iFaz commited on
Commit
b02d39a
·
verified ·
1 Parent(s): 0b7c390

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/meta-llama-3.1-8b-instruct-unsloth-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
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 128004,
22
+ "pretraining_tp": 1,
23
+ "quantization_config": {
24
+ "bnb_4bit_compute_dtype": "float16",
25
+ "bnb_4bit_quant_type": "nf4",
26
+ "bnb_4bit_use_double_quant": true,
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_has_fp16_weight": false,
29
+ "llm_int8_skip_modules": null,
30
+ "llm_int8_threshold": 6.0,
31
+ "load_in_4bit": true,
32
+ "load_in_8bit": false,
33
+ "quant_method": "bitsandbytes"
34
+ },
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_scaling": {
37
+ "factor": 8.0,
38
+ "high_freq_factor": 4.0,
39
+ "low_freq_factor": 1.0,
40
+ "original_max_position_embeddings": 8192,
41
+ "rope_type": "llama3"
42
+ },
43
+ "rope_theta": 500000.0,
44
+ "tie_word_embeddings": false,
45
+ "torch_dtype": "float16",
46
+ "transformers_version": "4.48.3",
47
+ "unsloth_fixed": true,
48
+ "unsloth_version": "2025.2.15",
49
+ "use_cache": true,
50
+ "vocab_size": 128256
51
+ }
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": "4.48.3"
14
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:280b1810c769c03eedb55dcf0820a7b9d7b8948126cdb3c086d3d556c46d9983
3
+ size 4913507395
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e9a36ad418b0cd9b253f65771552d7dc05cf1abf1170b94de4b4d546aac255d
3
+ size 1050673280
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff