初始化项目,由ModelHub XC社区提供模型
Model: Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base Source: Original Platform
This commit is contained in:
36
old/config.json
Normal file
36
old/config.json
Normal file
@@ -0,0 +1,36 @@
|
||||
{
|
||||
"_name_or_path": "/Users/jsarnecki/opt/Workspace/meta-llama/Llama-3.1-8B",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128001,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 8.0,
|
||||
"high_freq_factor": 4.0,
|
||||
"low_freq_factor": 1.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "llama3"
|
||||
},
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.45.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
4
old/special_tokens_map.json
Normal file
4
old/special_tokens_map.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"bos_token": "<|begin_of_text|>",
|
||||
"eos_token": "<|end_of_text|>"
|
||||
}
|
||||
410563
old/tokenizer.json
Normal file
410563
old/tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
2061
old/tokenizer_config.json
Normal file
2061
old/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user