Initial commit
Browse files- logs.txt +0 -0
- mlc-chat-config.json +40 -0
- ndarray-cache-b16.json +2631 -0
- ndarray-cache.json +2631 -0
- params_shard_0.bin +3 -0
- params_shard_1.bin +3 -0
- params_shard_10.bin +3 -0
- params_shard_11.bin +3 -0
- params_shard_12.bin +3 -0
- params_shard_13.bin +3 -0
- params_shard_14.bin +3 -0
- params_shard_15.bin +3 -0
- params_shard_16.bin +3 -0
- params_shard_17.bin +3 -0
- params_shard_18.bin +3 -0
- params_shard_19.bin +3 -0
- params_shard_2.bin +3 -0
- params_shard_20.bin +3 -0
- params_shard_21.bin +3 -0
- params_shard_22.bin +3 -0
- params_shard_23.bin +3 -0
- params_shard_3.bin +3 -0
- params_shard_4.bin +3 -0
- params_shard_5.bin +3 -0
- params_shard_6.bin +3 -0
- params_shard_7.bin +3 -0
- params_shard_8.bin +3 -0
- params_shard_9.bin +3 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +40 -0
logs.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
mlc-chat-config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_type": "llama",
|
3 |
+
"quantization": "q4f32_1",
|
4 |
+
"model_config": {
|
5 |
+
"hidden_size": 2048,
|
6 |
+
"intermediate_size": 5632,
|
7 |
+
"num_attention_heads": 32,
|
8 |
+
"num_hidden_layers": 22,
|
9 |
+
"rms_norm_eps": 1e-05,
|
10 |
+
"vocab_size": 32000,
|
11 |
+
"position_embedding_base": 10000.0,
|
12 |
+
"context_window_size": 4096,
|
13 |
+
"prefill_chunk_size": 2048,
|
14 |
+
"num_key_value_heads": 4,
|
15 |
+
"head_dim": 64,
|
16 |
+
"tensor_parallel_shards": 1
|
17 |
+
},
|
18 |
+
"vocab_size": 32000,
|
19 |
+
"context_window_size": 4096,
|
20 |
+
"sliding_window_size": -1,
|
21 |
+
"prefill_chunk_size": 2048,
|
22 |
+
"attention_sink_size": -1,
|
23 |
+
"tensor_parallel_shards": 1,
|
24 |
+
"mean_gen_len": 128,
|
25 |
+
"max_gen_len": 512,
|
26 |
+
"shift_fill_factor": 0.3,
|
27 |
+
"temperature": 0.7,
|
28 |
+
"repetition_penalty": 1.0,
|
29 |
+
"top_p": 0.95,
|
30 |
+
"conv_template": "chatml",
|
31 |
+
"pad_token_id": 0,
|
32 |
+
"bos_token_id": 1,
|
33 |
+
"eos_token_id": 2,
|
34 |
+
"tokenizer_files": [
|
35 |
+
"tokenizer.model",
|
36 |
+
"tokenizer.json",
|
37 |
+
"tokenizer_config.json"
|
38 |
+
],
|
39 |
+
"version": "0.1.0"
|
40 |
+
}
|
ndarray-cache-b16.json
ADDED
@@ -0,0 +1,2631 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"ParamSize": 225,
|
4 |
+
"ParamBytes": 687841280.0,
|
5 |
+
"BitsPerParam": 5.0022620095953885
|
6 |
+
},
|
7 |
+
"records": [
|
8 |
+
{
|
9 |
+
"dataPath": "params_shard_0.bin",
|
10 |
+
"format": "raw-shard",
|
11 |
+
"nbytes": 32768000,
|
12 |
+
"records": [
|
13 |
+
{
|
14 |
+
"name": "lm_head.q_weight",
|
15 |
+
"shape": [
|
16 |
+
32000,
|
17 |
+
256
|
18 |
+
],
|
19 |
+
"dtype": "uint32",
|
20 |
+
"format": "f32-to-bf16",
|
21 |
+
"nbytes": 32768000,
|
22 |
+
"byteOffset": 0
|
23 |
+
}
|
24 |
+
],
|
25 |
+
"md5sum": "6acf42e9e3428cda2d937cedfbc2bdbe"
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"dataPath": "params_shard_1.bin",
|
29 |
+
"format": "raw-shard",
|
30 |
+
"nbytes": 32768000,
|
31 |
+
"records": [
|
32 |
+
{
|
33 |
+
"name": "model.embed_tokens.q_weight",
|
34 |
+
"shape": [
|
35 |
+
32000,
|
36 |
+
256
|
37 |
+
],
|
38 |
+
"dtype": "uint32",
|
39 |
+
"format": "f32-to-bf16",
|
40 |
+
"nbytes": 32768000,
|
41 |
+
"byteOffset": 0
|
42 |
+
}
|
43 |
+
],
|
44 |
+
"md5sum": "5a4dc43f3da7ea1f953c0c460796a420"
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"dataPath": "params_shard_2.bin",
|
48 |
+
"format": "raw-shard",
|
49 |
+
"nbytes": 32976896,
|
50 |
+
"records": [
|
51 |
+
{
|
52 |
+
"name": "lm_head.q_scale",
|
53 |
+
"shape": [
|
54 |
+
32000,
|
55 |
+
64
|
56 |
+
],
|
57 |
+
"dtype": "bfloat16",
|
58 |
+
"format": "raw",
|
59 |
+
"nbytes": 4096000,
|
60 |
+
"byteOffset": 0
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"name": "model.embed_tokens.q_scale",
|
64 |
+
"shape": [
|
65 |
+
32000,
|
66 |
+
64
|
67 |
+
],
|
68 |
+
"dtype": "bfloat16",
|
69 |
+
"format": "raw",
|
70 |
+
"nbytes": 4096000,
|
71 |
+
"byteOffset": 4096000
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"name": "model.layers.0.input_layernorm.weight",
|
75 |
+
"shape": [
|
76 |
+
2048
|
77 |
+
],
|
78 |
+
"dtype": "bfloat16",
|
79 |
+
"format": "raw",
|
80 |
+
"nbytes": 4096,
|
81 |
+
"byteOffset": 8192000
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"name": "model.layers.0.mlp.down_proj.q_weight",
|
85 |
+
"shape": [
|
86 |
+
2048,
|
87 |
+
704
|
88 |
+
],
|
89 |
+
"dtype": "uint32",
|
90 |
+
"format": "f32-to-bf16",
|
91 |
+
"nbytes": 5767168,
|
92 |
+
"byteOffset": 8196096
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"name": "model.layers.0.mlp.down_proj.q_scale",
|
96 |
+
"shape": [
|
97 |
+
2048,
|
98 |
+
176
|
99 |
+
],
|
100 |
+
"dtype": "bfloat16",
|
101 |
+
"format": "raw",
|
102 |
+
"nbytes": 720896,
|
103 |
+
"byteOffset": 13963264
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"name": "model.layers.0.mlp.gate_up_proj.q_weight",
|
107 |
+
"shape": [
|
108 |
+
11264,
|
109 |
+
256
|
110 |
+
],
|
111 |
+
"dtype": "uint32",
|
112 |
+
"format": "f32-to-bf16",
|
113 |
+
"nbytes": 11534336,
|
114 |
+
"byteOffset": 14684160
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
|
118 |
+
"shape": [
|
119 |
+
11264,
|
120 |
+
64
|
121 |
+
],
|
122 |
+
"dtype": "bfloat16",
|
123 |
+
"format": "raw",
|
124 |
+
"nbytes": 1441792,
|
125 |
+
"byteOffset": 26218496
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"name": "model.layers.0.post_attention_layernorm.weight",
|
129 |
+
"shape": [
|
130 |
+
2048
|
131 |
+
],
|
132 |
+
"dtype": "bfloat16",
|
133 |
+
"format": "raw",
|
134 |
+
"nbytes": 4096,
|
135 |
+
"byteOffset": 27660288
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"name": "model.layers.0.self_attn.qkv_proj.q_weight",
|
139 |
+
"shape": [
|
140 |
+
2560,
|
141 |
+
256
|
142 |
+
],
|
143 |
+
"dtype": "uint32",
|
144 |
+
"format": "f32-to-bf16",
|
145 |
+
"nbytes": 2621440,
|
146 |
+
"byteOffset": 27664384
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"name": "model.layers.0.self_attn.qkv_proj.q_scale",
|
150 |
+
"shape": [
|
151 |
+
2560,
|
152 |
+
64
|
153 |
+
],
|
154 |
+
"dtype": "bfloat16",
|
155 |
+
"format": "raw",
|
156 |
+
"nbytes": 327680,
|
157 |
+
"byteOffset": 30285824
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"name": "model.layers.0.self_attn.o_proj.q_weight",
|
161 |
+
"shape": [
|
162 |
+
2048,
|
163 |
+
256
|
164 |
+
],
|
165 |
+
"dtype": "uint32",
|
166 |
+
"format": "f32-to-bf16",
|
167 |
+
"nbytes": 2097152,
|
168 |
+
"byteOffset": 30613504
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"name": "model.layers.0.self_attn.o_proj.q_scale",
|
172 |
+
"shape": [
|
173 |
+
2048,
|
174 |
+
64
|
175 |
+
],
|
176 |
+
"dtype": "bfloat16",
|
177 |
+
"format": "raw",
|
178 |
+
"nbytes": 262144,
|
179 |
+
"byteOffset": 32710656
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"name": "model.layers.1.input_layernorm.weight",
|
183 |
+
"shape": [
|
184 |
+
2048
|
185 |
+
],
|
186 |
+
"dtype": "bfloat16",
|
187 |
+
"format": "raw",
|
188 |
+
"nbytes": 4096,
|
189 |
+
"byteOffset": 32972800
|
190 |
+
}
|
191 |
+
],
|
192 |
+
"md5sum": "b8052fae94b2f9484c7fed0f270034b6"
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"dataPath": "params_shard_3.bin",
|
196 |
+
"format": "raw-shard",
|
197 |
+
"nbytes": 31268864,
|
198 |
+
"records": [
|
199 |
+
{
|
200 |
+
"name": "model.layers.1.mlp.down_proj.q_weight",
|
201 |
+
"shape": [
|
202 |
+
2048,
|
203 |
+
704
|
204 |
+
],
|
205 |
+
"dtype": "uint32",
|
206 |
+
"format": "f32-to-bf16",
|
207 |
+
"nbytes": 5767168,
|
208 |
+
"byteOffset": 0
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"name": "model.layers.1.mlp.down_proj.q_scale",
|
212 |
+
"shape": [
|
213 |
+
2048,
|
214 |
+
176
|
215 |
+
],
|
216 |
+
"dtype": "bfloat16",
|
217 |
+
"format": "raw",
|
218 |
+
"nbytes": 720896,
|
219 |
+
"byteOffset": 5767168
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"name": "model.layers.1.mlp.gate_up_proj.q_weight",
|
223 |
+
"shape": [
|
224 |
+
11264,
|
225 |
+
256
|
226 |
+
],
|
227 |
+
"dtype": "uint32",
|
228 |
+
"format": "f32-to-bf16",
|
229 |
+
"nbytes": 11534336,
|
230 |
+
"byteOffset": 6488064
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
|
234 |
+
"shape": [
|
235 |
+
11264,
|
236 |
+
64
|
237 |
+
],
|
238 |
+
"dtype": "bfloat16",
|
239 |
+
"format": "raw",
|
240 |
+
"nbytes": 1441792,
|
241 |
+
"byteOffset": 18022400
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"name": "model.layers.1.post_attention_layernorm.weight",
|
245 |
+
"shape": [
|
246 |
+
2048
|
247 |
+
],
|
248 |
+
"dtype": "bfloat16",
|
249 |
+
"format": "raw",
|
250 |
+
"nbytes": 4096,
|
251 |
+
"byteOffset": 19464192
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"name": "model.layers.1.self_attn.qkv_proj.q_weight",
|
255 |
+
"shape": [
|
256 |
+
2560,
|
257 |
+
256
|
258 |
+
],
|
259 |
+
"dtype": "uint32",
|
260 |
+
"format": "f32-to-bf16",
|
261 |
+
"nbytes": 2621440,
|
262 |
+
"byteOffset": 19468288
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
|
266 |
+
"shape": [
|
267 |
+
2560,
|
268 |
+
64
|
269 |
+
],
|
270 |
+
"dtype": "bfloat16",
|
271 |
+
"format": "raw",
|
272 |
+
"nbytes": 327680,
|
273 |
+
"byteOffset": 22089728
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"name": "model.layers.1.self_attn.o_proj.q_weight",
|
277 |
+
"shape": [
