Add model weights
Browse files- config.json +37 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/aiops/yangph/checkpoints/glide/checkpoint/experiments/longchat-13b-slim6b.glide.A100.tp1dp1.zero3.v1.0.sinkpi-slicing.longv2-16k-5e-6.lig-ce.no-mask.longsft-5e-6.s42/checkpoint-last",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaGlideDecoderLayer"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 5120,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 13824,
|
| 15 |
+
"max_position_embeddings": 2048,
|
| 16 |
+
"max_sequence_length": 16384,
|
| 17 |
+
"mlp_bias": false,
|
| 18 |
+
"model_type": "llama",
|
| 19 |
+
"num_attention_heads": 40,
|
| 20 |
+
"num_hidden_layers": 40,
|
| 21 |
+
"num_key_value_heads": 40,
|
| 22 |
+
"pad_token_id": 2,
|
| 23 |
+
"pretraining_tp": 1,
|
| 24 |
+
"rms_norm_eps": 1e-06,
|
| 25 |
+
"rope_condense_ratio": 8,
|
| 26 |
+
"rope_scaling": {
|
| 27 |
+
"factor": 8.0,
|
| 28 |
+
"rope_type": "linear",
|
| 29 |
+
"type": "linear"
|
| 30 |
+
},
|
| 31 |
+
"rope_theta": 10000.0,
|
| 32 |
+
"tie_word_embeddings": false,
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.46.3",
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 32000
|
| 37 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc62a1b18d6c939af895fa23fb8d1c1690fbd01e567dda8b156f52664cfe9e36
|
| 3 |
+
size 1688393672
|