mrm8488 commited on
Commit
eac756d
1 Parent(s): e4745e0

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

README.md CHANGED
@@ -8,6 +8,7 @@ tags:
8
  - unsloth
9
  - llama
10
  - trl
 
11
  base_model: unsloth/llama-3-8b-bnb-4bit
12
  ---
13
 
 
8
  - unsloth
9
  - llama
10
  - trl
11
+ - sft
12
  base_model: unsloth/llama-3-8b-bnb-4bit
13
  ---
14
 
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/llama-3-8b-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": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "quantization_config": {
21
+ "bnb_4bit_compute_dtype": "bfloat16",
22
+ "bnb_4bit_quant_type": "nf4",
23
+ "bnb_4bit_use_double_quant": true,
24
+ "llm_int8_enable_fp32_cpu_offload": false,
25
+ "llm_int8_has_fp16_weight": false,
26
+ "llm_int8_skip_modules": null,
27
+ "llm_int8_threshold": 6.0,
28
+ "load_in_4bit": true,
29
+ "load_in_8bit": false,
30
+ "quant_method": "bitsandbytes"
31
+ },
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_scaling": null,
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.40.2",
38
+ "unsloth_version": "2024.5",
39
+ "use_cache": true,
40
+ "vocab_size": 128256
41
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": 128001,
5
+ "max_length": 4096,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.40.2"
9
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d334103f99535a8d8344ccec6e1a41090efb9fd6391cebc83051e414c24498fa
3
+ size 4652072930
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b09b2f5119431f75c6dbcce7a5048894e87c519bdd3f4f162def6b1de2dc0f6
3
+ size 1050673280
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff