mitultiwari commited on
Commit
f7fff2b
1 Parent(s): db29f55

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

README.md CHANGED
@@ -9,6 +9,7 @@ tags:
9
  - unsloth
10
  - llama
11
  - trl
 
12
  ---
13
 
14
  # Uploaded model
 
9
  - unsloth
10
  - llama
11
  - trl
12
+ - sft
13
  ---
14
 
15
  # Uploaded model
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "hidden_act": "silu",
15
+ "hidden_size": 4096,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 14336,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 8,
24
+ "pad_token_id": 128004,
25
+ "pretraining_tp": 1,
26
+ "quantization_config": {
27
+ "bnb_4bit_compute_dtype": "bfloat16",
28
+ "bnb_4bit_quant_type": "nf4",
29
+ "bnb_4bit_use_double_quant": true,
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": {
40
+ "factor": 8.0,
41
+ "high_freq_factor": 4.0,
42
+ "low_freq_factor": 1.0,
43
+ "original_max_position_embeddings": 8192,
44
+ "rope_type": "llama3"
45
+ },
46
+ "rope_theta": 500000.0,
47
+ "tie_word_embeddings": false,
48
+ "torch_dtype": "bfloat16",
49
+ "transformers_version": "4.44.2",
50
+ "unsloth_version": "2024.8",
51
+ "use_cache": true,
52
+ "vocab_size": 128256
53
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "max_length": 131072,
10
+ "pad_token_id": 128004,
11
+ "temperature": 0.6,
12
+ "top_p": 0.9,
13
+ "transformers_version": "4.44.2"
14
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cfef2776e546ff166c7da3c6e19a366f5f98b0c7e7d78459d9ce8595c544be4
3
+ size 4652072917
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5321ca97dd0968a3e2b676b3a42728e9f5327d516bcf0addd4e9cd61c068a1ad
3
+ size 1050673280
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff