(Trained with Unsloth)
Browse files- config.json +37 -37
- tokenizer_config.json +4 -1
config.json
CHANGED
|
@@ -1,38 +1,38 @@
|
|
| 1 |
{
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 128000,
|
| 8 |
+
"eos_token_id": 128009,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 3072,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8192,
|
| 14 |
+
"max_position_embeddings": 131072,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 24,
|
| 18 |
+
"num_hidden_layers": 28,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"pad_token_id": 128004,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"rms_norm_eps": 1e-05,
|
| 23 |
+
"rope_scaling": {
|
| 24 |
+
"factor": 32.0,
|
| 25 |
+
"high_freq_factor": 4.0,
|
| 26 |
+
"low_freq_factor": 1.0,
|
| 27 |
+
"original_max_position_embeddings": 8192,
|
| 28 |
+
"rope_type": "llama3"
|
| 29 |
+
},
|
| 30 |
+
"rope_theta": 500000.0,
|
| 31 |
+
"tie_word_embeddings": true,
|
| 32 |
+
"torch_dtype": "float16",
|
| 33 |
+
"transformers_version": "4.51.3",
|
| 34 |
+
"unsloth_fixed": true,
|
| 35 |
+
"unsloth_version": "2025.6.1",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 128256
|
| 38 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -2055,13 +2055,16 @@
|
|
| 2055 |
"clean_up_tokenization_spaces": true,
|
| 2056 |
"eos_token": "<|eot_id|>",
|
| 2057 |
"extra_special_tokens": {},
|
|
|
|
| 2058 |
"model_input_names": [
|
| 2059 |
"input_ids",
|
| 2060 |
"attention_mask"
|
| 2061 |
],
|
| 2062 |
"model_max_length": 131072,
|
|
|
|
| 2063 |
"pad_token": "<|finetune_right_pad_id|>",
|
| 2064 |
-
"
|
|
|
|
| 2065 |
"tokenizer_class": "PreTrainedTokenizer",
|
| 2066 |
"unk_token": null
|
| 2067 |
}
|
|
|
|
| 2055 |
"clean_up_tokenization_spaces": true,
|
| 2056 |
"eos_token": "<|eot_id|>",
|
| 2057 |
"extra_special_tokens": {},
|
| 2058 |
+
"max_length": null,
|
| 2059 |
"model_input_names": [
|
| 2060 |
"input_ids",
|
| 2061 |
"attention_mask"
|
| 2062 |
],
|
| 2063 |
"model_max_length": 131072,
|
| 2064 |
+
"pad_to_multiple_of": null,
|
| 2065 |
"pad_token": "<|finetune_right_pad_id|>",
|
| 2066 |
+
"pad_token_type_id": 0,
|
| 2067 |
+
"padding_side": "right",
|
| 2068 |
"tokenizer_class": "PreTrainedTokenizer",
|
| 2069 |
"unk_token": null
|
| 2070 |
}
|