Around6827
commited on
Commit
•
401d072
1
Parent(s):
c7e4882
Training in progress, epoch 0
Browse files- adapter_config.json +4 -4
- adapter_model.bin +1 -1
- added_tokens.json +4 -1
- config.json +15 -3
- tokenizer_config.json +12 -7
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -16,13 +16,13 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"k_proj",
|
20 |
-
"up_proj",
|
21 |
-
"gate_proj",
|
22 |
-
"q_proj",
|
23 |
"o_proj",
|
24 |
"v_proj",
|
25 |
-
"
|
|
|
|
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM"
|
28 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"down_proj",
|
20 |
"k_proj",
|
|
|
|
|
|
|
21 |
"o_proj",
|
22 |
"v_proj",
|
23 |
+
"up_proj",
|
24 |
+
"q_proj",
|
25 |
+
"gate_proj"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM"
|
28 |
}
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 500897101
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c29852f5cb6a3143c6c97f560414775e63bfa7e535f05dcfdf9bf07c5ec6033d
|
3 |
size 500897101
|
added_tokens.json
CHANGED
@@ -1,3 +1,6 @@
|
|
1 |
{
|
2 |
-
"
|
|
|
|
|
|
|
3 |
}
|
|
|
1 |
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<pad>": 32000,
|
4 |
+
"<s>": 1,
|
5 |
+
"<unk>": 0
|
6 |
}
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
@@ -16,12 +16,24 @@
|
|
16 |
"num_key_value_heads": 40,
|
17 |
"pad_token_id": 0,
|
18 |
"pretraining_tp": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
"rms_norm_eps": 1e-05,
|
20 |
"rope_scaling": null,
|
21 |
"rope_theta": 10000.0,
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "float16",
|
24 |
"transformers_version": "4.34.0.dev0",
|
25 |
-
"use_cache":
|
26 |
-
"vocab_size":
|
27 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "NousResearch/Llama-2-13b-chat-hf",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
|
|
16 |
"num_key_value_heads": 40,
|
17 |
"pad_token_id": 0,
|
18 |
"pretraining_tp": 1,
|
19 |
+
"quantization_config": {
|
20 |
+
"bnb_4bit_compute_dtype": "float32",
|
21 |
+
"bnb_4bit_quant_type": "fp4",
|
22 |
+
"bnb_4bit_use_double_quant": false,
|
23 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
24 |
+
"llm_int8_has_fp16_weight": false,
|
25 |
+
"llm_int8_skip_modules": null,
|
26 |
+
"llm_int8_threshold": 6.0,
|
27 |
+
"load_in_4bit": false,
|
28 |
+
"load_in_8bit": true,
|
29 |
+
"quant_method": "bitsandbytes"
|
30 |
+
},
|
31 |
"rms_norm_eps": 1e-05,
|
32 |
"rope_scaling": null,
|
33 |
"rope_theta": 10000.0,
|
34 |
"tie_word_embeddings": false,
|
35 |
"torch_dtype": "float16",
|
36 |
"transformers_version": "4.34.0.dev0",
|
37 |
+
"use_cache": false,
|
38 |
+
"vocab_size": 32001
|
39 |
}
|
tokenizer_config.json
CHANGED
@@ -1,26 +1,28 @@
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
5 |
-
"lstrip":
|
6 |
"normalized": false,
|
7 |
-
"rstrip":
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
"1": {
|
12 |
"content": "<s>",
|
13 |
-
"lstrip":
|
14 |
"normalized": false,
|
15 |
-
"rstrip":
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
"2": {
|
20 |
"content": "</s>",
|
21 |
-
"lstrip":
|
22 |
"normalized": false,
|
23 |
-
"rstrip":
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
@@ -43,6 +45,9 @@
|
|
43 |
"sp_model_kwargs": {},
|
44 |
"spaces_between_special_tokens": false,
|
45 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
46 |
"unk_token": "<unk>",
|
47 |
-
"use_default_system_prompt": true
|
|
|
48 |
}
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
7 |
+
"lstrip": true,
|
8 |
"normalized": false,
|
9 |
+
"rstrip": true,
|
10 |
"single_word": false,
|
11 |
"special": true
|
12 |
},
|
13 |
"1": {
|
14 |
"content": "<s>",
|
15 |
+
"lstrip": true,
|
16 |
"normalized": false,
|
17 |
+
"rstrip": true,
|
18 |
"single_word": false,
|
19 |
"special": true
|
20 |
},
|
21 |
"2": {
|
22 |
"content": "</s>",
|
23 |
+
"lstrip": true,
|
24 |
"normalized": false,
|
25 |
+
"rstrip": true,
|
26 |
"single_word": false,
|
27 |
"special": true
|
28 |
},
|
|
|
45 |
"sp_model_kwargs": {},
|
46 |
"spaces_between_special_tokens": false,
|
47 |
"tokenizer_class": "LlamaTokenizer",
|
48 |
+
"tokenizer_file": null,
|
49 |
+
"trust_remote_code": false,
|
50 |
"unk_token": "<unk>",
|
51 |
+
"use_default_system_prompt": true,
|
52 |
+
"use_fast": true
|
53 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4475
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fa31bea8c729aa47dee7c9c205a5c8d836a64cee9b393986dd02619c1669b66
|
3 |
size 4475
|