step 10000
Browse files- config.json +87 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
config.json
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"N": 20,
|
| 3 |
+
"base_config_dict": {
|
| 4 |
+
"_name_or_path": "TinyLlama/TinyLlama_v1.1",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LlamaForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"bos_token_id": 1,
|
| 11 |
+
"chunk_size_feed_forward": 0,
|
| 12 |
+
"dtype": "float32",
|
| 13 |
+
"eos_token_id": 2,
|
| 14 |
+
"head_dim": 64,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 2048,
|
| 17 |
+
"id2label": {
|
| 18 |
+
"0": "LABEL_0",
|
| 19 |
+
"1": "LABEL_1"
|
| 20 |
+
},
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 5632,
|
| 23 |
+
"is_encoder_decoder": false,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"LABEL_0": 0,
|
| 26 |
+
"LABEL_1": 1
|
| 27 |
+
},
|
| 28 |
+
"max_position_embeddings": 2048,
|
| 29 |
+
"mlp_bias": false,
|
| 30 |
+
"model_type": "llama",
|
| 31 |
+
"num_attention_heads": 32,
|
| 32 |
+
"num_hidden_layers": 22,
|
| 33 |
+
"num_key_value_heads": 4,
|
| 34 |
+
"output_attentions": false,
|
| 35 |
+
"output_hidden_states": false,
|
| 36 |
+
"pad_token_id": null,
|
| 37 |
+
"pretraining_tp": 1,
|
| 38 |
+
"problem_type": null,
|
| 39 |
+
"return_dict": true,
|
| 40 |
+
"rms_norm_eps": 1e-05,
|
| 41 |
+
"rope_parameters": {
|
| 42 |
+
"rope_theta": 10000.0,
|
| 43 |
+
"rope_type": "default"
|
| 44 |
+
},
|
| 45 |
+
"tie_word_embeddings": false,
|
| 46 |
+
"transformers_version": "5.3.0",
|
| 47 |
+
"use_cache": true,
|
| 48 |
+
"vocab_size": 32000
|
| 49 |
+
},
|
| 50 |
+
"base_model_name_or_path": "TinyLlama/TinyLlama_v1.1",
|
| 51 |
+
"convergence_epsilon": 0.01,
|
| 52 |
+
"decoder_layer_indices": [
|
| 53 |
+
21
|
| 54 |
+
],
|
| 55 |
+
"encoder_layer_indices": [
|
| 56 |
+
0
|
| 57 |
+
],
|
| 58 |
+
"halting_strategy": "threshold",
|
| 59 |
+
"hidden_size": 2048,
|
| 60 |
+
"model_type": "lds",
|
| 61 |
+
"q_eval_interval": 1,
|
| 62 |
+
"q_threshold": 0.9,
|
| 63 |
+
"reasoning_layer_indices": [
|
| 64 |
+
1,
|
| 65 |
+
2,
|
| 66 |
+
3,
|
| 67 |
+
4,
|
| 68 |
+
5,
|
| 69 |
+
6,
|
| 70 |
+
7,
|
| 71 |
+
8,
|
| 72 |
+
9,
|
| 73 |
+
10,
|
| 74 |
+
11,
|
| 75 |
+
12,
|
| 76 |
+
13,
|
| 77 |
+
14,
|
| 78 |
+
15,
|
| 79 |
+
16,
|
| 80 |
+
17,
|
| 81 |
+
18,
|
| 82 |
+
19,
|
| 83 |
+
20
|
| 84 |
+
],
|
| 85 |
+
"transformers_version": "5.3.0",
|
| 86 |
+
"vocab_size": 32000
|
| 87 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a7cfc4289b12259809627baec9b1ea944183c679191fb9ec39e858e992ff0a8
|
| 3 |
+
size 2202259364
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": null,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
+
"pad_token": "</s>",
|
| 10 |
+
"padding_side": "right",
|
| 11 |
+
"sp_model_kwargs": {},
|
| 12 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 13 |
+
"unk_token": "<unk>",
|
| 14 |
+
"use_default_system_prompt": false
|
| 15 |
+
}
|