Upload folder using huggingface_hub
Browse files- README.md +76 -0
- config.json +25 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +35 -0
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
---
|
4 |
+
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
|
5 |
+
|
6 |
+
it's based on the 3t base model (not chat tuned).
|
7 |
+
|
8 |
+
not extensively tested.
|
9 |
+
|
10 |
+
enjoy!
|
11 |
+
|
12 |
+
(model card is repeated due to open llm leaderboard length requirements)
|
13 |
+
|
14 |
+
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
|
15 |
+
|
16 |
+
it's based on the 3t base model (not chat tuned).
|
17 |
+
|
18 |
+
not extensively tested.
|
19 |
+
|
20 |
+
enjoy!
|
21 |
+
|
22 |
+
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
|
23 |
+
|
24 |
+
it's based on the 3t base model (not chat tuned).
|
25 |
+
|
26 |
+
not extensively tested.
|
27 |
+
|
28 |
+
enjoy!
|
29 |
+
|
30 |
+
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
|
31 |
+
|
32 |
+
it's based on the 3t base model (not chat tuned).
|
33 |
+
|
34 |
+
not extensively tested.
|
35 |
+
|
36 |
+
enjoy!
|
37 |
+
|
38 |
+
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
|
39 |
+
|
40 |
+
it's based on the 3t base model (not chat tuned).
|
41 |
+
|
42 |
+
not extensively tested.
|
43 |
+
|
44 |
+
enjoy!
|
45 |
+
|
46 |
+
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
|
47 |
+
|
48 |
+
it's based on the 3t base model (not chat tuned).
|
49 |
+
|
50 |
+
not extensively tested.
|
51 |
+
|
52 |
+
enjoy!
|
53 |
+
|
54 |
+
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
|
55 |
+
|
56 |
+
it's based on the 3t base model (not chat tuned).
|
57 |
+
|
58 |
+
not extensively tested.
|
59 |
+
|
60 |
+
enjoy!
|
61 |
+
|
62 |
+
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
|
63 |
+
|
64 |
+
it's based on the 3t base model (not chat tuned).
|
65 |
+
|
66 |
+
not extensively tested.
|
67 |
+
|
68 |
+
enjoy!
|
69 |
+
|
70 |
+
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
|
71 |
+
|
72 |
+
it's based on the 3t base model (not chat tuned).
|
73 |
+
|
74 |
+
not extensively tested.
|
75 |
+
|
76 |
+
enjoy!
|
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"MistralForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 2048,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 5632,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
+
"model_type": "mistral",
|
14 |
+
"num_attention_heads": 32,
|
15 |
+
"num_hidden_layers": 22,
|
16 |
+
"num_key_value_heads": 4,
|
17 |
+
"rms_norm_eps": 1e-05,
|
18 |
+
"rope_theta": 1000000.0,
|
19 |
+
"sliding_window": null,
|
20 |
+
"tie_word_embeddings": false,
|
21 |
+
"torch_dtype": "bfloat16",
|
22 |
+
"transformers_version": "4.31.0.dev0",
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 32000
|
25 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 1,
|
3 |
+
"eos_token_id": 2,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"max_length": 2048,
|
6 |
+
"transformers_version": "4.31.0.dev0"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9dc1c1a8c6b29e153dea7aaf2ed6c4d242163489add0e7c14c23889745437be4
|
3 |
+
size 4400216536
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"legacy": false,
|
22 |
+
"model_max_length": 1000000000000000019884624838656,
|
23 |
+
"pad_token": null,
|
24 |
+
"padding_side": "right",
|
25 |
+
"sp_model_kwargs": {},
|
26 |
+
"tokenizer_class": "LlamaTokenizer",
|
27 |
+
"unk_token": {
|
28 |
+
"__type": "AddedToken",
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|