Commit
•
d2ad0cc
1
Parent(s):
9aae6fd
Upload config
Browse files- README.md +1 -2
- config.json +5 -3
README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
-
license: apache-2.0
|
| 5 |
library_name: transformers
|
|
|
|
| 6 |
tags:
|
| 7 |
- unsloth
|
| 8 |
- transformers
|
|
@@ -11,7 +11,6 @@ tags:
|
|
| 11 |
- mistral-instruct
|
| 12 |
- instruct
|
| 13 |
- bnb
|
| 14 |
-
|
| 15 |
---
|
| 16 |
|
| 17 |
# 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
|
|
|
|
| 11 |
- mistral-instruct
|
| 12 |
- instruct
|
| 13 |
- bnb
|
|
|
|
| 14 |
---
|
| 15 |
|
| 16 |
# Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
|
config.json
CHANGED
|
@@ -1,11 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"MistralForCausalLM"
|
| 5 |
],
|
| 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,
|
|
@@ -15,13 +16,14 @@
|
|
| 15 |
"num_attention_heads": 32,
|
| 16 |
"num_hidden_layers": 32,
|
| 17 |
"num_key_value_heads": 8,
|
| 18 |
-
"pad_token_id":
|
| 19 |
"rms_norm_eps": 1e-05,
|
| 20 |
"rope_theta": 1000000.0,
|
| 21 |
"sliding_window": null,
|
| 22 |
"tie_word_embeddings": false,
|
| 23 |
"torch_dtype": "bfloat16",
|
| 24 |
-
"transformers_version": "4.
|
|
|
|
| 25 |
"use_cache": true,
|
| 26 |
"vocab_size": 32000
|
| 27 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "unsloth/Mistral-7B-Instruct-v0.2",
|
| 3 |
"architectures": [
|
| 4 |
"MistralForCausalLM"
|
| 5 |
],
|
| 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 |
+
"pad_token_id": 0,
|
| 20 |
"rms_norm_eps": 1e-05,
|
| 21 |
"rope_theta": 1000000.0,
|
| 22 |
"sliding_window": null,
|
| 23 |
"tie_word_embeddings": false,
|
| 24 |
"torch_dtype": "bfloat16",
|
| 25 |
+
"transformers_version": "4.44.0",
|
| 26 |
+
"unsloth_version": "2024.8",
|
| 27 |
"use_cache": true,
|
| 28 |
"vocab_size": 32000
|
| 29 |
}
|