devorein commited on
Commit
8f77897
1 Parent(s): b47e7a9

Upload folder using huggingface_hub

Browse files
adapter_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "",
3
+ "bias": "none",
4
+ "enable_lora": null,
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "lora_alpha": 16,
9
+ "lora_dropout": 0.05,
10
+ "merge_weights": false,
11
+ "modules_to_save": null,
12
+ "peft_type": "LORA",
13
+ "r": 8,
14
+ "target_modules": [
15
+ "q_proj",
16
+ "v_proj"
17
+ ]
18
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2eee1c7dcb6c63a59181bbcaad99832aaf5136f390b0f328b79c4e6b027f942
3
+ size 16819789
config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LLaMAForCausalLM"
4
+ ],
5
+ "bos_token_id": 0,
6
+ "eos_token_id": 1,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 4096,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 11008,
11
+ "max_sequence_length": 2048,
12
+ "model_type": "llama",
13
+ "num_attention_heads": 32,
14
+ "num_hidden_layers": 32,
15
+ "pad_token_id": -1,
16
+ "rms_norm_eps": 1e-06,
17
+ "tie_word_embeddings": false,
18
+ "torch_dtype": "float16",
19
+ "transformers_version": "4.28.1",
20
+ "use_cache": true,
21
+ "vocab_size": 32000
22
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27d7f70711e5c8fb5d42dc09b460ab3d5a08c06575104b55db373256ba4ee282
3
+ size 3911057236
special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "pad_token": "</s>"
3
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "",
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "tokenizer_class": "LlamaTokenizer",
7
+ "unk_token": ""
8
+ }
xturing.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name": "llama_lora_int4",
3
+ "finetuning_config": {
4
+ "learning_rate": 0.0001,
5
+ "gradient_accumulation_steps": 1,
6
+ "batch_size": 24,
7
+ "weight_decay": 0.01,
8
+ "warmup_steps": 50,
9
+ "eval_steps": 5000,
10
+ "save_steps": 5000,
11
+ "max_length": 256,
12
+ "num_train_epochs": 3,
13
+ "logging_steps": 10,
14
+ "max_grad_norm": 2.0,
15
+ "save_total_limit": 4,
16
+ "optimizer_name": "adamw",
17
+ "output_dir": "saved_model"
18
+ },
19
+ "generation_config": {
20
+ "penalty_alpha": 0.6,
21
+ "top_k": 4,
22
+ "max_new_tokens": 256,
23
+ "do_sample": false,
24
+ "top_p": null
25
+ }
26
+ }