|
278 |
+
2048,
|
279 |
+
256
|
280 |
+
],
|
281 |
+
"dtype": "uint32",
|
282 |
+
"format": "f32-to-bf16",
|
283 |
+
"nbytes": 2097152,
|
284 |
+
"byteOffset": 22417408
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"name": "model.layers.1.self_attn.o_proj.q_scale",
|
288 |
+
"shape": [
|
289 |
+
2048,
|
290 |
+
64
|
291 |
+
],
|
292 |
+
"dtype": "bfloat16",
|
293 |
+
"format": "raw",
|
294 |
+
"nbytes": 262144,
|
295 |
+
"byteOffset": 24514560
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"name": "model.layers.10.input_layernorm.weight",
|
299 |
+
"shape": [
|
300 |
+
2048
|
301 |
+
],
|
302 |
+
"dtype": "bfloat16",
|
303 |
+
"format": "raw",
|
304 |
+
"nbytes": 4096,
|
305 |
+
"byteOffset": 24776704
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"name": "model.layers.10.mlp.down_proj.q_weight",
|
309 |
+
"shape": [
|
310 |
+
2048,
|
311 |
+
704
|
312 |
+
],
|
313 |
+
"dtype": "uint32",
|
314 |
+
"format": "f32-to-bf16",
|
315 |
+
"nbytes": 5767168,
|
316 |
+
"byteOffset": 24780800
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"name": "model.layers.10.mlp.down_proj.q_scale",
|
320 |
+
"shape": [
|
321 |
+
2048,
|
322 |
+
176
|
323 |
+
],
|
324 |
+
"dtype": "bfloat16",
|
325 |
+
"format": "raw",
|
326 |
+
"nbytes": 720896,
|
327 |
+
"byteOffset": 30547968
|
328 |
+
}
|
329 |
+
],
|
330 |
+
"md5sum": "236ea086fe698d15895a284f828cd334"
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"dataPath": "params_shard_4.bin",
|
334 |
+
"format": "raw-shard",
|
335 |
+
"nbytes": 24780800,
|
336 |
+
"records": [
|
337 |
+
{
|
338 |
+
"name": "model.layers.10.mlp.gate_up_proj.q_weight",
|
339 |
+
"shape": [
|
340 |
+
11264,
|
341 |
+
256
|
342 |
+
],
|
343 |
+
"dtype": "uint32",
|
344 |
+
"format": "f32-to-bf16",
|
345 |
+
"nbytes": 11534336,
|
346 |
+
"byteOffset": 0
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
|
350 |
+
"shape": [
|
351 |
+
11264,
|
352 |
+
64
|
353 |
+
],
|
354 |
+
"dtype": "bfloat16",
|
355 |
+
"format": "raw",
|
356 |
+
"nbytes": 1441792,
|
357 |
+
"byteOffset": 11534336
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"name": "model.layers.10.post_attention_layernorm.weight",
|
361 |
+
"shape": [
|
362 |
+
2048
|
363 |
+
],
|
364 |
+
"dtype": "bfloat16",
|
365 |
+
"format": "raw",
|
366 |
+
"nbytes": 4096,
|
367 |
+
"byteOffset": 12976128
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"name": "model.layers.10.self_attn.qkv_proj.q_weight",
|
371 |
+
"shape": [
|
372 |
+
2560,
|
373 |
+
256
|
374 |
+
],
|
375 |
+
"dtype": "uint32",
|
376 |
+
"format": "f32-to-bf16",
|
377 |
+
"nbytes": 2621440,
|
378 |
+
"byteOffset": 12980224
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"name": "model.layers.10.self_attn.qkv_proj.q_scale",
|
382 |
+
"shape": [
|
383 |
+
2560,
|
384 |
+
64
|
385 |
+
],
|
386 |
+
"dtype": "bfloat16",
|
387 |
+
"format": "raw",
|
388 |
+
"nbytes": 327680,
|
389 |
+
"byteOffset": 15601664
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"name": "model.layers.10.self_attn.o_proj.q_weight",
|
393 |
+
"shape": [
|
394 |
+
2048,
|
395 |
+
256
|
396 |
+
],
|
397 |
+
"dtype": "uint32",
|
398 |
+
"format": "f32-to-bf16",
|
399 |
+
"nbytes": 2097152,
|
400 |
+
"byteOffset": 15929344
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"name": "model.layers.10.self_attn.o_proj.q_scale",
|
404 |
+
"shape": [
|
405 |
+
2048,
|
406 |
+
64
|
407 |
+
],
|
408 |
+
"dtype": "bfloat16",
|
409 |
+
"format": "raw",
|
410 |
+
"nbytes": 262144,
|
411 |
+
"byteOffset": 18026496
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"name": "model.layers.11.input_layernorm.weight",
|
415 |
+
"shape": [
|
416 |
+
2048
|
417 |
+
],
|
418 |
+
"dtype": "bfloat16",
|
419 |
+
"format": "raw",
|
420 |
+
"nbytes": 4096,
|
421 |
+
"byteOffset": 18288640
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"name": "model.layers.11.mlp.down_proj.q_weight",
|
425 |
+
"shape": [
|
426 |
+
2048,
|
427 |
+
704
|
428 |
+
],
|
429 |
+
"dtype": "uint32",
|
430 |
+
"format": "f32-to-bf16",
|
431 |
+
"nbytes": 5767168,
|
432 |
+
"byteOffset": 18292736
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"name": "model.layers.11.mlp.down_proj.q_scale",
|
436 |
+
"shape": [
|
437 |
+
2048,
|
438 |
+
176
|
439 |
+
],
|
440 |
+
"dtype": "bfloat16",
|
441 |
+
"format": "raw",
|
442 |
+
"nbytes": 720896,
|
443 |
+
"byteOffset": 24059904
|
444 |
+
}
|
445 |
+
],
|
446 |
+
"md5sum": "9f801a8ec12c49b630b273561a4d9554"
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"dataPath": "params_shard_5.bin",
|
450 |
+
"format": "raw-shard",
|
451 |
+
"nbytes": 24780800,
|
452 |
+
"records": [
|
453 |
+
{
|
454 |
+
"name": "model.layers.11.mlp.gate_up_proj.q_weight",
|
455 |
+
"shape": [
|
456 |
+
11264,
|
457 |
+
256
|
458 |
+
],
|
459 |
+
"dtype": "uint32",
|
460 |
+
"format": "f32-to-bf16",
|
461 |
+
"nbytes": 11534336,
|
462 |
+
"byteOffset": 0
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
|
466 |
+
"shape": [
|
467 |
+
11264,
|
468 |
+
64
|
469 |
+
],
|
470 |
+
"dtype": "bfloat16",
|
471 |
+
"format": "raw",
|
472 |
+
"nbytes": 1441792,
|
473 |
+
"byteOffset": 11534336
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"name": "model.layers.11.post_attention_layernorm.weight",
|
477 |
+
"shape": [
|
478 |
+
2048
|
479 |
+
],
|
480 |
+
"dtype": "bfloat16",
|
481 |
+
"format": "raw",
|
482 |
+
"nbytes": 4096,
|
483 |
+
"byteOffset": 12976128
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"name": "model.layers.11.self_attn.qkv_proj.q_weight",
|
487 |
+
"shape": [
|
488 |
+
2560,
|
489 |
+
256
|
490 |
+
],
|
491 |
+
"dtype": "uint32",
|
492 |
+
"format": "f32-to-bf16",
|
493 |
+
"nbytes": 2621440,
|
494 |
+
"byteOffset": 12980224
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"name": "model.layers.11.self_attn.qkv_proj.q_scale",
|
498 |
+
"shape": [
|
499 |
+
2560,
|
500 |
+
64
|
501 |
+
],
|
502 |
+
"dtype": "bfloat16",
|
503 |
+
"format": "raw",
|
504 |
+
"nbytes": 327680,
|
505 |
+
"byteOffset": 15601664
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"name": "model.layers.11.self_attn.o_proj.q_weight",
|
509 |
+
"shape": [
|
510 |
+
2048,
|
511 |
+
256
|
512 |
+
],
|
513 |
+
"dtype": "uint32",
|
514 |
+
"format": "f32-to-bf16",
|
515 |
+
"nbytes": 2097152,
|
516 |
+
"byteOffset": 15929344
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"name": "model.layers.11.self_attn.o_proj.q_scale",
|
520 |
+
"shape": [
|
521 |
+
2048,
|
522 |
+
64
|
523 |
+
],
|
524 |
+
"dtype": "bfloat16",
|
525 |
+
"format": "raw",
|
526 |
+
"nbytes": 262144,
|
527 |
+
"byteOffset": 18026496
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"name": "model.layers.12.input_layernorm.weight",
|
531 |
+
"shape": [
|
532 |
+
2048
|
533 |
+
],
|
534 |
+
"dtype": "bfloat16",
|
535 |
+
"format": "raw",
|
536 |
+
"nbytes": 4096,
|
537 |
+
"byteOffset": 18288640
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"name": "model.layers.12.mlp.down_proj.q_weight",
|
541 |
+
"shape": [
|
542 |
+
2048,
|
543 |
+
704
|
544 |
+
],
|
545 |
+
"dtype": "uint32",
|
546 |
+
"format": "f32-to-bf16",
|
547 |
+
"nbytes": 5767168,
|
548 |
+
"byteOffset": 18292736
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"name": "model.layers.12.mlp.down_proj.q_scale",
|
552 |
+
"shape": [
|
553 |
+
2048,
|
554 |
+
176
|
555 |
+
],
|
556 |
+
"dtype": "bfloat16",
|
557 |
+
"format": "raw",
|
558 |
+
"nbytes": 720896,
|
559 |
+
"byteOffset": 24059904
|
560 |
+
}
|
561 |
+
],
|
562 |
+
"md5sum": "4a90502242460bc5d815ab87dcc2c3fc"
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"dataPath": "params_shard_6.bin",
|
566 |
+
"format": "raw-shard",
|
567 |
+
"nbytes": 24780800,
|
568 |
+
"records": [
|
569 |
+
{
|
570 |
+
"name": "model.layers.12.mlp.gate_up_proj.q_weight",
|
571 |
+
"shape": [
|
572 |
+
11264,
|
573 |
+
256
|
574 |
+
],
|
575 |
+
"dtype": "uint32",
|
576 |
+
"format": "f32-to-bf16",
|
577 |
+
"nbytes": 11534336,
|
578 |
+
"byteOffset": 0
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
|
582 |
+
"shape": [
|
583 |
+
11264,
|
584 |
+
64
|
585 |
+
],
|
586 |
+
"dtype": "bfloat16",
|
587 |
+
"format": "raw",
|
588 |
+
"nbytes": 1441792,
|
589 |
+
"byteOffset": 11534336
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"name": "model.layers.12.post_attention_layernorm.weight",
|
593 |
+
"shape": [
|
594 |
+
2048
|
595 |
+
],
|
596 |
+
"dtype": "bfloat16",
|
597 |
+
"format": "raw",
|
598 |
+
"nbytes": 4096,
|
599 |
+
"byteOffset": 12976128
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"name": "model.layers.12.self_attn.qkv_proj.q_weight",
|
603 |
+
"shape": [
|
604 |
+
2560,
|
605 |
+
256
|
606 |
+
],
|
607 |
+
"dtype": "uint32",
|
608 |
+
"format": "f32-to-bf16",
|
609 |
+
"nbytes": 2621440,
|
610 |
+
"byteOffset": 12980224
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"name": "model.layers.12.self_attn.qkv_proj.q_scale",
|
614 |
+
"shape": [
|
615 |
+
2560,
|
616 |
+
64
|
617 |
+
],
|
618 |
+
"dtype": "bfloat16",
|
619 |
+
"format": "raw",
|
620 |
+
"nbytes": 327680,
|
621 |
+
"byteOffset": 15601664
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"name": "model.layers.12.self_attn.o_proj.q_weight",
|
625 |
+
"shape": [
|
626 |
+
2048,
|
627 |
+
256
|
628 |
+
],
|
629 |
+
"dtype": "uint32",
|
630 |
+
"format": "f32-to-bf16",
|
631 |
+
"nbytes": 2097152,
|
632 |
+
"byteOffset": 15929344
