hama-jp commited on
Commit
b18256a
1 Parent(s): af57714

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hama-jp/gemma-2-27b",
3
+ "architectures": [
4
+ "Gemma2ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": 50.0,
9
+ "bos_token_id": 2,
10
+ "cache_implementation": "hybrid",
11
+ "eos_token_id": 1,
12
+ "final_logit_softcapping": 30.0,
13
+ "head_dim": 128,
14
+ "hidden_act": "gelu_pytorch_tanh",
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 4608,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 36864,
19
+ "max_position_embeddings": 8192,
20
+ "model_type": "gemma2",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 46,
23
+ "num_key_value_heads": 16,
24
+ "pad_token_id": 0,
25
+ "quantization_config": {
26
+ "bnb_4bit_compute_dtype": "bfloat16",
27
+ "bnb_4bit_quant_type": "nf4",
28
+ "bnb_4bit_use_double_quant": true,
29
+ "llm_int8_enable_fp32_cpu_offload": false,
30
+ "llm_int8_has_fp16_weight": false,
31
+ "llm_int8_skip_modules": null,
32
+ "llm_int8_threshold": 6.0,
33
+ "load_in_4bit": true,
34
+ "load_in_8bit": false,
35
+ "quant_method": "bitsandbytes"
36
+ },
37
+ "query_pre_attn_scalar": 144,
38
+ "rms_norm_eps": 1e-06,
39
+ "rope_scaling": null,
40
+ "rope_theta": 10000.0,
41
+ "sliding_window": 4096,
42
+ "sliding_window_size": 4096,
43
+ "torch_dtype": "bfloat16",
44
+ "transformers_version": "4.46.3",
45
+ "unsloth_version": "2024.11.10",
46
+ "use_cache": true,
47
+ "vocab_size": 256000
48
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "cache_implementation": "hybrid",
5
+ "eos_token_id": 1,
6
+ "max_length": 8192,
7
+ "pad_token_id": 0,
8
+ "transformers_version": "4.46.3"
9
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf688305951e9d372ec8f47bec35803f9ef04b21627c2236d6bfcc5ad8fb815c
3
+ size 4998405317
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77a366cb537738a356bf9c304d4abe1862d1a3eeb4ff6262c9fa17aae6402c28
3
+ size 4986068553
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41c7ce05b963df1cdc5153032593b44173569c711522629a3b85319d31b3a709
3
+ size 4966589227
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd5a10142fb9cb6942e8b9e479d7fb43bc9d6e3b291f898981f3484490082ded
3
+ size 847247996
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff