wiweka24 commited on
Commit
22b61e4
1 Parent(s): 51a9853

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

README.md CHANGED
@@ -9,6 +9,7 @@ tags:
9
  - unsloth
10
  - gemma
11
  - trl
 
12
  ---
13
 
14
  # Uploaded model
 
9
  - unsloth
10
  - gemma
11
  - trl
12
+ - sft
13
  ---
14
 
15
  # Uploaded model
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/gemma-7b-bnb-4bit",
3
+ "architectures": [
4
+ "GemmaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 2,
9
+ "eos_token_id": 1,
10
+ "head_dim": 256,
11
+ "hidden_act": "gelu",
12
+ "hidden_activation": "gelu_pytorch_tanh",
13
+ "hidden_size": 3072,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 24576,
16
+ "max_position_embeddings": 8192,
17
+ "model_type": "gemma",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 28,
20
+ "num_key_value_heads": 16,
21
+ "pad_token_id": 0,
22
+ "quantization_config": {
23
+ "bnb_4bit_compute_dtype": "float16",
24
+ "bnb_4bit_quant_type": "nf4",
25
+ "bnb_4bit_use_double_quant": true,
26
+ "llm_int8_enable_fp32_cpu_offload": false,
27
+ "llm_int8_has_fp16_weight": false,
28
+ "llm_int8_skip_modules": null,
29
+ "llm_int8_threshold": 6.0,
30
+ "load_in_4bit": true,
31
+ "load_in_8bit": false,
32
+ "quant_method": "bitsandbytes"
33
+ },
34
+ "rms_norm_eps": 1e-06,
35
+ "rope_scaling": null,
36
+ "rope_theta": 10000.0,
37
+ "torch_dtype": "float16",
38
+ "transformers_version": "4.41.2",
39
+ "unsloth_version": "2024.6",
40
+ "use_cache": true,
41
+ "vocab_size": 256000
42
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.41.2"
7
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03fd71cb41f31737b3b0a83fcfbea3f615d9812dd003c04ba7420cc9a5b30de3
3
+ size 4999604052
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d34981fcd6563ddb6596a51c2af92f550da8c587cb7f07f2cebc8d4742a400d
3
+ size 572543797
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff