q-allen commited on
Commit
1d36b9c
1 Parent(s): fbefca8

Upload LlamaForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +48 -0
  2. generation_config.json +10 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "yentinglin/Taiwan-LLM-7B-v2.0.1-chat",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 32,
18
+ "pretraining_tp": 1,
19
+ "quantization_config": {
20
+ "batch_size": 1,
21
+ "bits": 4,
22
+ "block_name_to_quantize": "model.layers",
23
+ "damp_percent": 0.1,
24
+ "dataset": "c4",
25
+ "desc_act": false,
26
+ "disable_exllama": false,
27
+ "group_size": 128,
28
+ "max_input_length": null,
29
+ "model_seqlen": 4096,
30
+ "module_name_preceding_first_block": [
31
+ "model.embed_tokens"
32
+ ],
33
+ "pad_token_id": null,
34
+ "quant_method": "gptq",
35
+ "sym": true,
36
+ "tokenizer": null,
37
+ "true_sequential": true,
38
+ "use_cuda_fp16": true
39
+ },
40
+ "rms_norm_eps": 1e-05,
41
+ "rope_scaling": null,
42
+ "rope_theta": 10000.0,
43
+ "tie_word_embeddings": false,
44
+ "torch_dtype": "float16",
45
+ "transformers_version": "4.34.0",
46
+ "use_cache": true,
47
+ "vocab_size": 32000
48
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.34.0"
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34473253f9ffd27d1c7d05f5514bc0ced9075f670abdf84a5ad29c67e87b7704
3
+ size 3896963281