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"name": "model.layers.12.self_attn.o_proj.q_scale",
|
636 |
+
"shape": [
|
637 |
+
2048,
|
638 |
+
64
|
639 |
+
],
|
640 |
+
"dtype": "bfloat16",
|
641 |
+
"format": "raw",
|
642 |
+
"nbytes": 262144,
|
643 |
+
"byteOffset": 18026496
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"name": "model.layers.13.input_layernorm.weight",
|
647 |
+
"shape": [
|
648 |
+
2048
|
649 |
+
],
|
650 |
+
"dtype": "bfloat16",
|
651 |
+
"format": "raw",
|
652 |
+
"nbytes": 4096,
|
653 |
+
"byteOffset": 18288640
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"name": "model.layers.13.mlp.down_proj.q_weight",
|
657 |
+
"shape": [
|
658 |
+
2048,
|
659 |
+
704
|
660 |
+
],
|
661 |
+
"dtype": "uint32",
|
662 |
+
"format": "f32-to-bf16",
|
663 |
+
"nbytes": 5767168,
|
664 |
+
"byteOffset": 18292736
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"name": "model.layers.13.mlp.down_proj.q_scale",
|
668 |
+
"shape": [
|
669 |
+
2048,
|
670 |
+
176
|
671 |
+
],
|
672 |
+
"dtype": "bfloat16",
|
673 |
+
"format": "raw",
|
674 |
+
"nbytes": 720896,
|
675 |
+
"byteOffset": 24059904
|
676 |
+
}
|
677 |
+
],
|
678 |
+
"md5sum": "4bc1e064d362ffbf9bae57c15e735e8d"
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"dataPath": "params_shard_7.bin",
|
682 |
+
"format": "raw-shard",
|
683 |
+
"nbytes": 24780800,
|
684 |
+
"records": [
|
685 |
+
{
|
686 |
+
"name": "model.layers.13.mlp.gate_up_proj.q_weight",
|
687 |
+
"shape": [
|
688 |
+
11264,
|
689 |
+
256
|
690 |
+
],
|
691 |
+
"dtype": "uint32",
|
692 |
+
"format": "f32-to-bf16",
|
693 |
+
"nbytes": 11534336,
|
694 |
+
"byteOffset": 0
|
695 |
+
},
|
696 |
+
{
|
697 |
+
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
|
698 |
+
"shape": [
|
699 |
+
11264,
|
700 |
+
64
|
701 |
+
],
|
702 |
+
"dtype": "bfloat16",
|
703 |
+
"format": "raw",
|
704 |
+
"nbytes": 1441792,
|
705 |
+
"byteOffset": 11534336
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"name": "model.layers.13.post_attention_layernorm.weight",
|
709 |
+
"shape": [
|
710 |
+
2048
|
711 |
+
],
|
712 |
+
"dtype": "bfloat16",
|
713 |
+
"format": "raw",
|
714 |
+
"nbytes": 4096,
|
715 |
+
"byteOffset": 12976128
|
716 |
+
},
|
717 |
+
{
|
718 |
+
"name": "model.layers.13.self_attn.qkv_proj.q_weight",
|
719 |
+
"shape": [
|
720 |
+
2560,
|
721 |
+
256
|
722 |
+
],
|
723 |
+
"dtype": "uint32",
|
724 |
+
"format": "f32-to-bf16",
|
725 |
+
"nbytes": 2621440,
|
726 |
+
"byteOffset": 12980224
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"name": "model.layers.13.self_attn.qkv_proj.q_scale",
|
730 |
+
"shape": [
|
731 |
+
2560,
|
732 |
+
64
|
733 |
+
],
|
734 |
+
"dtype": "bfloat16",
|
735 |
+
"format": "raw",
|
736 |
+
"nbytes": 327680,
|
737 |
+
"byteOffset": 15601664
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"name": "model.layers.13.self_attn.o_proj.q_weight",
|
741 |
+
"shape": [
|
742 |
+
2048,
|
743 |
+
256
|
744 |
+
],
|
745 |
+
"dtype": "uint32",
|
746 |
+
"format": "f32-to-bf16",
|
747 |
+
"nbytes": 2097152,
|
748 |
+
"byteOffset": 15929344
|
749 |
+
},
|
750 |
+
{
|
751 |
+
"name": "model.layers.13.self_attn.o_proj.q_scale",
|
752 |
+
"shape": [
|
753 |
+
2048,
|
754 |
+
64
|
755 |
+
],
|
756 |
+
"dtype": "bfloat16",
|
757 |
+
"format": "raw",
|
758 |
+
"nbytes": 262144,
|
759 |
+
"byteOffset": 18026496
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"name": "model.layers.14.input_layernorm.weight",
|
763 |
+
"shape": [
|
764 |
+
2048
|
765 |
+
],
|
766 |
+
"dtype": "bfloat16",
|
767 |
+
"format": "raw",
|
768 |
+
"nbytes": 4096,
|
769 |
+
"byteOffset": 18288640
|
770 |
+
},
|
771 |
+
{
|
772 |
+
"name": "model.layers.14.mlp.down_proj.q_weight",
|
773 |
+
"shape": [
|
774 |
+
2048,
|
775 |
+
704
|
776 |
+
],
|
777 |
+
"dtype": "uint32",
|
778 |
+
"format": "f32-to-bf16",
|
779 |
+
"nbytes": 5767168,
|
780 |
+
"byteOffset": 18292736
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"name": "model.layers.14.mlp.down_proj.q_scale",
|
784 |
+
"shape": [
|
785 |
+
2048,
|
786 |
+
176
|
787 |
+
],
|
788 |
+
"dtype": "bfloat16",
|
789 |
+
"format": "raw",
|
790 |
+
"nbytes": 720896,
|
791 |
+
"byteOffset": 24059904
|
792 |
+
}
|
793 |
+
],
|
794 |
+
"md5sum": "85a8f0c3b9857df7a6fa1b9cbbb5d927"
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"dataPath": "params_shard_8.bin",
|
798 |
+
"format": "raw-shard",
|
799 |
+
"nbytes": 24780800,
|
800 |
+
"records": [
|
801 |
+
{
|
802 |
+
"name": "model.layers.14.mlp.gate_up_proj.q_weight",
|
803 |
+
"shape": [
|
804 |
+
11264,
|
805 |
+
256
|
806 |
+
],
|
807 |
+
"dtype": "uint32",
|
808 |
+
"format": "f32-to-bf16",
|
809 |
+
"nbytes": 11534336,
|
810 |
+
"byteOffset": 0
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
|
814 |
+
"shape": [
|
815 |
+
11264,
|
816 |
+
64
|
817 |
+
],
|
818 |
+
"dtype": "bfloat16",
|
819 |
+
"format": "raw",
|
820 |
+
"nbytes": 1441792,
|
821 |
+
"byteOffset": 11534336
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"name": "model.layers.14.post_attention_layernorm.weight",
|
825 |
+
"shape": [
|
826 |
+
2048
|
827 |
+
],
|
828 |
+
"dtype": "bfloat16",
|
829 |
+
"format": "raw",
|
830 |
+
"nbytes": 4096,
|
831 |
+
"byteOffset": 12976128
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"name": "model.layers.14.self_attn.qkv_proj.q_weight",
|
835 |
+
"shape": [
|
836 |
+
2560,
|
837 |
+
256
|
838 |
+
],
|
839 |
+
"dtype": "uint32",
|
840 |
+
"format": "f32-to-bf16",
|
841 |
+
"nbytes": 2621440,
|
842 |
+
"byteOffset": 12980224
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"name": "model.layers.14.self_attn.qkv_proj.q_scale",
|
846 |
+
"shape": [
|
847 |
+
2560,
|
848 |
+
64
|
849 |
+
],
|
850 |
+
"dtype": "bfloat16",
|
851 |
+
"format": "raw",
|
852 |
+
"nbytes": 327680,
|
853 |
+
"byteOffset": 15601664
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"name": "model.layers.14.self_attn.o_proj.q_weight",
|
857 |
+
"shape": [
|
858 |
+
2048,
|
859 |
+
256
|
860 |
+
],
|
861 |
+
"dtype": "uint32",
|
862 |
+
"format": "f32-to-bf16",
|
863 |
+
"nbytes": 2097152,
|
864 |
+
"byteOffset": 15929344
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"name": "model.layers.14.self_attn.o_proj.q_scale",
|
868 |
+
"shape": [
|
869 |
+
2048,
|
870 |
+
64
|
871 |
+
],
|
872 |
+
"dtype": "bfloat16",
|
873 |
+
"format": "raw",
|
874 |
+
"nbytes": 262144,
|
875 |
+
"byteOffset": 18026496
|
876 |
+
},
|
877 |
+
{
|
878 |
+
"name": "model.layers.15.input_layernorm.weight",
|
879 |
+
"shape": [
|
880 |
+
2048
|
881 |
+
],
|
882 |
+
"dtype": "bfloat16",
|
883 |
+
"format": "raw",
|
884 |
+
"nbytes": 4096,
|
885 |
+
"byteOffset": 18288640
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"name": "model.layers.15.mlp.down_proj.q_weight",
|
889 |
+
"shape": [
|
890 |
+
2048,
|
891 |
+
704
|
892 |
+
],
|
893 |
+
"dtype": "uint32",
|
894 |
+
"format": "f32-to-bf16",
|
895 |
+
"nbytes": 5767168,
|
896 |
+
"byteOffset": 18292736
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"name": "model.layers.15.mlp.down_proj.q_scale",
|
900 |
+
"shape": [
|
901 |
+
2048,
|
902 |
+
176
|
903 |
+
],
|
904 |
+
"dtype": "bfloat16",
|
905 |
+
"format": "raw",
|
906 |
+
"nbytes": 720896,
|
907 |
+
"byteOffset": 24059904
|
908 |
+
}
|
909 |
+
],
|
910 |
+
"md5sum": "18e9c491a88f7adc43ed17d6f940f080"
|
911 |
+
},
|
912 |
+
{
|
913 |
+
"dataPath": "params_shard_9.bin",
|
914 |
+
"format": "raw-shard",
|
915 |
+
"nbytes": 24780800,
|
916 |
+
"records": [
|
917 |
+
{
|
918 |
+
"name": "model.layers.15.mlp.gate_up_proj.q_weight",
|
919 |
+
"shape": [
|
920 |
+
11264,
|
921 |
+
256
|
922 |
+
],
|
923 |
+
"dtype": "uint32",
|
924 |
+
"format": "f32-to-bf16",
|
925 |
+
"nbytes": 11534336,
|
926 |
+
"byteOffset": 0
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
|
930 |
+
"shape": [
|
931 |
+
11264,
|
932 |
+
64
|
933 |
+
],
|
934 |
+
"dtype": "bfloat16",
|
935 |
+
"format": "raw",
|
936 |
+
"nbytes": 1441792,
|
937 |
+
"byteOffset": 11534336
|
938 |
+
},
|
939 |
+
{
|
940 |
+
"name": "model.layers.15.post_attention_layernorm.weight",
|
941 |
+
"shape": [
|
942 |
+
2048
|
943 |
+
],
|
944 |
+
"dtype": "bfloat16",
|
945 |
+
"format": "raw",
|
946 |
+
"nbytes": 4096,
|
947 |
+
"byteOffset": 12976128
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"name": "model.layers.15.self_attn.qkv_proj.q_weight",
|
951 |
+
"shape": [
|
952 |
+
2560,
|
953 |
+
256
|
954 |
+
],
|
955 |
+
"dtype": "uint32",
|
956 |
+
"format": "f32-to-bf16",
|
957 |
+
"nbytes": 2621440,
|
958 |
+
"byteOffset": 12980224
|
959 |
+
},
|
960 |
+
{
|
961 |
+
"name": "model.layers.15.self_attn.qkv_proj.q_scale",
|
962 |
+
"shape": [
|
963 |
+
2560,
|
964 |
+
64
|
965 |
+
],
|
966 |
+
"dtype": "bfloat16",
|
967 |
+
"format": "raw",
|
968 |
+
"nbytes": 327680,
|
969 |
+
"byteOffset": 15601664
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"name": "model.layers.15.self_attn.o_proj.q_weight",
|
973 |
+
"shape": [
|
974 |
+
2048,
|
975 |
+
256
|
976 |
+
],
|
977 |
+
"dtype": "uint32",
|
978 |
+
"format": "f32-to-bf16",
|
979 |
+
"nbytes": 2097152,
|
980 |
+
"byteOffset": 15929344
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"name": "model.layers.15.self_attn.o_proj.q_scale",
|
984 |
+
"shape": [
|
985 |
+
2048,
|
986 |
+
64
|
987 |
+
],
|
988 |
+
"dtype": "bfloat16",
|
989 |
+
"format": "raw",
|
990 |
+
"nbytes": 262144,
