sosuke commited on
Commit
6dde7b6
1 Parent(s): d13d657

Upload LlamaForCausalLM

Browse files
README.md CHANGED
@@ -1,6 +1,8 @@
1
  ---
2
  library_name: transformers
3
- tags: []
 
 
4
  ---
5
 
6
  # Model Card for Model ID
 
1
  ---
2
  library_name: transformers
3
+ tags:
4
+ - trl
5
+ - dpo
6
  ---
7
 
8
  # Model Card for Model ID
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "llm-book/Swallow-7b-hf-oasst1-21k-ja",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
+ "max_sequence_length": 4096,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 32,
21
+ "pad_token_id": 0,
22
+ "pretraining_tp": 1,
23
+ "quantization_config": {
24
+ "_load_in_4bit": true,
25
+ "_load_in_8bit": false,
26
+ "bnb_4bit_compute_dtype": "bfloat16",
27
+ "bnb_4bit_quant_storage": "uint8",
28
+ "bnb_4bit_quant_type": "nf4",
29
+ "bnb_4bit_use_double_quant": false,
30
+ "llm_int8_enable_fp32_cpu_offload": false,
31
+ "llm_int8_has_fp16_weight": false,
32
+ "llm_int8_skip_modules": null,
33
+ "llm_int8_threshold": 6.0,
34
+ "load_in_4bit": true,
35
+ "load_in_8bit": false,
36
+ "quant_method": "bitsandbytes"
37
+ },
38
+ "rms_norm_eps": 1e-05,
39
+ "rope_scaling": null,
40
+ "rope_theta": 10000.0,
41
+ "tie_word_embeddings": false,
42
+ "torch_dtype": "bfloat16",
43
+ "transformers_version": "4.42.4",
44
+ "use_cache": false,
45
+ "vocab_size": 43176
46
+ }
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": "4.42.4"
10
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed0bd90446afca1e1df71c1332147d81048dc9267bb384e05fe983ce504e25c7
3
+ size 4996538202
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d13703786d6603251444f04914057bc96e149275957507d9913ff9c5a9b9176
3
+ size 634154390
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff