Upload LlamaForCausalLM
Browse files- config.json +30 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "llmware/bling-sheared-llama-1.3b-0.1",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"description": "Instruct train fine-tuning using distilled knowledge based critical reading tasks training dataset",
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 2048,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 5504,
|
13 |
+
"max_position_embeddings": 4096,
|
14 |
+
"model_name": "bling-sheared-llama-1.3b-0.1",
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 16,
|
17 |
+
"num_hidden_layers": 24,
|
18 |
+
"num_key_value_heads": 16,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"training_comments": "sheared-llama-1.3b-base",
|
26 |
+
"training_timestamp": "Sun Oct 22 14:31:15 2023",
|
27 |
+
"transformers_version": "4.31.0",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 32000
|
30 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.31.0"
|
7 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:484d08266f18c39d91e8daebad043835ccea407d1de0e9bc4e5be23a57d6d11f
|
3 |
+
size 5381778946
|