Trained with Unsloth
Browse files- README.md +1 -0
- config.json +31 -0
- generation_config.json +8 -0
- pytorch_model.bin +3 -0
README.md
CHANGED
@@ -9,6 +9,7 @@ tags:
|
|
9 |
- unsloth
|
10 |
- llama
|
11 |
- trl
|
|
|
12 |
---
|
13 |
|
14 |
# Uploaded model
|
|
|
9 |
- unsloth
|
10 |
- llama
|
11 |
- trl
|
12 |
+
- sft
|
13 |
---
|
14 |
|
15 |
# Uploaded model
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "HuggingFaceTB/SmolLM-360M",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 960,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 2560,
|
14 |
+
"max_position_embeddings": 2048,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 15,
|
18 |
+
"num_hidden_layers": 32,
|
19 |
+
"num_key_value_heads": 5,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"pretraining_tp": 1,
|
22 |
+
"rms_norm_eps": 1e-05,
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rope_theta": 10000.0,
|
25 |
+
"tie_word_embeddings": true,
|
26 |
+
"torch_dtype": "float16",
|
27 |
+
"transformers_version": "4.44.2",
|
28 |
+
"unsloth_version": "2024.8",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 49152
|
31 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"max_length": 2048,
|
6 |
+
"pad_token_id": 0,
|
7 |
+
"transformers_version": "4.44.2"
|
8 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e79bc4b0a6378942d475af7c21eabd79cabe76d164de65323393ad8fb6a18e2
|
3 |
+
size 818112470
|