danielhanchen
commited on
Commit
•
407f627
1
Parent(s):
efac62f
Upload config
Browse files- README.md +1 -2
- config.json +5 -2
README.md
CHANGED
@@ -1,15 +1,14 @@
|
|
1 |
---
|
2 |
language:
|
3 |
- en
|
4 |
-
license: apache-2.0
|
5 |
library_name: transformers
|
|
|
6 |
tags:
|
7 |
- unsloth
|
8 |
- transformers
|
9 |
- mistral
|
10 |
- mistral-7b
|
11 |
- bnb
|
12 |
-
|
13 |
---
|
14 |
|
15 |
# Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
|
|
|
1 |
---
|
2 |
language:
|
3 |
- en
|
|
|
4 |
library_name: transformers
|
5 |
+
license: apache-2.0
|
6 |
tags:
|
7 |
- unsloth
|
8 |
- transformers
|
9 |
- mistral
|
10 |
- mistral-7b
|
11 |
- bnb
|
|
|
12 |
---
|
13 |
|
14 |
# Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
|
config.json
CHANGED
@@ -6,6 +6,7 @@
|
|
6 |
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 1,
|
8 |
"eos_token_id": 2,
|
|
|
9 |
"hidden_act": "silu",
|
10 |
"hidden_size": 4096,
|
11 |
"initializer_range": 0.02,
|
@@ -15,9 +16,11 @@
|
|
15 |
"num_attention_heads": 32,
|
16 |
"num_hidden_layers": 32,
|
17 |
"num_key_value_heads": 8,
|
18 |
-
"pad_token_id": 2,
|
19 |
"quantization_config": {
|
|
|
|
|
20 |
"bnb_4bit_compute_dtype": "bfloat16",
|
|
|
21 |
"bnb_4bit_quant_type": "nf4",
|
22 |
"bnb_4bit_use_double_quant": true,
|
23 |
"llm_int8_enable_fp32_cpu_offload": false,
|
@@ -33,7 +36,7 @@
|
|
33 |
"sliding_window": 4096,
|
34 |
"tie_word_embeddings": false,
|
35 |
"torch_dtype": "bfloat16",
|
36 |
-
"transformers_version": "4.
|
37 |
"use_cache": true,
|
38 |
"vocab_size": 32000
|
39 |
}
|
|
|
6 |
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 1,
|
8 |
"eos_token_id": 2,
|
9 |
+
"head_dim": 128,
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 4096,
|
12 |
"initializer_range": 0.02,
|
|
|
16 |
"num_attention_heads": 32,
|
17 |
"num_hidden_layers": 32,
|
18 |
"num_key_value_heads": 8,
|
|
|
19 |
"quantization_config": {
|
20 |
+
"_load_in_4bit": true,
|
21 |
+
"_load_in_8bit": false,
|
22 |
"bnb_4bit_compute_dtype": "bfloat16",
|
23 |
+
"bnb_4bit_quant_storage": "uint8",
|
24 |
"bnb_4bit_quant_type": "nf4",
|
25 |
"bnb_4bit_use_double_quant": true,
|
26 |
"llm_int8_enable_fp32_cpu_offload": false,
|
|
|
36 |
"sliding_window": 4096,
|
37 |
"tie_word_embeddings": false,
|
38 |
"torch_dtype": "bfloat16",
|
39 |
+
"transformers_version": "4.44.0",
|
40 |
"use_cache": true,
|
41 |
"vocab_size": 32000
|
42 |
}
|