Upload folder using huggingface_hub
Browse files- generation_config.json +7 -0
- lit_model.pth +3 -0
- model_config.yaml +28 -0
- pytorch_model.bin +3 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +35 -0
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 |
+
}
|
lit_model.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6448bb7864529f7cbd3c8699a2c2a01138d07d216f03b47a804279ca725cc0b4
|
| 3 |
+
size 4400238830
|
model_config.yaml
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
bias: false
|
| 2 |
+
block_size: 2048
|
| 3 |
+
gelu_approximate: none
|
| 4 |
+
head_size: 64
|
| 5 |
+
hf_config:
|
| 6 |
+
name: TinyLlama-1.1B-intermediate-step-1431k-3T
|
| 7 |
+
org: TinyLlama
|
| 8 |
+
intermediate_size: 5632
|
| 9 |
+
lm_head_bias: false
|
| 10 |
+
mlp_class_name: LLaMAMLP
|
| 11 |
+
n_embd: 2048
|
| 12 |
+
n_expert: 0
|
| 13 |
+
n_expert_per_token: 0
|
| 14 |
+
n_head: 32
|
| 15 |
+
n_layer: 22
|
| 16 |
+
n_query_groups: 4
|
| 17 |
+
name: tiny-llama-1.1b
|
| 18 |
+
norm_class_name: RMSNorm
|
| 19 |
+
norm_eps: 1.0e-05
|
| 20 |
+
padded_vocab_size: 32000
|
| 21 |
+
padding_multiple: 64
|
| 22 |
+
parallel_residual: false
|
| 23 |
+
rope_base: 10000
|
| 24 |
+
rope_condense_ratio: 1
|
| 25 |
+
rotary_percentage: 1.0
|
| 26 |
+
scale_embeddings: false
|
| 27 |
+
shared_attention_norm: false
|
| 28 |
+
vocab_size: 32000
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f71ffc28a0118384d5b3888c8a1fdc1498ed0666c808b68873d4e2dc3351c5b
|
| 3 |
+
size 4400254027
|
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 |
+
}
|