Training in progress, step 100
Browse files- config.json +21 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ModernLLMForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": 1,
|
| 6 |
+
"dtype": "float32",
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_size": 768,
|
| 9 |
+
"intermediate_size": 2048,
|
| 10 |
+
"max_position_embeddings": 2048,
|
| 11 |
+
"model_type": "modern_llm",
|
| 12 |
+
"num_attention_heads": 12,
|
| 13 |
+
"num_hidden_layers": 12,
|
| 14 |
+
"num_key_value_heads": 4,
|
| 15 |
+
"pad_token_id": 0,
|
| 16 |
+
"rms_norm_eps": 1e-06,
|
| 17 |
+
"rope_theta": 1000000.0,
|
| 18 |
+
"transformers_version": "5.15.0",
|
| 19 |
+
"use_cache": false,
|
| 20 |
+
"vocab_size": 151936
|
| 21 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a746d1236d3fa2278997b4fe8b4862ddd7e6f6943a953a1e3a3dcb4e53feef47
|
| 3 |
+
size 1235573136
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edcf268bd411db3d29ef48993a8be91c48e0928ee9333782a1c880f5f6a50c85
|
| 3 |
+
size 5201
|