Upload config
Browse files- README.md +1 -2
- config.json +4 -2
README.md
CHANGED
|
@@ -1,14 +1,13 @@
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
-
license: apache-2.0
|
| 5 |
library_name: transformers
|
|
|
|
| 6 |
tags:
|
| 7 |
- unsloth
|
| 8 |
- transformers
|
| 9 |
- tinyllama
|
| 10 |
- chat
|
| 11 |
-
|
| 12 |
---
|
| 13 |
|
| 14 |
# 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 |
- tinyllama
|
| 10 |
- chat
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
# Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
@@ -12,6 +12,7 @@
|
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 5632,
|
| 14 |
"max_position_embeddings": 2048,
|
|
|
|
| 15 |
"model_type": "llama",
|
| 16 |
"num_attention_heads": 32,
|
| 17 |
"num_hidden_layers": 22,
|
|
@@ -23,7 +24,8 @@
|
|
| 23 |
"rope_theta": 10000.0,
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
"torch_dtype": "bfloat16",
|
| 26 |
-
"transformers_version": "4.
|
|
|
|
| 27 |
"use_cache": true,
|
| 28 |
"vocab_size": 32000
|
| 29 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "unsloth/tinyllama-chat",
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
|
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 5632,
|
| 14 |
"max_position_embeddings": 2048,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
"model_type": "llama",
|
| 17 |
"num_attention_heads": 32,
|
| 18 |
"num_hidden_layers": 22,
|
|
|
|
| 24 |
"rope_theta": 10000.0,
|
| 25 |
"tie_word_embeddings": false,
|
| 26 |
"torch_dtype": "bfloat16",
|
| 27 |
+
"transformers_version": "4.44.0",
|
| 28 |
+
"unsloth_version": "2024.8",
|
| 29 |
"use_cache": true,
|
| 30 |
"vocab_size": 32000
|
| 31 |
}
|