Instructions to use N8Programs/arc-tiny-transformer-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use N8Programs/arc-tiny-transformer-models with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("N8Programs/arc-tiny-transformer-models", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add 50m-3.0b checkpoint
Browse files- 50m-3.0b/config.json +26 -0
- 50m-3.0b/generation_config.json +5 -0
- 50m-3.0b/model.safetensors +3 -0
- 50m-3.0b/tokenizer.json +1 -0
- 50m-3.0b/tokenizer_config.json +16 -0
50m-3.0b/config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"model_type": "qwen3",
|
| 6 |
+
"vocab_size": 19,
|
| 7 |
+
"hidden_size": 512,
|
| 8 |
+
"num_hidden_layers": 16,
|
| 9 |
+
"intermediate_size": 1536,
|
| 10 |
+
"num_attention_heads": 4,
|
| 11 |
+
"num_key_value_heads": 2,
|
| 12 |
+
"head_dim": 128,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"rms_norm_eps": 1e-06,
|
| 15 |
+
"max_position_embeddings": 16384,
|
| 16 |
+
"rope_theta": 1000000.0,
|
| 17 |
+
"rope_scaling": null,
|
| 18 |
+
"attention_bias": false,
|
| 19 |
+
"attention_dropout": 0.0,
|
| 20 |
+
"tie_word_embeddings": false,
|
| 21 |
+
"use_cache": true,
|
| 22 |
+
"bos_token_id": 1,
|
| 23 |
+
"eos_token_id": 2,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"torch_dtype": "float32"
|
| 26 |
+
}
|
50m-3.0b/generation_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"pad_token_id": 0
|
| 5 |
+
}
|
50m-3.0b/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fd2d8c8f320be3debec07a1008d38e038e3c3401fdb292255dfc0b48bc77b43
|
| 3 |
+
size 201507992
|
50m-3.0b/tokenizer.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"version": "1.0", "truncation": null, "padding": null, "added_tokens": [{"id": 0, "content": "<PAD>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 1, "content": "<BOS>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 2, "content": "<EOS>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 3, "content": "<BEGIN_GRID>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 4, "content": "<END_GRID>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 5, "content": "<BEGIN_ROW>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 6, "content": "<END_ROW>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 7, "content": "<INPUT>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 8, "content": "<OUTPUT>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}, {"id": 9, "content": "<COLOR_BLACK>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 10, "content": "<COLOR_BLUE>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 11, "content": "<COLOR_RED>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 12, "content": "<COLOR_GREEN>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 13, "content": "<COLOR_YELLOW>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 14, "content": "<COLOR_GREY>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 15, "content": "<COLOR_FUCHSIA>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 16, "content": "<COLOR_ORANGE>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 17, "content": "<COLOR_TEAL>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}, {"id": 18, "content": "<COLOR_BROWN>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false}], "normalizer": null, "pre_tokenizer": {"type": "WhitespaceSplit"}, "post_processor": null, "decoder": {"type": "WordPiece", "prefix": "##", "cleanup": false}, "model": {"type": "WordLevel", "vocab": {"<PAD>": 0, "<BOS>": 1, "<EOS>": 2, "<BEGIN_GRID>": 3, "<END_GRID>": 4, "<BEGIN_ROW>": 5, "<END_ROW>": 6, "<INPUT>": 7, "<OUTPUT>": 8, "<COLOR_BLACK>": 9, "<COLOR_BLUE>": 10, "<COLOR_RED>": 11, "<COLOR_GREEN>": 12, "<COLOR_YELLOW>": 13, "<COLOR_GREY>": 14, "<COLOR_FUCHSIA>": 15, "<COLOR_ORANGE>": 16, "<COLOR_TEAL>": 17, "<COLOR_BROWN>": 18}, "unk_token": "<PAD>"}}
|
50m-3.0b/tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 3 |
+
"bos_token": "<BOS>",
|
| 4 |
+
"eos_token": "<EOS>",
|
| 5 |
+
"pad_token": "<PAD>",
|
| 6 |
+
"additional_special_tokens": [
|
| 7 |
+
"<BEGIN_GRID>",
|
| 8 |
+
"<END_GRID>",
|
| 9 |
+
"<BEGIN_ROW>",
|
| 10 |
+
"<END_ROW>",
|
| 11 |
+
"<INPUT>",
|
| 12 |
+
"<OUTPUT>"
|
| 13 |
+
],
|
| 14 |
+
"model_max_length": 16384,
|
| 15 |
+
"clean_up_tokenization_spaces": false
|
| 16 |
+
}
|