Commit
•
e3db6e5
1
Parent(s):
d99047c
Upload checkpoint trained from Gemma 1.1 2B
Browse files- config.json +5 -6
- generation_config.json +1 -1
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
- tokenizer_config.json +1 -1
- trainer_state.json +0 -0
- training_args.bin +2 -2
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "google/gemma-2b-it",
|
3 |
"architectures": [
|
4 |
"LlavaGemmaForCausalLM"
|
5 |
],
|
@@ -9,8 +9,8 @@
|
|
9 |
"eos_token_id": 1,
|
10 |
"freeze_mm_mlp_adapter": false,
|
11 |
"head_dim": 256,
|
12 |
-
"hidden_act": "
|
13 |
-
"hidden_activation":
|
14 |
"hidden_size": 2048,
|
15 |
"image_aspect_ratio": "pad",
|
16 |
"initializer_range": 0.02,
|
@@ -31,12 +31,11 @@
|
|
31 |
"num_key_value_heads": 1,
|
32 |
"pad_token_id": 0,
|
33 |
"rms_norm_eps": 1e-06,
|
34 |
-
"rope_scaling": null,
|
35 |
"rope_theta": 10000.0,
|
36 |
-
"tokenizer_model_max_length":
|
37 |
"tokenizer_padding_side": "right",
|
38 |
"torch_dtype": "bfloat16",
|
39 |
-
"transformers_version": "4.
|
40 |
"tune_mm_mlp_adapter": false,
|
41 |
"use_cache": true,
|
42 |
"use_mm_proj": true,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "google/gemma-1.1-2b-it",
|
3 |
"architectures": [
|
4 |
"LlavaGemmaForCausalLM"
|
5 |
],
|
|
|
9 |
"eos_token_id": 1,
|
10 |
"freeze_mm_mlp_adapter": false,
|
11 |
"head_dim": 256,
|
12 |
+
"hidden_act": "gelu_pytorch_tanh",
|
13 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
14 |
"hidden_size": 2048,
|
15 |
"image_aspect_ratio": "pad",
|
16 |
"initializer_range": 0.02,
|
|
|
31 |
"num_key_value_heads": 1,
|
32 |
"pad_token_id": 0,
|
33 |
"rms_norm_eps": 1e-06,
|
|
|
34 |
"rope_theta": 10000.0,
|
35 |
+
"tokenizer_model_max_length": 4096,
|
36 |
"tokenizer_padding_side": "right",
|
37 |
"torch_dtype": "bfloat16",
|
38 |
+
"transformers_version": "4.41.0.dev0",
|
39 |
"tune_mm_mlp_adapter": false,
|
40 |
"use_cache": true,
|
41 |
"use_mm_proj": true,
|
generation_config.json
CHANGED
@@ -3,5 +3,5 @@
|
|
3 |
"bos_token_id": 2,
|
4 |
"eos_token_id": 1,
|
5 |
"pad_token_id": 0,
|
6 |
-
"transformers_version": "4.
|
7 |
}
|
|
|
3 |
"bos_token_id": 2,
|
4 |
"eos_token_id": 1,
|
5 |
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.41.0.dev0"
|
7 |
}
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4945242264
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:862efa4d98e8d07baf1e5f1ce46c1d24d953445fe6263bfa56578990f54c5657
|
3 |
size 4945242264
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1274422600
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:005624fb8471e7e9b59252d5c7ac9bb64797b5d72205517000d2dc939aecac2d
|
3 |
size 1274422600
|
tokenizer_config.json
CHANGED
@@ -1507,7 +1507,7 @@
|
|
1507 |
"chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
|
1508 |
"clean_up_tokenization_spaces": false,
|
1509 |
"eos_token": "<eos>",
|
1510 |
-
"model_max_length":
|
1511 |
"pad_token": "<unk>",
|
1512 |
"padding_side": "right",
|
1513 |
"sp_model_kwargs": {},
|
|
|
1507 |
"chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
|
1508 |
"clean_up_tokenization_spaces": false,
|
1509 |
"eos_token": "<eos>",
|
1510 |
+
"model_max_length": 4096,
|
1511 |
"pad_token": "<unk>",
|
1512 |
"padding_side": "right",
|
1513 |
"sp_model_kwargs": {},
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:496f2c2ad43e62b2e6084575d2233fe9782bed50acb223e6f68714bfbe1cbdac
|
3 |
+
size 6776
|