crumb commited on
Commit
6821e80
1 Parent(s): 5086b06

Upload LlamaForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +38 -0
  2. generation_config.json +7 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/.cache/huggingface/hub/models--Trisert--open_llama_3b-sharded/snapshots/d9c0e88dfa5c6e35f856c4d1fefbfd75a9f2cd58",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3200,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 8640,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 26,
16
+ "num_key_value_heads": 32,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "quantization_config": {
20
+ "bnb_4bit_compute_dtype": "bfloat16",
21
+ "bnb_4bit_quant_type": "nf4",
22
+ "bnb_4bit_use_double_quant": true,
23
+ "llm_int8_enable_fp32_cpu_offload": false,
24
+ "llm_int8_has_fp16_weight": false,
25
+ "llm_int8_skip_modules": null,
26
+ "llm_int8_threshold": 6.0,
27
+ "load_in_4bit": true,
28
+ "load_in_8bit": false,
29
+ "quant_method": "bitsandbytes"
30
+ },
31
+ "rms_norm_eps": 1e-06,
32
+ "rope_scaling": null,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.32.1",
36
+ "use_cache": true,
37
+ "vocab_size": 32000
38
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.32.1"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cee1ea933a64bc4d7493edb4f3f7abcf38da5b28906695c9a8f4f65b6820384b
3
+ size 6853027945