funnyNeurons commited on
Commit
380273f
1 Parent(s): 83d2af8

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

README.md CHANGED
@@ -8,6 +8,7 @@ tags:
8
  - unsloth
9
  - gemma
10
  - trl
 
11
  base_model: unsloth/gemma-7b-bnb-4bit
12
  ---
13
 
 
8
  - unsloth
9
  - gemma
10
  - trl
11
+ - sft
12
  base_model: unsloth/gemma-7b-bnb-4bit
13
  ---
14
 
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_size": 3072,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 24576,
15
+ "max_position_embeddings": 8192,
16
+ "model_type": "gemma",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 16,
20
+ "pad_token_id": 0,
21
+ "quantization_config": {
22
+ "bnb_4bit_compute_dtype": "float16",
23
+ "bnb_4bit_quant_type": "nf4",
24
+ "bnb_4bit_use_double_quant": true,
25
+ "llm_int8_enable_fp32_cpu_offload": false,
26
+ "llm_int8_has_fp16_weight": false,
27
+ "llm_int8_skip_modules": null,
28
+ "llm_int8_threshold": 6.0,
29
+ "load_in_4bit": true,
30
+ "load_in_8bit": false,
31
+ "quant_method": "bitsandbytes"
32
+ },
33
+ "rms_norm_eps": 1e-06,
34
+ "rope_scaling": null,
35
+ "rope_theta": 10000.0,
36
+ "torch_dtype": "float16",
37
+ "transformers_version": "4.38.2",
38
+ "unsloth_version": "2024.3",
39
+ "use_cache": true,
40
+ "vocab_size": 256000
41
+ }
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": "4.38.2"
7
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87566574c4a9510950179a3f9deaf3c66b51911b08abf22d5ee11610e933677c
3
+ size 4999604058
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:248f035bd1b454ca6cf805896645e5350ece5d54a11ee4ed72954e26a13eba26
3
+ size 572543806
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff