danielhanchen
commited on
Commit
•
122bf48
1
Parent(s):
45a6d71
Upload LlamaForCausalLM
Browse files- README.md +1 -2
- config.json +3 -2
- generation_config.json +1 -1
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +2 -2
- model.safetensors.index.json +1 -1
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 |
- codellama
|
10 |
- bnb
|
11 |
- 4-bit
|
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 |
- codellama
|
10 |
- bnb
|
11 |
- 4-bit
|
|
|
12 |
---
|
13 |
|
14 |
# Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
|
config.json
CHANGED
@@ -12,16 +12,17 @@
|
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 13824,
|
14 |
"max_position_embeddings": 16384,
|
|
|
15 |
"model_type": "llama",
|
16 |
"num_attention_heads": 40,
|
17 |
"num_hidden_layers": 40,
|
18 |
"num_key_value_heads": 40,
|
19 |
-
"pad_token_id": 0,
|
20 |
"pretraining_tp": 1,
|
21 |
"quantization_config": {
|
22 |
"_load_in_4bit": true,
|
23 |
"_load_in_8bit": false,
|
24 |
"bnb_4bit_compute_dtype": "bfloat16",
|
|
|
25 |
"bnb_4bit_quant_type": "nf4",
|
26 |
"bnb_4bit_use_double_quant": true,
|
27 |
"llm_int8_enable_fp32_cpu_offload": false,
|
@@ -37,7 +38,7 @@
|
|
37 |
"rope_theta": 1000000,
|
38 |
"tie_word_embeddings": false,
|
39 |
"torch_dtype": "bfloat16",
|
40 |
-
"transformers_version": "4.
|
41 |
"use_cache": true,
|
42 |
"vocab_size": 32016
|
43 |
}
|
|
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 13824,
|
14 |
"max_position_embeddings": 16384,
|
15 |
+
"mlp_bias": false,
|
16 |
"model_type": "llama",
|
17 |
"num_attention_heads": 40,
|
18 |
"num_hidden_layers": 40,
|
19 |
"num_key_value_heads": 40,
|
|
|
20 |
"pretraining_tp": 1,
|
21 |
"quantization_config": {
|
22 |
"_load_in_4bit": true,
|
23 |
"_load_in_8bit": false,
|
24 |
"bnb_4bit_compute_dtype": "bfloat16",
|
25 |
+
"bnb_4bit_quant_storage": "uint8",
|
26 |
"bnb_4bit_quant_type": "nf4",
|
27 |
"bnb_4bit_use_double_quant": true,
|
28 |
"llm_int8_enable_fp32_cpu_offload": false,
|
|
|
38 |
"rope_theta": 1000000,
|
39 |
"tie_word_embeddings": false,
|
40 |
"torch_dtype": "bfloat16",
|
41 |
+
"transformers_version": "4.43.3",
|
42 |
"use_cache": true,
|
43 |
"vocab_size": 32016
|
44 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.43.3"
|
6 |
}
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a292bcb31805a335961ba5e98ed2bf48e5be59adebd7921da6ab233c060e77ea
|
3 |
+
size 4999962118
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1251542793126e75e5b74eeeceb3bb57c200ad8649eff7a32a53efdc0b06eedd
|
3 |
+
size 2202347144
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00002-of-00002.safetensors",
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 7202098830
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00002-of-00002.safetensors",
|