LeonKogler
commited on
Commit
•
7b526d7
1
Parent(s):
f20437d
Trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- config.json +6 -6
- generation_config.json +6 -6
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +1 -1
- model.safetensors.index.json +1 -1
config.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "unsloth/llama-3-8b-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":
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 4096,
|
12 |
"initializer_range": 0.02,
|
@@ -19,7 +19,7 @@
|
|
19 |
"num_key_value_heads": 8,
|
20 |
"pretraining_tp": 1,
|
21 |
"quantization_config": {
|
22 |
-
"bnb_4bit_compute_dtype": "
|
23 |
"bnb_4bit_quant_type": "nf4",
|
24 |
"bnb_4bit_use_double_quant": true,
|
25 |
"llm_int8_enable_fp32_cpu_offload": false,
|
@@ -34,9 +34,9 @@
|
|
34 |
"rope_scaling": null,
|
35 |
"rope_theta": 500000.0,
|
36 |
"tie_word_embeddings": false,
|
37 |
-
"torch_dtype": "
|
38 |
-
"transformers_version": "4.
|
39 |
-
"unsloth_version": "2024.
|
40 |
"use_cache": true,
|
41 |
"vocab_size": 128256
|
42 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "unsloth/llama-3-8b-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": 4096,
|
12 |
"initializer_range": 0.02,
|
|
|
19 |
"num_key_value_heads": 8,
|
20 |
"pretraining_tp": 1,
|
21 |
"quantization_config": {
|
22 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
23 |
"bnb_4bit_quant_type": "nf4",
|
24 |
"bnb_4bit_use_double_quant": true,
|
25 |
"llm_int8_enable_fp32_cpu_offload": false,
|
|
|
34 |
"rope_scaling": null,
|
35 |
"rope_theta": 500000.0,
|
36 |
"tie_word_embeddings": false,
|
37 |
+
"torch_dtype": "bfloat16",
|
38 |
+
"transformers_version": "4.42.4",
|
39 |
+
"unsloth_version": "2024.7",
|
40 |
"use_cache": true,
|
41 |
"vocab_size": 128256
|
42 |
}
|
generation_config.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
|
|
2 |
"bos_token_id": 128000,
|
3 |
-
"
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
"
|
8 |
-
"transformers_version": "4.41.2"
|
9 |
}
|
|
|
1 |
{
|
2 |
+
"_from_model_config": true,
|
3 |
"bos_token_id": 128000,
|
4 |
+
"eos_token_id": [
|
5 |
+
128001,
|
6 |
+
128009
|
7 |
+
],
|
8 |
+
"transformers_version": "4.42.4"
|
|
|
9 |
}
|
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:fcb97bdf82180811b56f447ced0a001d8d9f5b0804502182776ec7ae3efbdcbc
|
3 |
+
size 4652072942
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1050673280
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:674610adfedb7f19d21475a7280d6b34774894e654f1d50f4c24444ba7bd0d04
|
3 |
size 1050673280
|
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": 5702577758
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00002-of-00002.safetensors",
|