llm1234 commited on
Commit
f508dec
1 Parent(s): 8997f6a

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ericzzz/falcon-rw-1b-instruct-openorca",
3
+ "alibi": true,
4
+ "apply_residual_connection_post_layernorm": false,
5
+ "architectures": [
6
+ "FalconForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bias": true,
10
+ "bos_token_id": 11,
11
+ "eos_token_id": 11,
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "layer_norm_epsilon": 1e-05,
16
+ "max_position_embeddings": 2048,
17
+ "model_type": "falcon",
18
+ "multi_query": false,
19
+ "new_decoder_architecture": false,
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 24,
22
+ "num_kv_heads": 32,
23
+ "parallel_attn": false,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.31.0",
28
+ "use_cache": false,
29
+ "vocab_size": 50304
30
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 11,
4
+ "eos_token_id": 11,
5
+ "transformers_version": "4.31.0",
6
+ "use_cache": false
7
+ }
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 sha256:6738fc1a05e5d7dc2174cd4399ad99c23136b8fcb8d2c5b3a123469cc89ffcc2
3
+ size 2623284688
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
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