Text Generation
Transformers
PyTorch
Chinese
llama
text-generation-inference
Inference Endpoints
4-bit precision
gptq
q-allen commited on
Commit
68e40c0
1 Parent(s): e2d0b38

Upload LlamaForCausalLM

Browse files
Files changed (2) hide show
  1. config.json +49 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "yentinglin/Taiwan-LLaMa-v1.0",
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": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13824,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 40,
17
+ "num_key_value_heads": 40,
18
+ "pad_token_id": 0,
19
+ "pretraining_tp": 1,
20
+ "quantization_config": {
21
+ "batch_size": 1,
22
+ "bits": 4,
23
+ "block_name_to_quantize": "model.layers",
24
+ "damp_percent": 0.1,
25
+ "dataset": "c4",
26
+ "desc_act": false,
27
+ "disable_exllama": false,
28
+ "group_size": 128,
29
+ "max_input_length": null,
30
+ "model_seqlen": 4096,
31
+ "module_name_preceding_first_block": [
32
+ "model.embed_tokens"
33
+ ],
34
+ "pad_token_id": null,
35
+ "quant_method": "gptq",
36
+ "sym": true,
37
+ "tokenizer": null,
38
+ "true_sequential": true,
39
+ "use_cuda_fp16": true
40
+ },
41
+ "rms_norm_eps": 1e-05,
42
+ "rope_scaling": null,
43
+ "rope_theta": 10000.0,
44
+ "tie_word_embeddings": false,
45
+ "torch_dtype": "float16",
46
+ "transformers_version": "4.34.1",
47
+ "use_cache": false,
48
+ "vocab_size": 32000
49
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4a811aff332bc713b4f9bc2abffb5ae45610b46020803fec5a1d34cc207bcc8
3
+ size 7259754197