|
991 |
+
"byteOffset": 18026496
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"name": "model.layers.16.input_layernorm.weight",
|
995 |
+
"shape": [
|
996 |
+
2048
|
997 |
+
],
|
998 |
+
"dtype": "bfloat16",
|
999 |
+
"format": "raw",
|
1000 |
+
"nbytes": 4096,
|
1001 |
+
"byteOffset": 18288640
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"name": "model.layers.16.mlp.down_proj.q_weight",
|
1005 |
+
"shape": [
|
1006 |
+
2048,
|
1007 |
+
704
|
1008 |
+
],
|
1009 |
+
"dtype": "uint32",
|
1010 |
+
"format": "f32-to-bf16",
|
1011 |
+
"nbytes": 5767168,
|
1012 |
+
"byteOffset": 18292736
|
1013 |
+
},
|
1014 |
+
{
|
1015 |
+
"name": "model.layers.16.mlp.down_proj.q_scale",
|
1016 |
+
"shape": [
|
1017 |
+
2048,
|
1018 |
+
176
|
1019 |
+
],
|
1020 |
+
"dtype": "bfloat16",
|
1021 |
+
"format": "raw",
|
1022 |
+
"nbytes": 720896,
|
1023 |
+
"byteOffset": 24059904
|
1024 |
+
}
|
1025 |
+
],
|
1026 |
+
"md5sum": "ebe88a618b7cb4980864878efb2bdbb7"
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"dataPath": "params_shard_10.bin",
|
1030 |
+
"format": "raw-shard",
|
1031 |
+
"nbytes": 24780800,
|
1032 |
+
"records": [
|
1033 |
+
{
|
1034 |
+
"name": "model.layers.16.mlp.gate_up_proj.q_weight",
|
1035 |
+
"shape": [
|
1036 |
+
11264,
|
1037 |
+
256
|
1038 |
+
],
|
1039 |
+
"dtype": "uint32",
|
1040 |
+
"format": "f32-to-bf16",
|
1041 |
+
"nbytes": 11534336,
|
1042 |
+
"byteOffset": 0
|
1043 |
+
},
|
1044 |
+
{
|
1045 |
+
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
|
1046 |
+
"shape": [
|
1047 |
+
11264,
|
1048 |
+
64
|
1049 |
+
],
|
1050 |
+
"dtype": "bfloat16",
|
1051 |
+
"format": "raw",
|
1052 |
+
"nbytes": 1441792,
|
1053 |
+
"byteOffset": 11534336
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"name": "model.layers.16.post_attention_layernorm.weight",
|
1057 |
+
"shape": [
|
1058 |
+
2048
|
1059 |
+
],
|
1060 |
+
"dtype": "bfloat16",
|
1061 |
+
"format": "raw",
|
1062 |
+
"nbytes": 4096,
|
1063 |
+
"byteOffset": 12976128
|
1064 |
+
},
|
1065 |
+
{
|
1066 |
+
"name": "model.layers.16.self_attn.qkv_proj.q_weight",
|
1067 |
+
"shape": [
|
1068 |
+
2560,
|
1069 |
+
256
|
1070 |
+
],
|
1071 |
+
"dtype": "uint32",
|
1072 |
+
"format": "f32-to-bf16",
|
1073 |
+
"nbytes": 2621440,
|
1074 |
+
"byteOffset": 12980224
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"name": "model.layers.16.self_attn.qkv_proj.q_scale",
|
1078 |
+
"shape": [
|
1079 |
+
2560,
|
1080 |
+
64
|
1081 |
+
],
|
1082 |
+
"dtype": "bfloat16",
|
1083 |
+
"format": "raw",
|
1084 |
+
"nbytes": 327680,
|
1085 |
+
"byteOffset": 15601664
|
1086 |
+
},
|
1087 |
+
{
|
1088 |
+
"name": "model.layers.16.self_attn.o_proj.q_weight",
|
1089 |
+
"shape": [
|
1090 |
+
2048,
|
1091 |
+
256
|
1092 |
+
],
|
1093 |
+
"dtype": "uint32",
|
1094 |
+
"format": "f32-to-bf16",
|
1095 |
+
"nbytes": 2097152,
|
1096 |
+
"byteOffset": 15929344
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"name": "model.layers.16.self_attn.o_proj.q_scale",
|
1100 |
+
"shape": [
|
1101 |
+
2048,
|
1102 |
+
64
|
1103 |
+
],
|
1104 |
+
"dtype": "bfloat16",
|
1105 |
+
"format": "raw",
|
1106 |
+
"nbytes": 262144,
|
1107 |
+
"byteOffset": 18026496
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"name": "model.layers.17.input_layernorm.weight",
|
1111 |
+
"shape": [
|
1112 |
+
2048
|
1113 |
+
],
|
1114 |
+
"dtype": "bfloat16",
|
1115 |
+
"format": "raw",
|
1116 |
+
"nbytes": 4096,
|
1117 |
+
"byteOffset": 18288640
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"name": "model.layers.17.mlp.down_proj.q_weight",
|
1121 |
+
"shape": [
|
1122 |
+
2048,
|
1123 |
+
704
|
1124 |
+
],
|
1125 |
+
"dtype": "uint32",
|
1126 |
+
"format": "f32-to-bf16",
|
1127 |
+
"nbytes": 5767168,
|
1128 |
+
"byteOffset": 18292736
|
1129 |
+
},
|
1130 |
+
{
|
1131 |
+
"name": "model.layers.17.mlp.down_proj.q_scale",
|
1132 |
+
"shape": [
|
1133 |
+
2048,
|
1134 |
+
176
|
1135 |
+
],
|
1136 |
+
"dtype": "bfloat16",
|
1137 |
+
"format": "raw",
|
1138 |
+
"nbytes": 720896,
|
1139 |
+
"byteOffset": 24059904
|
1140 |
+
}
|
1141 |
+
],
|
1142 |
+
"md5sum": "2a298c0af58f1e1a208b199e40b49972"
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"dataPath": "params_shard_11.bin",
|
1146 |
+
"format": "raw-shard",
|
1147 |
+
"nbytes": 24780800,
|
1148 |
+
"records": [
|
1149 |
+
{
|
1150 |
+
"name": "model.layers.17.mlp.gate_up_proj.q_weight",
|
1151 |
+
"shape": [
|
1152 |
+
11264,
|
1153 |
+
256
|
1154 |
+
],
|
1155 |
+
"dtype": "uint32",
|
1156 |
+
"format": "f32-to-bf16",
|
1157 |
+
"nbytes": 11534336,
|
1158 |
+
"byteOffset": 0
|
1159 |
+
},
|
1160 |
+
{
|
1161 |
+
"name": "model.layers.17.mlp.gate_up_proj.q_scale",
|
1162 |
+
"shape": [
|
1163 |
+
11264,
|
1164 |
+
64
|
1165 |
+
],
|
1166 |
+
"dtype": "bfloat16",
|
1167 |
+
"format": "raw",
|
1168 |
+
"nbytes": 1441792,
|
1169 |
+
"byteOffset": 11534336
|
1170 |
+
},
|
1171 |
+
{
|
1172 |
+
"name": "model.layers.17.post_attention_layernorm.weight",
|
1173 |
+
"shape": [
|
1174 |
+
2048
|
1175 |
+
],
|
1176 |
+
"dtype": "bfloat16",
|
1177 |
+
"format": "raw",
|
1178 |
+
"nbytes": 4096,
|
1179 |
+
"byteOffset": 12976128
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"name": "model.layers.17.self_attn.qkv_proj.q_weight",
|
1183 |
+
"shape": [
|
1184 |
+
2560,
|
1185 |
+
256
|
1186 |
+
],
|
1187 |
+
"dtype": "uint32",
|
1188 |
+
"format": "f32-to-bf16",
|
1189 |
+
"nbytes": 2621440,
|
1190 |
+
"byteOffset": 12980224
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"name": "model.layers.17.self_attn.qkv_proj.q_scale",
|
1194 |
+
"shape": [
|
1195 |
+
2560,
|
1196 |
+
64
|
1197 |
+
],
|
1198 |
+
"dtype": "bfloat16",
|
1199 |
+
"format": "raw",
|
1200 |
+
"nbytes": 327680,
|
1201 |
+
"byteOffset": 15601664
|
1202 |
+
},
|
1203 |
+
{
|
1204 |
+
"name": "model.layers.17.self_attn.o_proj.q_weight",
|
1205 |
+
"shape": [
|
1206 |
+
2048,
|
1207 |
+
256
|
1208 |
+
],
|
1209 |
+
"dtype": "uint32",
|
1210 |
+
"format": "f32-to-bf16",
|
1211 |
+
"nbytes": 2097152,
|
1212 |
+
"byteOffset": 15929344
|
1213 |
+
},
|
1214 |
+
{
|
1215 |
+
"name": "model.layers.17.self_attn.o_proj.q_scale",
|
1216 |
+
"shape": [
|
1217 |
+
2048,
|
1218 |
+
64
|
1219 |
+
],
|
1220 |
+
"dtype": "bfloat16",
|
1221 |
+
"format": "raw",
|
1222 |
+
"nbytes": 262144,
|
1223 |
+
"byteOffset": 18026496
|
1224 |
+
},
|
1225 |
+
{
|
1226 |
+
"name": "model.layers.18.input_layernorm.weight",
|
1227 |
+
"shape": [
|
1228 |
+
2048
|
1229 |
+
],
|
1230 |
+
"dtype": "bfloat16",
|
1231 |
+
"format": "raw",
|
1232 |
+
"nbytes": 4096,
|
1233 |
+
"byteOffset": 18288640
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"name": "model.layers.18.mlp.down_proj.q_weight",
|
1237 |
+
"shape": [
|
1238 |
+
2048,
|
1239 |
+
704
|
1240 |
+
],
|
1241 |
+
"dtype": "uint32",
|
1242 |
+
"format": "f32-to-bf16",
|
1243 |
+
"nbytes": 5767168,
|
1244 |
+
"byteOffset": 18292736
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"name": "model.layers.18.mlp.down_proj.q_scale",
|
1248 |
+
"shape": [
|
1249 |
+
2048,
|
1250 |
+
176
|
1251 |
+
],
|
1252 |
+
"dtype": "bfloat16",
|
1253 |
+
"format": "raw",
|
1254 |
+
"nbytes": 720896,
|
1255 |
+
"byteOffset": 24059904
|
1256 |
+
}
|
1257 |
+
],
|
1258 |
+
"md5sum": "8a6ef364911a1049b2c0531be0fc15b6"
|
1259 |
+
},
|
1260 |
+
{
|
1261 |
+
"dataPath": "params_shard_12.bin",
|
1262 |
+
"format": "raw-shard",
|
1263 |
+
"nbytes": 24780800,
|
1264 |
+
"records": [
|
1265 |
+
{
|
1266 |
+
"name": "model.layers.18.mlp.gate_up_proj.q_weight",
|
1267 |
+
"shape": [
|
1268 |
+
11264,
|
1269 |
+
256
|
1270 |
+
],
|
1271 |
+
"dtype": "uint32",
|
1272 |
+
"format": "f32-to-bf16",
|
1273 |
+
"nbytes": 11534336,
|
1274 |
+
"byteOffset": 0
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"name": "model.layers.18.mlp.gate_up_proj.q_scale",
|
1278 |
+
"shape": [
|
1279 |
+
11264,
|
1280 |
+
64
|
1281 |
+
],
|
1282 |
+
"dtype": "bfloat16",
|
1283 |
+
"format": "raw",
|
1284 |
+
"nbytes": 1441792,
|
1285 |
+
"byteOffset": 11534336
|
1286 |
+
},
|
1287 |
+
{
|
1288 |
+
"name": "model.layers.18.post_attention_layernorm.weight",
|
1289 |
+
"shape": [
|
1290 |
+
2048
|
1291 |
+
],
|
1292 |
+
"dtype": "bfloat16",
|
1293 |
+
"format": "raw",
|
1294 |
+
"nbytes": 4096,
|
1295 |
+
"byteOffset": 12976128
|
1296 |
+
},
|
1297 |
+
{
|
1298 |
+
"name": "model.layers.18.self_attn.qkv_proj.q_weight",
|
1299 |
+
"shape": [
|
1300 |
+
2560,
|
1301 |
+
256
|
1302 |
+
],
|
1303 |
+
"dtype": "uint32",
|
1304 |
+
"format": "f32-to-bf16",
|
1305 |
+
"nbytes": 2621440,
|
1306 |
+
"byteOffset": 12980224
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"name": "model.layers.18.self_attn.qkv_proj.q_scale",
|
1310 |
+
"shape": [
|
1311 |
+
2560,
|
1312 |
+
64
|
1313 |
+
],
|
1314 |
+
"dtype": "bfloat16",
|
1315 |
+
"format": "raw",
|
1316 |
+
"nbytes": 327680,
|
1317 |
+
"byteOffset": 15601664
|
1318 |
+
},
|
1319 |
+
{
|
1320 |
+
"name": "model.layers.18.self_attn.o_proj.q_weight",
|
1321 |
+
"shape": [
|
1322 |
+
2048,
|
1323 |
+
256
|
1324 |
+
],
|
1325 |
+
"dtype": "uint32",
|
1326 |
+
"format": "f32-to-bf16",
|
1327 |
+
"nbytes": 2097152,
|
1328 |
+
"byteOffset": 15929344
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"name": "model.layers.18.self_attn.o_proj.q_scale",
|
1332 |
+
"shape": [
|
1333 |
+
2048,
|
1334 |
+
64
|
1335 |
+
],
|
1336 |
+
"dtype": "bfloat16",
|
1337 |
+
"format": "raw",
|
1338 |
+
"nbytes": 262144,
|
1339 |
+
"byteOffset": 18026496
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"name": "model.layers.19.input_layernorm.weight",
|
1343 |
+
"shape": [
|
1344 |
+
2048
|
1345 |
+
],
|
1346 |
+
"dtype": "bfloat16",
|
1347 |
+
"format": "raw",
|
1348 |
+
"nbytes": 4096,
|
1349 |
+
"byteOffset": 18288640
|
1350 |
+
},
|
1351 |
+
{
|
1352 |
+
"name": "model.layers.19.mlp.down_proj.q_weight",
|
1353 |
+
"shape": [
|
1354 |
+
2048,
|
1355 |
+
704
|
1356 |
+
],
|
1357 |
+
"dtype": "uint32",
|
1358 |
+
"format": "f32-to-bf16",
|
1359 |
+
"nbytes": 5767168,
|
1360 |
+
"byteOffset": 18292736
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"name": "model.layers.19.mlp.down_proj.q_scale",
|
1364 |
+
"shape": [
|
1365 |
+
2048,
|
1366 |
+
176
|
1367 |
+
],
|
1368 |
+
"dtype": "bfloat16",
|
1369 |
+
"format": "raw",
|
1370 |
+
"nbytes": 720896,
|
1371 |
+
"byteOffset": 24059904
|
1372 |
+
}
|
1373 |
+
],
|
1374 |
+
"md5sum": "13ffdc8591e96c1c5f27090d70144bd0"
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"dataPath": "params_shard_13.bin",
|
1378 |
+
"format": "raw-shard",
|
1379 |
+
"nbytes": 24780800,
|
1380 |
+
"records": [
|
1381 |
+
{
|
1382 |
+
"name": "model.layers.19.mlp.gate_up_proj.q_weight",
|
1383 |
+
"shape": [
|
1384 |
+
11264,
|
1385 |
+
256
|
1386 |
+
],
|
1387 |
+
"dtype": "uint32",
|
1388 |
+
"format": "f32-to-bf16",
|
1389 |
+
"nbytes": 11534336,
|
1390 |
+
"byteOffset": 0
|
1391 |
+
},
|
1392 |
+
{
|
1393 |
+
"name": "model.layers.19.mlp.gate_up_proj.q_scale",
|
1394 |
+
"shape": [
|
1395 |
+
11264,
|
1396 |
+
64
|
1397 |
+
],
|
1398 |
+
"dtype": "bfloat16",
|
1399 |
+
"format": "raw",
|
1400 |
+
"nbytes": 1441792,
|
1401 |
+
"byteOffset": 11534336
|
1402 |
+
},
|
1403 |
+
{
|
1404 |
+
"name": "model.layers.19.post_attention_layernorm.weight",
|
1405 |
+
"shape": [
|
1406 |
+
2048
|
1407 |
+
],
|
1408 |
+
"dtype": "bfloat16",
|
1409 |
+
"format": "raw",
|
1410 |
+
"nbytes": 4096,
|
1411 |
+
"byteOffset": 12976128
|
1412 |
+
},
|
1413 |
+
{
|
1414 |
+
"name": "model.layers.19.self_attn.qkv_proj.q_weight",
|
1415 |
+
"shape": [
|
1416 |
+
2560,
|
1417 |
+
256
|
1418 |
+
],
|
1419 |
+
"dtype": "uint32",
|
1420 |
+
"format": "f32-to-bf16",
|
1421 |
+
"nbytes": 2621440,
|
1422 |
+
"byteOffset": 12980224
|
1423 |
+
},
|
1424 |
+
{
|
1425 |
+
"name": "model.layers.19.self_attn.qkv_proj.q_scale",
|
1426 |
+
"shape": [
|
1427 |
+
2560,
|
1428 |
+
64
|
1429 |
+
],
|
1430 |
+
"dtype": "bfloat16",
|
1431 |
+
"format": "raw",
|
1432 |
+
"nbytes": 327680,
|
1433 |
+
"byteOffset": 15601664
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"name": "model.layers.19.self_attn.o_proj.q_weight",
|
1437 |
+
"shape": [
|
1438 |
+
2048,
|
1439 |
+
256
|
1440 |
+
],
|
1441 |
+
"dtype": "uint32",
|
1442 |
+
"format": "f32-to-bf16",
|
1443 |
+
"nbytes": 2097152,
|
1444 |
+
"byteOffset": 15929344
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"name": "model.layers.19.self_attn.o_proj.q_scale",
|
1448 |
+
"shape": [
|
1449 |
+
2048,
|
1450 |
+
64
|
1451 |
+
],
|
1452 |
+
"dtype": "bfloat16",
|
1453 |
+
"format": "raw",
|
1454 |
+
"nbytes": 262144,
|
1455 |
+
"byteOffset": 18026496
|
1456 |
+
},
|
1457 |
+
{
|
1458 |
+
"name": "model.layers.2.input_layernorm.weight",
|
1459 |
+
"shape": [
|
1460 |
+
2048
|
1461 |
+
],
|
1462 |
+
"dtype": "bfloat16",
|
1463 |
+
"format": "raw",
|
1464 |
+
"nbytes": 4096,
|
1465 |
+
"byteOffset": 18288640
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"name": "model.layers.2.mlp.down_proj.q_weight",
|
1469 |
+
"shape": [
|
1470 |
+
2048,
|
1471 |
+
704
|
1472 |
+
],
|
1473 |
+
"dtype": "uint32",
|
1474 |
+
"format": "f32-to-bf16",
|
1475 |
+
"nbytes": 5767168,
|
1476 |
+
"byteOffset": 18292736
|
1477 |
+
},
|
1478 |
+
{
|
1479 |
+
"name": "model.layers.2.mlp.down_proj.q_scale",
|
1480 |
+
"shape": [
|
1481 |
+
2048,
|
1482 |
+
176
|
1483 |
+
],
|
1484 |
+
"dtype": "bfloat16",
|
1485 |
+
"format": "raw",
|
1486 |
+
"nbytes": 720896,
|
1487 |
+
"byteOffset": 24059904
|
1488 |
+
}
|
1489 |
+
],
|
1490 |
+
"md5sum": "35244475eb557462112a7fa2d3db4dc9"
|
1491 |
+
},
|
1492 |
+
{
|
1493 |
+
"dataPath": "params_shard_14.bin",
|
1494 |
+
"format": "raw-shard",
|
1495 |
+
"nbytes": 24780800,
|
1496 |
+
"records": [
|
1497 |
+
{
|
1498 |
+
"name": "model.layers.2.mlp.gate_up_proj.q_weight",
|
1499 |
+
"shape": [
|
1500 |
+
11264,
|
1501 |
+
256
|
1502 |
+
],
|
1503 |
+
"dtype": "uint32",
|
1504 |
+
"format": "f32-to-bf16",
|
1505 |
+
"nbytes": 11534336,
|
1506 |
+
"byteOffset": 0
|
1507 |
+
},
|
1508 |
+
{
|
1509 |
+
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
|
1510 |
+
"shape": [
|
1511 |
+
11264,
|
1512 |
+
64
|
1513 |
+
],
|
1514 |
+
"dtype": "bfloat16",
|
1515 |
+
"format": "raw",
|
1516 |
+
"nbytes": 1441792,
|
1517 |
+
"byteOffset": 11534336
|
1518 |
+
},
|
1519 |
+
{
|
1520 |
+
"name": "model.layers.2.post_attention_layernorm.weight",
|
1521 |
+
"shape": [
|
1522 |
+
2048
|
1523 |
+
],
|
1524 |
+
"dtype": "bfloat16",
|
1525 |
+
"format": "raw",
|
1526 |
+
"nbytes": 4096,
|
1527 |
+
"byteOffset": 12976128
|
1528 |
+
},
|
1529 |
+
{
|
1530 |
+
"name": "model.layers.2.self_attn.qkv_proj.q_weight",
|
1531 |
+
"shape": [
|
1532 |
+
2560,
|
1533 |
+
256
|
1534 |
+
],
|
1535 |
+
"dtype": "uint32",
|
1536 |
+
"format": "f32-to-bf16",
|
1537 |
+
"nbytes": 2621440,
|
1538 |
+
"byteOffset": 12980224
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
|
1542 |
+
"shape": [
|
1543 |
+
2560,
|
1544 |
+
64
|
1545 |
+
],
|
1546 |
+
"dtype": "bfloat16",
|
1547 |
+
"format": "raw",
|
1548 |
+
"nbytes": 327680,
|
1549 |
+
"byteOffset": 15601664
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"name": "model.layers.2.self_attn.o_proj.q_weight",
|
1553 |
+
"shape": [
|
1554 |
+
2048,
|
1555 |
+
256
|
1556 |
+
],
|
1557 |
+
"dtype": "uint32",
|
1558 |
+
"format": "f32-to-bf16",
|
1559 |
+
"nbytes": 2097152,
|
1560 |
+
"byteOffset": 15929344
|
1561 |
+
},
|
1562 |
+
{
|
1563 |
+
"name": "model.layers.2.self_attn.o_proj.q_scale",
|
1564 |
+
"shape": [
|
1565 |
+
2048,
|
1566 |
+
64
|
1567 |
+
],
|
1568 |
+
"dtype": "bfloat16",
|
1569 |
+
"format": "raw",
|
1570 |
+
"nbytes": 262144,
|
1571 |
+
"byteOffset": 18026496
|
1572 |
+
},
|
1573 |
+
{
|
1574 |
+
"name": "model.layers.20.input_layernorm.weight",
|
1575 |
+
"shape": [
|
1576 |
+
2048
|
1577 |
+
],
|
1578 |
+
"dtype": "bfloat16",
|
1579 |
+
"format": "raw",
|
1580 |
+
"nbytes": 4096,
|
1581 |
+
"byteOffset": 18288640
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"name": "model.layers.20.mlp.down_proj.q_weight",
|
1585 |
+
"shape": [
|
1586 |
+
2048,
|
1587 |
+
704
|
1588 |
+
],
|
1589 |
+
"dtype": "uint32",
|
1590 |
+
"format": "f32-to-bf16",
|
1591 |
+
"nbytes": 5767168,
|
1592 |
+
"byteOffset": 18292736
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"name": "model.layers.20.mlp.down_proj.q_scale",
|
1596 |
+
"shape": [
|
1597 |
+
2048,
|
1598 |
+
176
|
1599 |
+
],
|
1600 |
+
"dtype": "bfloat16",
|
1601 |
+
"format": "raw",
|
1602 |
+
"nbytes": 720896,
|
1603 |
+
"byteOffset": 24059904
|
1604 |
+
}
|
1605 |
+
],
|
1606 |
+
"md5sum": "f87ee6617b7866df37b8c66980d7144f"
|
1607 |
+
},
|
1608 |
+
{
|
1609 |
+
"dataPath": "params_shard_15.bin",
|
1610 |
+
"format": "raw-shard",
|
1611 |
+
"nbytes": 24780800,
|
1612 |
+
"records": [
|
1613 |
+
{
|
1614 |
+
"name": "model.layers.20.mlp.gate_up_proj.q_weight",
|
1615 |
+
"shape": [
|
1616 |
+
11264,
|
1617 |
+
256
|
1618 |
+
],
|
1619 |
+
"dtype": "uint32",
|
1620 |
+
"format": "f32-to-bf16",
|
1621 |
+
"nbytes": 11534336,
|
1622 |
+
"byteOffset": 0
|
1623 |
+
},
|
1624 |
+
{
|
1625 |
+
"name": "model.layers.20.mlp.gate_up_proj.q_scale",
|
1626 |
+
"shape": [
|
1627 |
+
11264,
|
1628 |
+
64
|
1629 |
+
],
|
1630 |
+
"dtype": "bfloat16",
|
1631 |
+
"format": "raw",
|
1632 |
+
"nbytes": 1441792,
|
1633 |
+
"byteOffset": 11534336
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"name": "model.layers.20.post_attention_layernorm.weight",
|
1637 |
+
"shape": [
|
1638 |
+
2048
|
1639 |
+
],
|
1640 |
+
"dtype": "bfloat16",
|
1641 |
+
"format": "raw",
|
1642 |
+
"nbytes": 4096,
|
1643 |
+
"byteOffset": 12976128
|
1644 |
+
},
|
1645 |
+
{
|
1646 |
+
"name": "model.layers.20.self_attn.qkv_proj.q_weight",
|
1647 |
+
"shape": [
|
1648 |
+
2560,
|
1649 |
+
256
|
1650 |
+
],
|
1651 |
+
"dtype": "uint32",
|
1652 |
+
"format": "f32-to-bf16",
|
1653 |
+
"nbytes": 2621440,
|
1654 |
+
"byteOffset": 12980224
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"name": "model.layers.20.self_attn.qkv_proj.q_scale",
|
1658 |
+
"shape": [
|
1659 |
+
2560,
|
1660 |
+
64
|
1661 |
+
],
|
1662 |
+
"dtype": "bfloat16",
|
1663 |
+
"format": "raw",
|
1664 |
+
"nbytes": 327680,
|
1665 |
+
"byteOffset": 15601664
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"name": "model.layers.20.self_attn.o_proj.q_weight",
|
1669 |
+
"shape": [
|
1670 |
+
2048,
|
1671 |
+
256
|
1672 |
+
],
|
1673 |
+
"dtype": "uint32",
|
1674 |
+
"format": "f32-to-bf16",
|
1675 |
+
"nbytes": 2097152,
|
1676 |
+
"byteOffset": 15929344
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"name": "model.layers.20.self_attn.o_proj.q_scale",
|
1680 |
+
"shape": [
|
1681 |
+
2048,
|
1682 |
+
64
|
1683 |
+
],
|
1684 |
+
"dtype": "bfloat16",
|
1685 |
+
"format": "raw",
|
1686 |
+
"nbytes": 262144,
|
