hf-100 commited on
Commit
ba06cb3
·
verified ·
1 Parent(s): f1e16e6

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/Meta-Llama-3.1-70B-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": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 131072,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 64,
18
+ "num_hidden_layers": 80,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 128004,
21
+ "pretraining_tp": 1,
22
+ "quantization_config": {
23
+ "bnb_4bit_compute_dtype": "bfloat16",
24
+ "bnb_4bit_quant_type": "nf4",
25
+ "bnb_4bit_use_double_quant": true,
26
+ "llm_int8_enable_fp32_cpu_offload": false,
27
+ "llm_int8_has_fp16_weight": false,
28
+ "llm_int8_skip_modules": null,
29
+ "llm_int8_threshold": 6.0,
30
+ "load_in_4bit": true,
31
+ "load_in_8bit": false,
32
+ "quant_method": "bitsandbytes"
33
+ },
34
+ "rms_norm_eps": 1e-05,
35
+ "rope_scaling": {
36
+ "factor": 8.0,
37
+ "high_freq_factor": 4.0,
38
+ "low_freq_factor": 1.0,
39
+ "original_max_position_embeddings": 8192,
40
+ "rope_type": "llama3"
41
+ },
42
+ "rope_theta": 500000.0,
43
+ "tie_word_embeddings": false,
44
+ "torch_dtype": "bfloat16",
45
+ "transformers_version": "4.44.2",
46
+ "unsloth_version": "2024.8",
47
+ "use_cache": true,
48
+ "vocab_size": 128256
49
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "max_length": 131072,
7
+ "pad_token_id": 128004,
8
+ "temperature": 0.6,
9
+ "top_p": 0.9,
10
+ "transformers_version": "4.44.2"
11
+ }
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec861df248c681660e7a074af360c813464f47e8e01a9c3f6c44cf57748d108e
3
+ size 4949082292
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2879efcae40b8e629324168c94755bf72a0205ae085d552770612f294f3bccb4
3
+ size 4977054930
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f367117ad99102d9210475be40f77f9dc134e524056b7d7631c050c44c322eca
3
+ size 4977088084
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f0cc49fff38b7371314f8bdcca2fe32165acf7485f894a0ee5c963b3d6c43fa
3
+ size 4933786844
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcc538bbcc989b879d0734c3911530ba31e79bd497ec033ba8b37e4b650326ff
3
+ size 4977055136
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad68ccdda6923ae237f0a7f6be3c340d5fa0de564eb31c6f084c9b395b7dd77
3
+ size 4977055097
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:669b71c1d528808f82734d0df64b577791430e104f5c2ac6b0ad055dafa734cf
3
+ size 4977088088
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5ed77896ad812d2bbbbba668c80911b81af170eb33bdcbfc412b514646ea521
3
+ size 4750027596
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff