %}",
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"head_dim": 64,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_dropout": 0.0,
|
| 14 |
+
"hidden_size": 576,
|
| 15 |
+
"id2label": {
|
| 16 |
+
"0": "LABEL_0",
|
| 17 |
+
"1": "LABEL_1",
|
| 18 |
+
"2": "LABEL_2",
|
| 19 |
+
"3": "LABEL_3",
|
| 20 |
+
"4": "LABEL_4",
|
| 21 |
+
"5": "LABEL_5",
|
| 22 |
+
"6": "LABEL_6",
|
| 23 |
+
"7": "LABEL_7",
|
| 24 |
+
"8": "LABEL_8"
|
| 25 |
+
},
|
| 26 |
+
"initializer_range": 0.02,
|
| 27 |
+
"intermediate_size": 1536,
|
| 28 |
+
"label2id": {
|
| 29 |
+
"LABEL_0": 0,
|
| 30 |
+
"LABEL_1": 1,
|
| 31 |
+
"LABEL_2": 2,
|
| 32 |
+
"LABEL_3": 3,
|
| 33 |
+
"LABEL_4": 4,
|
| 34 |
+
"LABEL_5": 5,
|
| 35 |
+
"LABEL_6": 6,
|
| 36 |
+
"LABEL_7": 7,
|
| 37 |
+
"LABEL_8": 8
|
| 38 |
+
},
|
| 39 |
+
"max_position_embeddings": 2048,
|
| 40 |
+
"mlp_bias": false,
|
| 41 |
+
"model_type": "llama",
|
| 42 |
+
"num_attention_heads": 9,
|
| 43 |
+
"num_hidden_layers": 30,
|
| 44 |
+
"num_key_value_heads": 3,
|
| 45 |
+
"pad_token_id": 0,
|
| 46 |
+
"pretraining_tp": 1,
|
| 47 |
+
"problem_type": "multi_label_classification",
|
| 48 |
+
"rms_norm_eps": 1e-05,
|
| 49 |
+
"rope_parameters": {
|
| 50 |
+
"rope_theta": 10000.0,
|
| 51 |
+
"rope_type": "default"
|
| 52 |
+
},
|
| 53 |
+
"tie_word_embeddings": true,
|
| 54 |
+
"transformers_version": "5.6.0",
|
| 55 |
+
"use_cache": false,
|
| 56 |
+
"vocab_size": 49152
|
| 57 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b726ffde07064122430a175ad2c857608bd5c45dae2d0fe13e01f3d5dc12731
|
| 3 |
+
size 269176032
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|endoftext|>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|endoftext|>",
|
| 10 |
+
"<|im_start|>",
|
| 11 |
+
"<|im_end|>",
|
| 12 |
+
"<repo_name>",
|
| 13 |
+
"<reponame>",
|
| 14 |
+
"<file_sep>",
|
| 15 |
+
"<filename>",
|
| 16 |
+
"<gh_stars>",
|
| 17 |
+
"<issue_start>",
|
| 18 |
+
"<issue_comment>",
|
| 19 |
+
"<issue_closed>",
|
| 20 |
+
"<jupyter_start>",
|
| 21 |
+
"<jupyter_text>",
|
| 22 |
+
"<jupyter_code>",
|
| 23 |
+
"<jupyter_output>",
|
| 24 |
+
"<jupyter_script>",
|
| 25 |
+
"<empty_output>"
|
| 26 |
+
],
|
| 27 |
+
"is_local": false,
|
| 28 |
+
"local_files_only": false,
|
| 29 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 30 |
+
"pad_token": "<|endoftext|>",
|
| 31 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 32 |
+
"unk_token": "<|endoftext|>",
|
| 33 |
+
"vocab_size": 49152
|
| 34 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f7912ca9205fada1932370cf3489fac77492e8b90fc4c3a7facf86f2d0db441
|
| 3 |
+
size 5265
|