MartaSamoilenko
commited on
Commit
•
4624a6c
1
Parent(s):
5df04d8
Upload 8 files
Browse files- config.json +58 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +19 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "tiiuae/falcon-rw-1b",
|
3 |
+
"alibi": true,
|
4 |
+
"apply_residual_connection_post_layernorm": false,
|
5 |
+
"architectures": [
|
6 |
+
"FalconForCausalLM"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"auto_map": {
|
10 |
+
"AutoConfig": "tiiuae/falcon-rw-1b--configuration_falcon.FalconConfig",
|
11 |
+
"AutoModel": "tiiuae/falcon-rw-1b--modeling_falcon.FalconModel",
|
12 |
+
"AutoModelForCausalLM": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForCausalLM",
|
13 |
+
"AutoModelForQuestionAnswering": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForQuestionAnswering",
|
14 |
+
"AutoModelForSequenceClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForSequenceClassification",
|
15 |
+
"AutoModelForTokenClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForTokenClassification"
|
16 |
+
},
|
17 |
+
"bias": true,
|
18 |
+
"bos_token_id": 1,
|
19 |
+
"eos_token_id": 2,
|
20 |
+
"hidden_dropout": 0.0,
|
21 |
+
"hidden_size": 2048,
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"layer_norm_epsilon": 1e-05,
|
24 |
+
"model_type": "falcon",
|
25 |
+
"multi_query": false,
|
26 |
+
"new_decoder_architecture": false,
|
27 |
+
"num_attention_heads": 32,
|
28 |
+
"num_hidden_layers": 24,
|
29 |
+
"num_kv_heads": 32,
|
30 |
+
"parallel_attn": false,
|
31 |
+
"quantization_config": {
|
32 |
+
"batch_size": 1,
|
33 |
+
"bits": 4,
|
34 |
+
"block_name_to_quantize": null,
|
35 |
+
"cache_block_outputs": true,
|
36 |
+
"damp_percent": 0.1,
|
37 |
+
"dataset": "ptb",
|
38 |
+
"desc_act": false,
|
39 |
+
"exllama_config": {
|
40 |
+
"version": 1
|
41 |
+
},
|
42 |
+
"group_size": 64,
|
43 |
+
"max_input_length": null,
|
44 |
+
"model_seqlen": null,
|
45 |
+
"module_name_preceding_first_block": null,
|
46 |
+
"pad_token_id": null,
|
47 |
+
"quant_method": "gptq",
|
48 |
+
"sym": true,
|
49 |
+
"tokenizer": null,
|
50 |
+
"true_sequential": true,
|
51 |
+
"use_cuda_fp16": false,
|
52 |
+
"use_exllama": false
|
53 |
+
},
|
54 |
+
"torch_dtype": "float16",
|
55 |
+
"transformers_version": "4.36.2",
|
56 |
+
"use_cache": true,
|
57 |
+
"vocab_size": 50304
|
58 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.36.2"
|
6 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a148330a7dc86a5b036a5fb8faad8d32fcb5086fa74148730dd5204540175f4f
|
3 |
+
size 859940616
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<|endoftext|>",
|
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_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
}
|
12 |
+
},
|
13 |
+
"bos_token": "<|endoftext|>",
|
14 |
+
"clean_up_tokenization_spaces": true,
|
15 |
+
"eos_token": "<|endoftext|>",
|
16 |
+
"model_max_length": 1024,
|
17 |
+
"tokenizer_class": "GPT2Tokenizer",
|
18 |
+
"unk_token": "<|endoftext|>"
|
19 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|