1687 |
+
"byteOffset": 18026496
|
1688 |
+
},
|
1689 |
+
{
|
1690 |
+
"name": "model.layers.21.input_layernorm.weight",
|
1691 |
+
"shape": [
|
1692 |
+
2048
|
1693 |
+
],
|
1694 |
+
"dtype": "bfloat16",
|
1695 |
+
"format": "raw",
|
1696 |
+
"nbytes": 4096,
|
1697 |
+
"byteOffset": 18288640
|
1698 |
+
},
|
1699 |
+
{
|
1700 |
+
"name": "model.layers.21.mlp.down_proj.q_weight",
|
1701 |
+
"shape": [
|
1702 |
+
2048,
|
1703 |
+
704
|
1704 |
+
],
|
1705 |
+
"dtype": "uint32",
|
1706 |
+
"format": "f32-to-bf16",
|
1707 |
+
"nbytes": 5767168,
|
1708 |
+
"byteOffset": 18292736
|
1709 |
+
},
|
1710 |
+
{
|
1711 |
+
"name": "model.layers.21.mlp.down_proj.q_scale",
|
1712 |
+
"shape": [
|
1713 |
+
2048,
|
1714 |
+
176
|
1715 |
+
],
|
1716 |
+
"dtype": "bfloat16",
|
1717 |
+
"format": "raw",
|
1718 |
+
"nbytes": 720896,
|
1719 |
+
"byteOffset": 24059904
|
1720 |
+
}
|
1721 |
+
],
|
1722 |
+
"md5sum": "b1864fe4abf3244367e8fedd502eb8ca"
|
1723 |
+
},
|
1724 |
+
{
|
1725 |
+
"dataPath": "params_shard_16.bin",
|
1726 |
+
"format": "raw-shard",
|
1727 |
+
"nbytes": 24780800,
|
1728 |
+
"records": [
|
1729 |
+
{
|
1730 |
+
"name": "model.layers.21.mlp.gate_up_proj.q_weight",
|
1731 |
+
"shape": [
|
1732 |
+
11264,
|
1733 |
+
256
|
1734 |
+
],
|
1735 |
+
"dtype": "uint32",
|
1736 |
+
"format": "f32-to-bf16",
|
1737 |
+
"nbytes": 11534336,
|
1738 |
+
"byteOffset": 0
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"name": "model.layers.21.mlp.gate_up_proj.q_scale",
|
1742 |
+
"shape": [
|
1743 |
+
11264,
|
1744 |
+
64
|
1745 |
+
],
|
1746 |
+
"dtype": "bfloat16",
|
1747 |
+
"format": "raw",
|
1748 |
+
"nbytes": 1441792,
|
1749 |
+
"byteOffset": 11534336
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"name": "model.layers.21.post_attention_layernorm.weight",
|
1753 |
+
"shape": [
|
1754 |
+
2048
|
1755 |
+
],
|
1756 |
+
"dtype": "bfloat16",
|
1757 |
+
"format": "raw",
|
1758 |
+
"nbytes": 4096,
|
1759 |
+
"byteOffset": 12976128
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"name": "model.layers.21.self_attn.qkv_proj.q_weight",
|
1763 |
+
"shape": [
|
1764 |
+
2560,
|
1765 |
+
256
|
1766 |
+
],
|
1767 |
+
"dtype": "uint32",
|
1768 |
+
"format": "f32-to-bf16",
|
1769 |
+
"nbytes": 2621440,
|
1770 |
+
"byteOffset": 12980224
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"name": "model.layers.21.self_attn.qkv_proj.q_scale",
|
1774 |
+
"shape": [
|
1775 |
+
2560,
|
1776 |
+
64
|
1777 |
+
],
|
1778 |
+
"dtype": "bfloat16",
|
1779 |
+
"format": "raw",
|
1780 |
+
"nbytes": 327680,
|
1781 |
+
"byteOffset": 15601664
|
1782 |
+
},
|
1783 |
+
{
|
1784 |
+
"name": "model.layers.21.self_attn.o_proj.q_weight",
|
1785 |
+
"shape": [
|
1786 |
+
2048,
|
1787 |
+
256
|
1788 |
+
],
|
1789 |
+
"dtype": "uint32",
|
1790 |
+
"format": "f32-to-bf16",
|
1791 |
+
"nbytes": 2097152,
|
1792 |
+
"byteOffset": 15929344
|
1793 |
+
},
|
1794 |
+
{
|
1795 |
+
"name": "model.layers.21.self_attn.o_proj.q_scale",
|
1796 |
+
"shape": [
|
1797 |
+
2048,
|
1798 |
+
64
|
1799 |
+
],
|
1800 |
+
"dtype": "bfloat16",
|
1801 |
+
"format": "raw",
|
1802 |
+
"nbytes": 262144,
|
1803 |
+
"byteOffset": 18026496
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"name": "model.layers.3.input_layernorm.weight",
|
1807 |
+
"shape": [
|
1808 |
+
2048
|
1809 |
+
],
|
1810 |
+
"dtype": "bfloat16",
|
1811 |
+
"format": "raw",
|
1812 |
+
"nbytes": 4096,
|
1813 |
+
"byteOffset": 18288640
|
1814 |
+
},
|
1815 |
+
{
|
1816 |
+
"name": "model.layers.3.mlp.down_proj.q_weight",
|
1817 |
+
"shape": [
|
1818 |
+
2048,
|
1819 |
+
704
|
1820 |
+
],
|
1821 |
+
"dtype": "uint32",
|
1822 |
+
"format": "f32-to-bf16",
|
1823 |
+
"nbytes": 5767168,
|
1824 |
+
"byteOffset": 18292736
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"name": "model.layers.3.mlp.down_proj.q_scale",
|
1828 |
+
"shape": [
|
1829 |
+
2048,
|
1830 |
+
176
|
1831 |
+
],
|
1832 |
+
"dtype": "bfloat16",
|
1833 |
+
"format": "raw",
|
1834 |
+
"nbytes": 720896,
|
1835 |
+
"byteOffset": 24059904
|
1836 |
+
}
|
1837 |
+
],
|
1838 |
+
"md5sum": "505cab1c1b2228b83fd2c1d2240f0959"
|
1839 |
+
},
|
1840 |
+
{
|
1841 |
+
"dataPath": "params_shard_17.bin",
|
1842 |
+
"format": "raw-shard",
|
1843 |
+
"nbytes": 24780800,
|
1844 |
+
"records": [
|
1845 |
+
{
|
1846 |
+
"name": "model.layers.3.mlp.gate_up_proj.q_weight",
|
1847 |
+
"shape": [
|
1848 |
+
11264,
|
1849 |
+
256
|
1850 |
+
],
|
1851 |
+
"dtype": "uint32",
|
1852 |
+
"format": "f32-to-bf16",
|
1853 |
+
"nbytes": 11534336,
|
1854 |
+
"byteOffset": 0
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
|
1858 |
+
"shape": [
|
1859 |
+
11264,
|
1860 |
+
64
|
1861 |
+
],
|
1862 |
+
"dtype": "bfloat16",
|
1863 |
+
"format": "raw",
|
1864 |
+
"nbytes": 1441792,
|
1865 |
+
"byteOffset": 11534336
|
1866 |
+
},
|
1867 |
+
{
|
1868 |
+
"name": "model.layers.3.post_attention_layernorm.weight",
|
1869 |
+
"shape": [
|
1870 |
+
2048
|
1871 |
+
],
|
1872 |
+
"dtype": "bfloat16",
|
1873 |
+
"format": "raw",
|
1874 |
+
"nbytes": 4096,
|
1875 |
+
"byteOffset": 12976128
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"name": "model.layers.3.self_attn.qkv_proj.q_weight",
|
1879 |
+
"shape": [
|
1880 |
+
2560,
|
1881 |
+
256
|
1882 |
+
],
|
1883 |
+
"dtype": "uint32",
|
1884 |
+
"format": "f32-to-bf16",
|
1885 |
+
"nbytes": 2621440,
|
1886 |
+
"byteOffset": 12980224
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
|
1890 |
+
"shape": [
|
1891 |
+
2560,
|
1892 |
+
64
|
1893 |
+
],
|
1894 |
+
"dtype": "bfloat16",
|
1895 |
+
"format": "raw",
|
1896 |
+
"nbytes": 327680,
|
1897 |
+
"byteOffset": 15601664
|
1898 |
+
},
|
1899 |
+
{
|
1900 |
+
"name": "model.layers.3.self_attn.o_proj.q_weight",
|
1901 |
+
"shape": [
|
1902 |
+
2048,
|
1903 |
+
256
|
1904 |
+
],
|
1905 |
+
"dtype": "uint32",
|
1906 |
+
"format": "f32-to-bf16",
|
1907 |
+
"nbytes": 2097152,
|
1908 |
+
"byteOffset": 15929344
|
1909 |
+
},
|
1910 |
+
{
|
1911 |
+
"name": "model.layers.3.self_attn.o_proj.q_scale",
|
1912 |
+
"shape": [
|
1913 |
+
2048,
|
1914 |
+
64
|
1915 |
+
],
|
1916 |
+
"dtype": "bfloat16",
|
1917 |
+
"format": "raw",
|
1918 |
+
"nbytes": 262144,
|
1919 |
+
"byteOffset": 18026496
|
1920 |
+
},
|
1921 |
+
{
|
1922 |
+
"name": "model.layers.4.input_layernorm.weight",
|
1923 |
+
"shape": [
|
1924 |
+
2048
|
1925 |
+
],
|
1926 |
+
"dtype": "bfloat16",
|
1927 |
+
"format": "raw",
|
1928 |
+
"nbytes": 4096,
|
1929 |
+
"byteOffset": 18288640
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"name": "model.layers.4.mlp.down_proj.q_weight",
|
1933 |
+
"shape": [
|
1934 |
+
2048,
|
1935 |
+
704
|
1936 |
+
],
|
1937 |
+
"dtype": "uint32",
|
1938 |
+
"format": "f32-to-bf16",
|
1939 |
+
"nbytes": 5767168,
|
1940 |
+
"byteOffset": 18292736
|
1941 |
+
},
|
1942 |
+
{
|
1943 |
+
"name": "model.layers.4.mlp.down_proj.q_scale",
|
1944 |
+
"shape": [
|
1945 |
+
2048,
|
1946 |
+
176
|
1947 |
+
],
|
1948 |
+
"dtype": "bfloat16",
|
1949 |
+
"format": "raw",
|
1950 |
+
"nbytes": 720896,
|
1951 |
+
"byteOffset": 24059904
|
1952 |
+
}
|
1953 |
+
],
|
1954 |
+
"md5sum": "a798beddbb6ccf6e8b76b51ae087c28e"
|
1955 |
+
},
|
1956 |
+
{
|
1957 |
+
"dataPath": "params_shard_18.bin",
|
1958 |
+
"format": "raw-shard",
|
1959 |
+
"nbytes": 24780800,
|
1960 |
+
"records": [
|
1961 |
+
{
|
1962 |
+
"name": "model.layers.4.mlp.gate_up_proj.q_weight",
|
1963 |
+
"shape": [
|
1964 |
+
11264,
|
1965 |
+
256
|
1966 |
+
],
|
1967 |
+
"dtype": "uint32",
|
1968 |
+
"format": "f32-to-bf16",
|
1969 |
+
"nbytes": 11534336,
|
1970 |
+
"byteOffset": 0
|
1971 |
+
},
|
1972 |
+
{
|
1973 |
+
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
|
1974 |
+
"shape": [
|
1975 |
+
11264,
|
1976 |
+
64
|
1977 |
+
],
|
1978 |
+
"dtype": "bfloat16",
|
1979 |
+
"format": "raw",
|
1980 |
+
"nbytes": 1441792,
|
1981 |
+
"byteOffset": 11534336
|
1982 |
+
},
|
1983 |
+
{
|
1984 |
+
"name": "model.layers.4.post_attention_layernorm.weight",
|
1985 |
+
"shape": [
|
1986 |
+
2048
|
1987 |
+
],
|
1988 |
+
"dtype": "bfloat16",
|
1989 |
+
"format": "raw",
|
1990 |
+
"nbytes": 4096,
|
1991 |
+
"byteOffset": 12976128
|
1992 |
+
},
|
1993 |
+
{
|
1994 |
+
"name": "model.layers.4.self_attn.qkv_proj.q_weight",
|
1995 |
+
"shape": [
|
1996 |
+
2560,
|
1997 |
+
256
|
1998 |
+
],
|
1999 |
+
"dtype": "uint32",
|
2000 |
+
"format": "f32-to-bf16",
|
2001 |
+
"nbytes": 2621440,
|
2002 |
+
"byteOffset": 12980224
|
2003 |
+
},
|
2004 |
+
{
|
2005 |
+
"name": "model.layers.4.self_attn.qkv_proj.q_scale",
|
2006 |
+
"shape": [
|
2007 |
+
2560,
|
2008 |
+
64
|
2009 |
+
],
|
2010 |
+
"dtype": "bfloat16",
|
2011 |
+
"format": "raw",
|
2012 |
+
"nbytes": 327680,
|
2013 |
+
"byteOffset": 15601664
|
2014 |
+
},
|
2015 |
+
{
|
2016 |
+
"name": "model.layers.4.self_attn.o_proj.q_weight",
|
2017 |
+
"shape": [
|
2018 |
+
2048,
|
2019 |
+
256
|
2020 |
+
],
|
2021 |
+
"dtype": "uint32",
|
2022 |
+
"format": "f32-to-bf16",
|
2023 |
+
"nbytes": 2097152,
|
2024 |
+
"byteOffset": 15929344
|
2025 |
+
},
|
2026 |
+
{
|
2027 |
+
"name": "model.layers.4.self_attn.o_proj.q_scale",
|
2028 |
+
"shape": [
|
2029 |
+
2048,
|
2030 |
+
64
|
2031 |
+
],
|
2032 |
+
"dtype": "bfloat16",
|
2033 |
+
"format": "raw",
|
2034 |
+
"nbytes": 262144,
|
2035 |
+
"byteOffset": 18026496
|
2036 |
+
},
|
2037 |
+
{
|
2038 |
+
"name": "model.layers.5.input_layernorm.weight",
|
2039 |
+
"shape": [
|
2040 |
+
2048
|
2041 |
+
],
|
2042 |
+
"dtype": "bfloat16",
|
2043 |
+
"format": "raw",
|
2044 |
+
"nbytes": 4096,
|
2045 |
+
"byteOffset": 18288640
|
2046 |
+
},
|
2047 |
+
{
|
2048 |
+
"name": "model.layers.5.mlp.down_proj.q_weight",
|
2049 |
+
"shape": [
|
2050 |
+
2048,
|
2051 |
+
704
|
2052 |
+
],
|
2053 |
+
"dtype": "uint32",
|
2054 |
+
"format": "f32-to-bf16",
|
2055 |
+
"nbytes": 5767168,
|
2056 |
+
"byteOffset": 18292736
|
2057 |
+
},
|
2058 |
+
{
|
2059 |
+
"name": "model.layers.5.mlp.down_proj.q_scale",
|
2060 |
+
"shape": [
|
2061 |
+
2048,
|
2062 |
+
176
|
2063 |
+
],
|
2064 |
+
"dtype": "bfloat16",
|
2065 |
+
"format": "raw",
|
2066 |
+
"nbytes": 720896,
|
2067 |
+
"byteOffset": 24059904
|
2068 |
+
}
|
2069 |
+
],
|
2070 |
+
"md5sum": "4fc462bba2bb7ed3004b13350e52ce3f"
|
2071 |
+
},
|
2072 |
+
{
|
2073 |
+
"dataPath": "params_shard_19.bin",
|
2074 |
+
"format": "raw-shard",
|
2075 |
+
"nbytes": 24780800,
|
2076 |
+
"records": [
|
2077 |
+
{
|
2078 |
+
"name": "model.layers.5.mlp.gate_up_proj.q_weight",
|
2079 |
+
"shape": [
|
2080 |
+
11264,
|
2081 |
+
256
|
2082 |
+
],
|
2083 |
+
"dtype": "uint32",
|
2084 |
+
"format": "f32-to-bf16",
|
2085 |
+
"nbytes": 11534336,
|
2086 |
+
"byteOffset": 0
|
2087 |
+
},
|
2088 |
+
{
|
2089 |
+
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
|
2090 |
+
"shape": [
|
2091 |
+
11264,
|
2092 |
+
64
|
2093 |
+
],
|
2094 |
+
"dtype": "bfloat16",
|
2095 |
+
"format": "raw",
|
2096 |
+
"nbytes": 1441792,
|
2097 |
+
"byteOffset": 11534336
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"name": "model.layers.5.post_attention_layernorm.weight",
|
2101 |
+
"shape": [
|
2102 |
+
2048
|
2103 |
+
],
|
2104 |
+
"dtype": "bfloat16",
|
2105 |
+
"format": "raw",
|
2106 |
+
"nbytes": 4096,
|
2107 |
+
"byteOffset": 12976128
|
2108 |
+
},
|
2109 |
+
{
|
2110 |
+
"name": "model.layers.5.self_attn.qkv_proj.q_weight",
|
2111 |
+
"shape": [
|
2112 |
+
2560,
|
2113 |
+
256
|
2114 |
+
],
|
2115 |
+
"dtype": "uint32",
|
2116 |
+
"format": "f32-to-bf16",
|
2117 |
+
"nbytes": 2621440,
|
2118 |
+
"byteOffset": 12980224
|
2119 |
+
},
|
2120 |
+
{
|
2121 |
+
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
|
2122 |
+
"shape": [
|
2123 |
+
2560,
|
2124 |
+
64
|
2125 |
+
],
|
2126 |
+
"dtype": "bfloat16",
|
2127 |
+
"format": "raw",
|
2128 |
+
"nbytes": 327680,
|
2129 |
+
"byteOffset": 15601664
|
2130 |
+
},
|
2131 |
+
{
|
2132 |
+
"name": "model.layers.5.self_attn.o_proj.q_weight",
|
2133 |
+
"shape": [
|
2134 |
+
2048,
|
2135 |
+
256
|
2136 |
+
],
|
2137 |
+
"dtype": "uint32",
|
2138 |
+
"format": "f32-to-bf16",
|
2139 |
+
"nbytes": 2097152,
|
2140 |
+
"byteOffset": 15929344
|
2141 |
+
},
|
2142 |
+
{
|
2143 |
+
"name": "model.layers.5.self_attn.o_proj.q_scale",
|
2144 |
+
"shape": [
|
2145 |
+
2048,
|
2146 |
+
64
|
2147 |
+
],
|
2148 |
+
"dtype": "bfloat16",
|
2149 |
+
"format": "raw",
|
2150 |
+
"nbytes": 262144,
|
2151 |
+
"byteOffset": 18026496
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"name": "model.layers.6.input_layernorm.weight",
|
2155 |
+
"shape": [
|
2156 |
+
2048
|
2157 |
+
],
|
2158 |
+
"dtype": "bfloat16",
|
2159 |
+
"format": "raw",
|
2160 |
+
"nbytes": 4096,
|
2161 |
+
"byteOffset": 18288640
|
2162 |
+
},
|
2163 |
+
{
|
2164 |
+
"name": "model.layers.6.mlp.down_proj.q_weight",
|
2165 |
+
"shape": [
|
2166 |
+
2048,
|
2167 |
+
704
|
2168 |
+
],
|
2169 |
+
"dtype": "uint32",
|
2170 |
+
"format": "f32-to-bf16",
|
2171 |
+
"nbytes": 5767168,
|
2172 |
+
"byteOffset": 18292736
|
2173 |
+
},
|
2174 |
+
{
|
2175 |
+
"name": "model.layers.6.mlp.down_proj.q_scale",
|
2176 |
+
"shape": [
|
2177 |
+
2048,
|
2178 |
+
176
|
2179 |
+
],
|
2180 |
+
"dtype": "bfloat16",
|
2181 |
+
"format": "raw",
|
2182 |
+
"nbytes": 720896,
|
2183 |
+
"byteOffset": 24059904
|
2184 |
+
}
|
2185 |
+
],
|
2186 |
+
"md5sum": "6f0b3e5f9da341272077d653a0983dfe"
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"dataPath": "params_shard_20.bin",
|
2190 |
+
"format": "raw-shard",
|
2191 |
+
"nbytes": 24780800,
|
2192 |
+
"records": [
|
2193 |
+
{
|
2194 |
+
"name": "model.layers.6.mlp.gate_up_proj.q_weight",
|
2195 |
+
"shape": [
|
2196 |
+
11264,
|
2197 |
+
256
|
2198 |
+
],
|
2199 |
+
"dtype": "uint32",
|
2200 |
+
"format": "f32-to-bf16",
|
2201 |
+
"nbytes": 11534336,
|
2202 |
+
"byteOffset": 0
|
2203 |
+
},
|
2204 |
+
{
|
2205 |
+
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
|
2206 |
+
"shape": [
|
2207 |
+
11264,
|
2208 |
+
64
|
2209 |
+
],
|
2210 |
+
"dtype": "bfloat16",
|
2211 |
+
"format": "raw",
|
2212 |
+
"nbytes": 1441792,
|
2213 |
+
"byteOffset": 11534336
|
2214 |
+
},
|
2215 |
+
{
|
2216 |
+
"name": "model.layers.6.post_attention_layernorm.weight",
|
2217 |
+
"shape": [
|
2218 |
+
2048
|
2219 |
+
],
|
2220 |
+
"dtype": "bfloat16",
|
2221 |
+
"format": "raw",
|
2222 |
+
"nbytes": 4096,
|
2223 |
+
"byteOffset": 12976128
|
2224 |
+
},
|
2225 |
+
{
|
2226 |
+
"name": "model.layers.6.self_attn.qkv_proj.q_weight",
|
2227 |
+
"shape": [
|
2228 |
+
2560,
|
2229 |
+
256
|
2230 |
+
],
|
2231 |
+
"dtype": "uint32",
|
2232 |
+
"format": "f32-to-bf16",
|
2233 |
+
"nbytes": 2621440,
|
2234 |
+
"byteOffset": 12980224
|
2235 |
+
},
|
2236 |
+
{
|
2237 |
+
"name": "model.layers.6.self_attn.qkv_proj.q_scale",
|
2238 |
+
"shape": [
|
2239 |
+
2560,
|
2240 |
+
64
|
2241 |
+
],
|
2242 |
+
"dtype": "bfloat16",
|
2243 |
+
"format": "raw",
|
2244 |
+
"nbytes": 327680,
|
2245 |
+
"byteOffset": 15601664
|
2246 |
+
},
|
2247 |
+
{
|
2248 |
+
"name": "model.layers.6.self_attn.o_proj.q_weight",
|
2249 |
+
"shape": [
|
2250 |
+
2048,
|
2251 |
+
256
|
2252 |
+
],
|
2253 |
+
"dtype": "uint32",
|
2254 |
+
"format": "f32-to-bf16",
|
2255 |
+
"nbytes": 2097152,
|
2256 |
+
"byteOffset": 15929344
|
2257 |
+
},
|
2258 |
+
{
|
2259 |
+
"name": "model.layers.6.self_attn.o_proj.q_scale",
|
2260 |
+
"shape": [
|
2261 |
+
2048,
|
2262 |
+
64
|
2263 |
+
],
|
2264 |
+
"dtype": "bfloat16",
|
2265 |
+
"format": "raw",
|
2266 |
+
"nbytes": 262144,
|
2267 |
+
"byteOffset": 18026496
|
2268 |
+
},
|
2269 |
+
{
|
2270 |
+
"name": "model.layers.7.input_layernorm.weight",
|
2271 |
+
"shape": [
|
2272 |
+
2048
|
2273 |
+
],
|
2274 |
+
"dtype": "bfloat16",
|
2275 |
+
"format": "raw",
|
2276 |
+
"nbytes": 4096,
|
2277 |
+
"byteOffset": 18288640
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"name": "model.layers.7.mlp.down_proj.q_weight",
|
2281 |
+
"shape": [
|
2282 |
+
2048,
|
2283 |
+
704
|
2284 |
+
],
|
2285 |
+
"dtype": "uint32",
|
2286 |
+
"format": "f32-to-bf16",
|
2287 |
+
"nbytes": 5767168,
|
2288 |
+
"byteOffset": 18292736
|
2289 |
+
},
|
2290 |
+
{
|
2291 |
+
"name": "model.layers.7.mlp.down_proj.q_scale",
|
2292 |
+
"shape": [
|
2293 |
+
2048,
|
2294 |
+
176
|
2295 |
+
],
|
2296 |
+
"dtype": "bfloat16",
|
2297 |
+
"format": "raw",
|
2298 |
+
"nbytes": 720896,
|
2299 |
+
"byteOffset": 24059904
|
2300 |
+
}
|
2301 |
+
],
|
2302 |
+
"md5sum": "686b2f5cffad40c9ede9515e7d23237e"
|
2303 |
+
},
|
2304 |
+
{
|
2305 |
+
"dataPath": "params_shard_21.bin",
|
2306 |
+
"format": "raw-shard",
|
2307 |
+
"nbytes": 24780800,
|
2308 |
+
"records": [
|
2309 |
+
{
|
2310 |
+
"name": "model.layers.7.mlp.gate_up_proj.q_weight",
|
2311 |
+
"shape": [
|
2312 |
+
11264,
|
2313 |
+
256
|
2314 |
+
],
|
2315 |
+
"dtype": "uint32",
|
2316 |
+
"format": "f32-to-bf16",
|
2317 |
+
"nbytes": 11534336,
|
2318 |
+
"byteOffset": 0
|
2319 |
+
},
|
2320 |
+
{
|
2321 |
+
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
|
2322 |
+
"shape": [
|
2323 |
+
11264,
|
2324 |
+
64
|
2325 |
+
],
|
2326 |
+
"dtype": "bfloat16",
|
2327 |
+
"format": "raw",
|
2328 |
+
"nbytes": 1441792,
|
2329 |
+
"byteOffset": 11534336
|
2330 |
+
},
|
2331 |
+
{
|
2332 |
+
"name": "model.layers.7.post_attention_layernorm.weight",
|
2333 |
+
"shape": [
|
2334 |
+
2048
|
2335 |
+
],
|
2336 |
+
"dtype": "bfloat16",
|
2337 |
+
"format": "raw",
|
2338 |
+
"nbytes": 4096,
|
2339 |
+
"byteOffset": 12976128
|
2340 |
+
},
|
2341 |
+
{
|
2342 |
+
"name": "model.layers.7.self_attn.qkv_proj.q_weight",
|
2343 |
+
"shape": [
|
2344 |
+
2560,
|
2345 |
+
256
|
2346 |
+
],
|
2347 |
+
"dtype": "uint32",
|
2348 |
+
"format": "f32-to-bf16",
|
2349 |
+
"nbytes": 2621440,
|
2350 |
+
"byteOffset": 12980224
|
2351 |
+
},
|
2352 |
+
{
|
2353 |
+
"name": "model.layers.7.self_attn.qkv_proj.q_scale",
|
2354 |
+
"shape": [
|
2355 |
+
2560,
|
2356 |
+
64
|
2357 |
+
],
|
2358 |
+
"dtype": "bfloat16",
|
2359 |
+
"format": "raw",
|
2360 |
+
"nbytes": 327680,
|
2361 |
+
"byteOffset": 15601664
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"name": "model.layers.7.self_attn.o_proj.q_weight",
|
2365 |
+
"shape": [
|
2366 |
+
2048,
|
2367 |
+
256
|
2368 |
+
],
|
2369 |
+
"dtype": "uint32",
|
2370 |
+
"format": "f32-to-bf16",
|
2371 |
+
"nbytes": 2097152,
|
2372 |
+
"byteOffset": 15929344
|
2373 |
+
},
|
2374 |
+
{
|
2375 |
+
"name": "model.layers.7.self_attn.o_proj.q_scale",
|
2376 |
+
"shape": [
|
2377 |
+
2048,
|
2378 |
+
64
|
2379 |
+
],
|
2380 |
+
"dtype": "bfloat16",
|
2381 |
+
"format": "raw",
|
2382 |
+
"nbytes": 262144,
|
2383 |
+
"byteOffset": 18026496
|
2384 |
+
},
|
2385 |
+
{
|
2386 |
+
"name": "model.layers.8.input_layernorm.weight",
|
2387 |
+
"shape": [
|
2388 |
+
2048
|
2389 |
+
],
|
2390 |
+
"dtype": "bfloat16",
|
2391 |
+
"format": "raw",
|
2392 |
+
"nbytes": 4096,
|
2393 |
+
"byteOffset": 18288640
|
2394 |
+
},
|
2395 |
