Upload folder using huggingface_hub
Browse files- config.json +82 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +34 -0
- tokenizer.json +0 -0
- tokenizer_config.json +51 -0
config.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Zyphra/Zamba2-1.2B-instruct",
|
3 |
+
"add_bias_linear": false,
|
4 |
+
"architectures": [
|
5 |
+
"Zamba2ForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"conv_dimension": 4,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"expansion_factor": 2,
|
12 |
+
"ffn_hidden_size": 8192,
|
13 |
+
"ft_lora": false,
|
14 |
+
"gated_linear_unit": true,
|
15 |
+
"hidden_size": 2048,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"kv_channels": 64,
|
18 |
+
"layers_block_type": [
|
19 |
+
"m",
|
20 |
+
"m",
|
21 |
+
"m",
|
22 |
+
"m",
|
23 |
+
"m",
|
24 |
+
"g",
|
25 |
+
"m",
|
26 |
+
"m",
|
27 |
+
"m",
|
28 |
+
"m",
|
29 |
+
"m",
|
30 |
+
"g",
|
31 |
+
"m",
|
32 |
+
"m",
|
33 |
+
"m",
|
34 |
+
"m",
|
35 |
+
"m",
|
36 |
+
"g",
|
37 |
+
"m",
|
38 |
+
"m",
|
39 |
+
"m",
|
40 |
+
"m",
|
41 |
+
"m",
|
42 |
+
"g",
|
43 |
+
"m",
|
44 |
+
"m",
|
45 |
+
"m",
|
46 |
+
"m",
|
47 |
+
"m",
|
48 |
+
"g",
|
49 |
+
"m",
|
50 |
+
"m",
|
51 |
+
"m",
|
52 |
+
"m",
|
53 |
+
"m",
|
54 |
+
"g",
|
55 |
+
"m",
|
56 |
+
"m"
|
57 |
+
],
|
58 |
+
"lora_rank": 128,
|
59 |
+
"lora_rank_mamba": 128,
|
60 |
+
"mamba_headdim": 64,
|
61 |
+
"max_position_embeddings": 4096,
|
62 |
+
"model_type": "zamba2",
|
63 |
+
"num_attention_heads": 32,
|
64 |
+
"num_hidden_layers": 38,
|
65 |
+
"num_key_value_heads": 32,
|
66 |
+
"num_logits_to_keep": 1,
|
67 |
+
"num_mem_blocks": 1,
|
68 |
+
"num_query_groups": 32,
|
69 |
+
"pad_token_id": 2,
|
70 |
+
"rms_norm_eps": 1e-05,
|
71 |
+
"rope_theta": 10000,
|
72 |
+
"sliding_window": null,
|
73 |
+
"state_size": 128,
|
74 |
+
"torch_dtype": "float32",
|
75 |
+
"transformers_version": "4.43.0.dev0",
|
76 |
+
"use_cache": false,
|
77 |
+
"use_mamba_kernels": true,
|
78 |
+
"use_mem_rope": true,
|
79 |
+
"use_shared_attention_lora": true,
|
80 |
+
"use_shared_block_lora": true,
|
81 |
+
"vocab_size": 32000
|
82 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.43.0.dev0"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec8527150b95e445a35031ec8b41cdeafa1a0cc28fca194596c25637cc52970c
|
3 |
+
size 2561248072
|
special_tokens_map.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<|im_start|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<|im_end|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "[PAD]",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"unk_token": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "[PAD]",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<|im_start|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "<|im_end|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"additional_special_tokens": [
|
32 |
+
"<|im_start|>",
|
33 |
+
"<|im_end|>"
|
34 |
+
],
|
35 |
+
"bos_token": "<|im_start|>",
|
36 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
37 |
+
"clean_up_tokenization_spaces": false,
|
38 |
+
"eos_token": "<|im_end|>",
|
39 |
+
"legacy": true,
|
40 |
+
"max_length": 4096,
|
41 |
+
"model_max_length": 4096,
|
42 |
+
"pad_token": "[PAD]",
|
43 |
+
"sp_model_kwargs": {},
|
44 |
+
"spaces_between_special_tokens": false,
|
45 |
+
"stride": 0,
|
46 |
+
"tokenizer_class": "LlamaTokenizer",
|
47 |
+
"truncation_side": "right",
|
48 |
+
"truncation_strategy": "longest_first",
|
49 |
+
"unk_token": "<unk>",
|
50 |
+
"use_default_system_prompt": false
|
51 |
+
}
|