Dogge commited on
Commit
2ee9f1c
1 Parent(s): 31a6f37

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-3-70b-Instruct-bnb-4bit
12
  ---
13
 
 
8
  - unsloth
9
  - llama
10
  - trl
11
+ - sft
12
  base_model: unsloth/llama-3-70b-Instruct-bnb-4bit
13
  ---
14
 
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/llama-3-70b-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": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 64,
17
+ "num_hidden_layers": 80,
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": "4.40.0",
38
+ "unsloth_version": "2024.4",
39
+ "use_cache": true,
40
+ "vocab_size": 128256
41
+ }
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": "4.40.0"
9
+ }
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:582fbaa20f9f72149cf56182cc43196b64a5563c81effe2ef3f72166fecc8af4
3
+ size 4949082241
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:993609f99db3c3d5f68f8487317ff94b1021985e6cb18373c3254916a782c69b
3
+ size 4977054860
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68aae786c3ea156e3649a88c79a5dcd3030f965a6ad1529b0d35067ba804adec
3
+ size 4977088015
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30c0693f4710c0c51be791843f1112ce773b140fbc8ff2269f74b4b663f5066a
3
+ size 4933786767
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a7f6083d542d80e4b36e75faf35c4b50b89f0e7e2725fd785daf98d5a177972
3
+ size 4977055043
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f23b07a78d3fb2fb71ef46c9a58dcf182992de27a39799e0c7cbfb976d5753f
3
+ size 4977055015
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90061967c3f33a057776340db433786b89e5aa535fd1acc5be415d01499bda86
3
+ size 4977088005
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace0afacad3ac1c952b3f1e0c73438f2fdc2326fe9409bf43e7ff1c1f6a41c18
3
+ size 4750027555
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff