d39351beae31de2c244e7a77e4efc96035ef2a07f2eb5ad5c3a75850e4a87a1c
Browse files- .gitattributes +1 -0
- config.json +60 -0
- generation_config.json +7 -0
- special_tokens_map.json +30 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +49 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_block_types": [
|
3 |
+
"recurrent",
|
4 |
+
"recurrent",
|
5 |
+
"attention"
|
6 |
+
],
|
7 |
+
"_name_or_path": "google/recurrentgemma-2b",
|
8 |
+
"architectures": [
|
9 |
+
"RecurrentGemmaForCausalLM"
|
10 |
+
],
|
11 |
+
"attention_bias": false,
|
12 |
+
"attention_dropout": 0.0,
|
13 |
+
"attention_window_size": 2048,
|
14 |
+
"block_types": [
|
15 |
+
"recurrent",
|
16 |
+
"recurrent",
|
17 |
+
"attention"
|
18 |
+
],
|
19 |
+
"bos_token_id": 2,
|
20 |
+
"conv1d_width": 4,
|
21 |
+
"embeddings_scale_by_sqrt_dim": true,
|
22 |
+
"eos_token_id": 1,
|
23 |
+
"final_w_init_variance_scale": 0.07692307692307693,
|
24 |
+
"head_dim": 256,
|
25 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
26 |
+
"hidden_size": 2560,
|
27 |
+
"intermediate_size": 15360,
|
28 |
+
"logits_soft_cap": 30.0,
|
29 |
+
"lru_width": 2560,
|
30 |
+
"model_type": "recurrent_gemma",
|
31 |
+
"num_attention_heads": 10,
|
32 |
+
"num_hidden_layers": 26,
|
33 |
+
"num_key_value_heads": 1,
|
34 |
+
"pad_token_id": 0,
|
35 |
+
"partial_rotary_factor": 0.5,
|
36 |
+
"quantization_config": {
|
37 |
+
"_load_in_4bit": true,
|
38 |
+
"_load_in_8bit": false,
|
39 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
40 |
+
"bnb_4bit_quant_storage": "uint8",
|
41 |
+
"bnb_4bit_quant_type": "fp4",
|
42 |
+
"bnb_4bit_use_double_quant": false,
|
43 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
44 |
+
"llm_int8_has_fp16_weight": false,
|
45 |
+
"llm_int8_skip_modules": [
|
46 |
+
"lm_head"
|
47 |
+
],
|
48 |
+
"llm_int8_threshold": 6.0,
|
49 |
+
"load_in_4bit": true,
|
50 |
+
"load_in_8bit": false,
|
51 |
+
"quant_method": "bitsandbytes"
|
52 |
+
},
|
53 |
+
"rms_norm_eps": 1e-06,
|
54 |
+
"rope_theta": 10000.0,
|
55 |
+
"torch_dtype": "bfloat16",
|
56 |
+
"transformers_version": "4.40.0.dev0",
|
57 |
+
"use_cache": true,
|
58 |
+
"vocab_size": 256000,
|
59 |
+
"w_init_variance_scale": 0.01
|
60 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.40.0.dev0"
|
7 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<bos>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<eos>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
|
3 |
+
size 17477553
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
3 |
+
size 4241003
|
tokenizer_config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<bos>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"bos_token": "<bos>",
|
39 |
+
"clean_up_tokenization_spaces": false,
|
40 |
+
"eos_token": "<eos>",
|
41 |
+
"legacy": null,
|
42 |
+
"model_max_length": 1000000000000000019884624838656,
|
43 |
+
"pad_token": "<pad>",
|
44 |
+
"sp_model_kwargs": {},
|
45 |
+
"spaces_between_special_tokens": false,
|
46 |
+
"tokenizer_class": "GemmaTokenizer",
|
47 |
+
"unk_token": "<unk>",
|
48 |
+
"use_default_system_prompt": false
|
49 |
+
}
|