ahmedgongi commited on
Commit
e45600b
1 Parent(s): e010483

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/llama-3-8b-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": 128009,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
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-05,
34
+ "rope_scaling": null,
35
+ "rope_theta": 500000.0,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "float16",
38
+ "transformers_version": "4.41.1",
39
+ "unsloth_version": "2024.5",
40
+ "use_cache": false,
41
+ "vocab_size": 128256
42
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128009
7
+ ],
8
+ "transformers_version": "4.41.1"
9
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e614c5e1e1c97b84458306fe7ca0037c8ab2055fd612e84c3a036120c3bf5a24
3
+ size 4652072868
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8005050c5e27c8232d9ce04f03631ce67bcc362c80fc57079bda23b498695c20
3
+ size 1050673280
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff