Upload folder using huggingface_hub
Browse files- config.json +32 -0
- generation_config.json +10 -0
- model.safetensors +3 -0
- sft_training_info.json +12 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 0,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 2048,
|
| 15 |
+
"max_position_embeddings": 2048,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 18,
|
| 20 |
+
"num_key_value_heads": 4,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-05,
|
| 24 |
+
"rope_parameters": {
|
| 25 |
+
"rope_theta": 10000.0,
|
| 26 |
+
"rope_type": "default"
|
| 27 |
+
},
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"transformers_version": "5.7.0",
|
| 30 |
+
"use_cache": false,
|
| 31 |
+
"vocab_size": 32768
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"pad_token_id": 1,
|
| 8 |
+
"transformers_version": "5.7.0",
|
| 9 |
+
"use_cache": false
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:129f111d87350f7968e793066a21b2592bc61cc56c6e6431c3d48de2effd3080
|
| 3 |
+
size 327231072
|
sft_training_info.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model": "/content/echo88_final/Echo88-150M-Instruct",
|
| 3 |
+
"instruct_dataset": "/content/echo88/echo88_fact_repair_20k.jsonl",
|
| 4 |
+
"max_length": 1024,
|
| 5 |
+
"micro_batch": 64,
|
| 6 |
+
"grad_accum": 2,
|
| 7 |
+
"epochs": 4,
|
| 8 |
+
"learning_rate": 1e-05,
|
| 9 |
+
"train_examples": 19500,
|
| 10 |
+
"eval_examples": 500,
|
| 11 |
+
"system_prompt": "You are Echo88, a helpful computer assistant whose records go up to the end of 1988. Answer clearly. Do not pretend to know events, products, or culture after 1988."
|
| 12 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"extra_special_tokens": [
|
| 6 |
+
"<|system|>",
|
| 7 |
+
"<|user|>",
|
| 8 |
+
"<|assistant|>",
|
| 9 |
+
"<|end|>"
|
| 10 |
+
],
|
| 11 |
+
"is_local": true,
|
| 12 |
+
"local_files_only": false,
|
| 13 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 14 |
+
"pad_token": "<|pad|>",
|
| 15 |
+
"tokenizer_class": "TokenizersBackend",
|
| 16 |
+
"unk_token": "<|unk|>"
|
| 17 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75a742724ffcbdc1864877d7b22149c4eaa266267320603881764b14f1172669
|
| 3 |
+
size 5265
|