quantumaikr commited on
Commit
9cbf061
·
1 Parent(s): 21d5fba

Upload LlamaForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +39 -0
  2. generation_config.json +7 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 32,
17
+ "pretraining_tp": 1,
18
+ "quantization_config": {
19
+ "bnb_4bit_compute_dtype": "bfloat16",
20
+ "bnb_4bit_quant_type": "fp4",
21
+ "bnb_4bit_use_double_quant": false,
22
+ "llm_int8_enable_fp32_cpu_offload": false,
23
+ "llm_int8_has_fp16_weight": false,
24
+ "llm_int8_skip_modules": null,
25
+ "llm_int8_threshold": 6.0,
26
+ "load_in_4bit": false,
27
+ "load_in_8bit": true
28
+ },
29
+ "rms_norm_eps": 1e-06,
30
+ "rope_scaling": {
31
+ "factor": 2,
32
+ "type": "dynamic"
33
+ },
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.32.0.dev0",
37
+ "use_cache": false,
38
+ "vocab_size": 32000
39
+ }
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
+ "transformers_version": "4.32.0.dev0",
6
+ "use_cache": false
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fd5241f8fce411c2d2c47134c8eee92f5bbc46d8bc290d996728e4e1168b849
3
+ size 7674527937