derekwong commited on
Commit
6d81a8c
·
verified ·
1 Parent(s): 43d16f4

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 128009,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 8192,
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": 128255,
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": null,
36
+ "rope_theta": 500000.0,
37
+ "tie_word_embeddings": false,
38
+ "torch_dtype": "bfloat16",
39
+ "transformers_version": "4.44.2",
40
+ "unsloth_version": "2024.8",
41
+ "use_cache": true,
42
+ "vocab_size": 128256
43
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128009
7
+ ],
8
+ "max_length": 8192,
9
+ "pad_token_id": 128255,
10
+ "temperature": 0.6,
11
+ "top_p": 0.9,
12
+ "transformers_version": "4.44.2"
13
+ }
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88e0c10c127245655253c775f99b70f2bebf108bfba5e320d96e856328ff1af3
3
+ size 4949082239
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6679c4ee0f39cb7d37b59b55c2d00d980ff5adfe1e9a58fb06e5ac949cb9a197
3
+ size 4977054853
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07df107a0bba9adf4c10536b1477a765ec1fd6928d87454d9f6a40cd923161bd
3
+ size 4977088014
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84a6f9a6358cc4bf65ec62351a3ee4cf11d25f95ac840ea1e76378441c7dae50
3
+ size 4933786759
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34958fea7b86d6c2473929eaa62827af37ac8b0e4d303ddddb339b73a89e9e35
3
+ size 4977055054
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8c8c24ea9f85b70706db9425a0b937328d8b9bd47167fd0b4b1356bf68c34c0
3
+ size 4977055024
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f3dcd794f7e1eebc5743920337255eeaa9fc7d46ceda803befd4355de9398a3
3
+ size 4977088014
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08b1a81f3945d25313f8c62e234d8fb55129908a6c5149d8c6efb0e16e0409f1
3
+ size 4750027548
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff