updated to mistral 7b base 0.2 from 0.1
Browse files- config.json +4 -4
- generation_config.json +2 -1
- pytorch_model-00001-of-00003.bin +1 -1
- pytorch_model-00002-of-00003.bin +1 -1
- pytorch_model-00003-of-00003.bin +1 -1
- tokenizer_config.json +1 -2
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
@@ -16,11 +16,11 @@
|
|
16 |
"num_hidden_layers": 32,
|
17 |
"num_key_value_heads": 8,
|
18 |
"rms_norm_eps": 1e-05,
|
19 |
-
"rope_theta":
|
20 |
-
"sliding_window":
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
-
"transformers_version": "4.
|
24 |
"use_cache": false,
|
25 |
"vocab_size": 32003
|
26 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/emanator/models/pippa-7b-qlora-lora/merged",
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
|
|
16 |
"num_hidden_layers": 32,
|
17 |
"num_key_value_heads": 8,
|
18 |
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 1000000.0,
|
20 |
+
"sliding_window": null,
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.40.0.dev0",
|
24 |
"use_cache": false,
|
25 |
"vocab_size": 32003
|
26 |
}
|
generation_config.json
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
|
|
4 |
"eos_token_id": 2,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
+
"do_sample": true,
|
5 |
"eos_token_id": 2,
|
6 |
+
"transformers_version": "4.40.0.dev0"
|
7 |
}
|
pytorch_model-00001-of-00003.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943210208
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c21ed646835026287afa0650c0706a4b06e62fe4ed1e84f5574726514dcbdc23
|
3 |
size 4943210208
|
pytorch_model-00002-of-00003.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999844744
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d17669896205d341119429cbf3aa9d6cc5477485ed0979101de7dedd0c2fb48
|
3 |
size 4999844744
|
pytorch_model-00003-of-00003.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4540561990
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07289868cdca2bc3a4670bf7b6bd14370f7a13f21008f3c265c4f6ca01ea3c78
|
3 |
size 4540561990
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
|
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
@@ -51,7 +52,6 @@
|
|
51 |
"special": false
|
52 |
}
|
53 |
},
|
54 |
-
"additional_special_tokens": [],
|
55 |
"bos_token": "<s>",
|
56 |
"clean_up_tokenization_spaces": false,
|
57 |
"eos_token": "</s>",
|
@@ -61,7 +61,6 @@
|
|
61 |
"sp_model_kwargs": {},
|
62 |
"spaces_between_special_tokens": false,
|
63 |
"tokenizer_class": "LlamaTokenizer",
|
64 |
-
"trust_remote_code": false,
|
65 |
"unk_token": "<unk>",
|
66 |
"use_default_system_prompt": false,
|
67 |
"use_fast": true
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
|
|
52 |
"special": false
|
53 |
}
|
54 |
},
|
|
|
55 |
"bos_token": "<s>",
|
56 |
"clean_up_tokenization_spaces": false,
|
57 |
"eos_token": "</s>",
|
|
|
61 |
"sp_model_kwargs": {},
|
62 |
"spaces_between_special_tokens": false,
|
63 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
64 |
"unk_token": "<unk>",
|
65 |
"use_default_system_prompt": false,
|
66 |
"use_fast": true
|