+
{
|
2396 |
+
"name": "model.layers.8.mlp.down_proj.q_weight",
|
2397 |
+
"shape": [
|
2398 |
+
2048,
|
2399 |
+
704
|
2400 |
+
],
|
2401 |
+
"dtype": "uint32",
|
2402 |
+
"format": "f32-to-bf16",
|
2403 |
+
"nbytes": 5767168,
|
2404 |
+
"byteOffset": 18292736
|
2405 |
+
},
|
2406 |
+
{
|
2407 |
+
"name": "model.layers.8.mlp.down_proj.q_scale",
|
2408 |
+
"shape": [
|
2409 |
+
2048,
|
2410 |
+
176
|
2411 |
+
],
|
2412 |
+
"dtype": "bfloat16",
|
2413 |
+
"format": "raw",
|
2414 |
+
"nbytes": 720896,
|
2415 |
+
"byteOffset": 24059904
|
2416 |
+
}
|
2417 |
+
],
|
2418 |
+
"md5sum": "686faea393d9673351ea835a31d58d1c"
|
2419 |
+
},
|
2420 |
+
{
|
2421 |
+
"dataPath": "params_shard_22.bin",
|
2422 |
+
"format": "raw-shard",
|
2423 |
+
"nbytes": 24780800,
|
2424 |
+
"records": [
|
2425 |
+
{
|
2426 |
+
"name": "model.layers.8.mlp.gate_up_proj.q_weight",
|
2427 |
+
"shape": [
|
2428 |
+
11264,
|
2429 |
+
256
|
2430 |
+
],
|
2431 |
+
"dtype": "uint32",
|
2432 |
+
"format": "f32-to-bf16",
|
2433 |
+
"nbytes": 11534336,
|
2434 |
+
"byteOffset": 0
|
2435 |
+
},
|
2436 |
+
{
|
2437 |
+
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
|
2438 |
+
"shape": [
|
2439 |
+
11264,
|
2440 |
+
64
|
2441 |
+
],
|
2442 |
+
"dtype": "bfloat16",
|
2443 |
+
"format": "raw",
|
2444 |
+
"nbytes": 1441792,
|
2445 |
+
"byteOffset": 11534336
|
2446 |
+
},
|
2447 |
+
{
|
2448 |
+
"name": "model.layers.8.post_attention_layernorm.weight",
|
2449 |
+
"shape": [
|
2450 |
+
2048
|
2451 |
+
],
|
2452 |
+
"dtype": "bfloat16",
|
2453 |
+
"format": "raw",
|
2454 |
+
"nbytes": 4096,
|
2455 |
+
"byteOffset": 12976128
|
2456 |
+
},
|
2457 |
+
{
|
2458 |
+
"name": "model.layers.8.self_attn.qkv_proj.q_weight",
|
2459 |
+
"shape": [
|
2460 |
+
2560,
|
2461 |
+
256
|
2462 |
+
],
|
2463 |
+
"dtype": "uint32",
|
2464 |
+
"format": "f32-to-bf16",
|
2465 |
+
"nbytes": 2621440,
|
2466 |
+
"byteOffset": 12980224
|
2467 |
+
},
|
2468 |
+
{
|
2469 |
+
"name": "model.layers.8.self_attn.qkv_proj.q_scale",
|
2470 |
+
"shape": [
|
2471 |
+
2560,
|
2472 |
+
64
|
2473 |
+
],
|
2474 |
+
"dtype": "bfloat16",
|
2475 |
+
"format": "raw",
|
2476 |
+
"nbytes": 327680,
|
2477 |
+
"byteOffset": 15601664
|
2478 |
+
},
|
2479 |
+
{
|
2480 |
+
"name": "model.layers.8.self_attn.o_proj.q_weight",
|
2481 |
+
"shape": [
|
2482 |
+
2048,
|
2483 |
+
256
|
2484 |
+
],
|
2485 |
+
"dtype": "uint32",
|
2486 |
+
"format": "f32-to-bf16",
|
2487 |
+
"nbytes": 2097152,
|
2488 |
+
"byteOffset": 15929344
|
2489 |
+
},
|
2490 |
+
{
|
2491 |
+
"name": "model.layers.8.self_attn.o_proj.q_scale",
|
2492 |
+
"shape": [
|
2493 |
+
2048,
|
2494 |
+
64
|
2495 |
+
],
|
2496 |
+
"dtype": "bfloat16",
|
2497 |
+
"format": "raw",
|
2498 |
+
"nbytes": 262144,
|
2499 |
+
"byteOffset": 18026496
|
2500 |
+
},
|
2501 |
+
{
|
2502 |
+
"name": "model.layers.9.input_layernorm.weight",
|
2503 |
+
"shape": [
|
2504 |
+
2048
|
2505 |
+
],
|
2506 |
+
"dtype": "bfloat16",
|
2507 |
+
"format": "raw",
|
2508 |
+
"nbytes": 4096,
|
2509 |
+
"byteOffset": 18288640
|
2510 |
+
},
|
2511 |
+
{
|
2512 |
+
"name": "model.layers.9.mlp.down_proj.q_weight",
|
2513 |
+
"shape": [
|
2514 |
+
2048,
|
2515 |
+
704
|
2516 |
+
],
|
2517 |
+
"dtype": "uint32",
|
2518 |
+
"format": "f32-to-bf16",
|
2519 |
+
"nbytes": 5767168,
|
2520 |
+
"byteOffset": 18292736
|
2521 |
+
},
|
2522 |
+
{
|
2523 |
+
"name": "model.layers.9.mlp.down_proj.q_scale",
|
2524 |
+
"shape": [
|
2525 |
+
2048,
|
2526 |
+
176
|
2527 |
+
],
|
2528 |
+
"dtype": "bfloat16",
|
2529 |
+
"format": "raw",
|
2530 |
+
"nbytes": 720896,
|
2531 |
+
"byteOffset": 24059904
|
2532 |
+
}
|
2533 |
+
],
|
2534 |
+
"md5sum": "5a11a5b68f457af4ae8df8926c2c02ff"
|
2535 |
+
},
|
2536 |
+
{
|
2537 |
+
"dataPath": "params_shard_23.bin",
|
2538 |
+
"format": "raw-shard",
|
2539 |
+
"nbytes": 18292736,
|
2540 |
+
"records": [
|
2541 |
+
{
|
2542 |
+
"name": "model.layers.9.mlp.gate_up_proj.q_weight",
|
2543 |
+
"shape": [
|
2544 |
+
11264,
|
2545 |
+
256
|
2546 |
+
],
|
2547 |
+
"dtype": "uint32",
|
2548 |
+
"format": "f32-to-bf16",
|
2549 |
+
"nbytes": 11534336,
|
2550 |
+
"byteOffset": 0
|
2551 |
+
},
|
2552 |
+
{
|
2553 |
+
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
|
2554 |
+
"shape": [
|
2555 |
+
11264,
|
2556 |
+
64
|
2557 |
+
],
|
2558 |
+
"dtype": "bfloat16",
|
2559 |
+
"format": "raw",
|
2560 |
+
"nbytes": 1441792,
|
2561 |
+
"byteOffset": 11534336
|
2562 |
+
},
|
2563 |
+
{
|
2564 |
+
"name": "model.layers.9.post_attention_layernorm.weight",
|
2565 |
+
"shape": [
|
2566 |
+
2048
|
2567 |
+
],
|
2568 |
+
"dtype": "bfloat16",
|
2569 |
+
"format": "raw",
|
2570 |
+
"nbytes": 4096,
|
2571 |
+
"byteOffset": 12976128
|
2572 |
+
},
|
2573 |
+
{
|
2574 |
+
"name": "model.layers.9.self_attn.qkv_proj.q_weight",
|
2575 |
+
"shape": [
|
2576 |
+
2560,
|
2577 |
+
256
|
2578 |
+
],
|
2579 |
+
"dtype": "uint32",
|
2580 |
+
"format": "f32-to-bf16",
|
2581 |
+
"nbytes": 2621440,
|
2582 |
+
"byteOffset": 12980224
|
2583 |
+
},
|
2584 |
+
{
|
2585 |
+
"name": "model.layers.9.self_attn.qkv_proj.q_scale",
|
2586 |
+
"shape": [
|
2587 |
+
2560,
|
2588 |
+
64
|
2589 |
+
],
|
2590 |
+
"dtype": "bfloat16",
|
2591 |
+
"format": "raw",
|
2592 |
+
"nbytes": 327680,
|
2593 |
+
"byteOffset": 15601664
|
2594 |
+
},
|
2595 |
+
{
|
2596 |
+
"name": "model.layers.9.self_attn.o_proj.q_weight",
|
2597 |
+
"shape": [
|
2598 |
+
2048,
|
2599 |
+
256
|
2600 |
+
],
|
2601 |
+
"dtype": "uint32",
|
2602 |
+
"format": "f32-to-bf16",
|
2603 |
+
"nbytes": 2097152,
|
2604 |
+
"byteOffset": 15929344
|
2605 |
+
},
|
2606 |
+
{
|
2607 |
+
"name": "model.layers.9.self_attn.o_proj.q_scale",
|
2608 |
+
"shape": [
|
2609 |
+
2048,
|
2610 |
+
64
|
2611 |
+
],
|
2612 |
+
"dtype": "bfloat16",
|
2613 |
+
"format": "raw",
|
2614 |
+
"nbytes": 262144,
|
2615 |
+
"byteOffset": 18026496
|
2616 |
+
},
|
2617 |
+
{
|
2618 |
+
"name": "model.norm.weight",
|
2619 |
+
"shape": [
|
2620 |
+
2048
|
2621 |
+
],
|
2622 |
+
"dtype": "bfloat16",
|
2623 |
+
"format": "raw",
|
2624 |
+
"nbytes": 4096,
|
2625 |
+
"byteOffset": 18288640
|
2626 |
+
}
|
2627 |
+
],
|
2628 |
+
"md5sum": "83f96e3340c8f435412897a17003888e"
|
2629 |
+
}
|
2630 |
+
]
|
2631 |
+
}
|
ndarray-cache.json
ADDED
@@ -0,0 +1,2631 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"ParamSize": 225,
|
4 |
+
"ParamBytes": 687841280.0,
|
5 |
+
"BitsPerParam": 5.0022620095953885
|
6 |
+
},
|
7 |
+
"records": [
|
8 |
+
{
|
9 |
+
"dataPath": "params_shard_0.bin",
|
10 |
+
"format": "raw-shard",
|
11 |
+
"nbytes": 32768000,
|
12 |
+
"records": [
|
13 |
+
{
|
14 |
+
"name": "lm_head.q_weight",
|
15 |
+
"shape": [
|
16 |
+
32000,
|
17 |
+
256
|
18 |
+
],
|
19 |
+
"dtype": "uint32",
|
20 |
+
"format": "f32-to-bf16",
|
21 |
+
"nbytes": 32768000,
|
22 |
+
"byteOffset": 0
|
23 |
+
}
|
24 |
+
],
|
25 |
+
"md5sum": "6acf42e9e3428cda2d937cedfbc2bdbe"
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"dataPath": "params_shard_1.bin",
|
29 |
+
"format": "raw-shard",
|
30 |
+
"nbytes": 32768000,
|
31 |
+
"records": [
|
32 |
+
{
|
33 |
+
"name": "model.embed_tokens.q_weight",
|
34 |
+
"shape": [
|
35 |
+
32000,
|
36 |
+
256
|
37 |
+
],
|
38 |
+
"dtype": "uint32",
|
39 |
+
"format": "f32-to-bf16",
|
40 |
+
"nbytes": 32768000,
|
41 |
+
"byteOffset": 0
|
42 |
+
}
|
43 |
+
],
|
44 |
+
"md5sum": "5a4dc43f3da7ea1f953c0c460796a420"
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"dataPath": "params_shard_2.bin",
|
48 |
+
"format": "raw-shard",
|
49 |
+
"nbytes": 32976896,
|
50 |
+
"records": [
|
51 |
+
{
|
52 |
+
"name": "lm_head.q_scale",
|
53 |
+
"shape": [
|
54 |
+
32000,
|
55 |
+
64
|
56 |
+
],
|
57 |
+
"dtype": "float32",
|
58 |
+
"format": "f32-to-bf16",
|
59 |
+
"nbytes": 4096000,
|
60 |
+
"byteOffset": 0
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"name": "model.embed_tokens.q_scale",
|
64 |
+
"shape": [
|
65 |
+
32000,
|
66 |
+
64
|
67 |
+
],
|
68 |
+
"dtype": "float32",
|
69 |
+
"format": "f32-to-bf16",
|
70 |
+
"nbytes": 4096000,
|
71 |
+
"byteOffset": 4096000
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"name": "model.layers.0.input_layernorm.weight",
|
75 |
+
"shape": [
|
76 |
+
2048
|
77 |
+
],
|
78 |
+
"dtype": "float32",
|
79 |
+
"format": "f32-to-bf16",
|
80 |
+
"nbytes": 4096,
|
81 |
+
"byteOffset": 8192000
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"name": "model.layers.0.mlp.down_proj.q_weight",
|
85 |
+
"shape": [
|
86 |
+
2048,
|
87 |
+
704
|
88 |
+
],
|
89 |
+
"dtype": "uint32",
|
90 |
+
"format": "f32-to-bf16",
|
91 |
+
"nbytes": 5767168,
|
92 |
+
"byteOffset": 8196096
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"name": "model.layers.0.mlp.down_proj.q_scale",
|
96 |
+
"shape": [
|
97 |
+
2048,
|
98 |
+
176
|
99 |
+
],
|
100 |
+
"dtype": "float32",
|
101 |
+
"format": "f32-to-bf16",
|
102 |
+
"nbytes": 720896,
|
103 |
+
"byteOffset": 13963264
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"name": "model.layers.0.mlp.gate_up_proj.q_weight",
|
107 |
+
"shape": [
|
108 |
+
11264,
|
109 |
+
256
|
110 |
+
],
|
111 |
+
"dtype": "uint32",
|
112 |
+
"format": "f32-to-bf16",
|
113 |
+
"nbytes": 11534336,
|
114 |
+
"byteOffset": 14684160
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"name": "model.layers.0.mlp.gate_up_proj.q_scale",
|
118 |
+
"shape": [
|
119 |
+
11264,
|
120 |
+
64
|
121 |
+
],
|
122 |
+
"dtype": "float32",
|
123 |
+
"format": "f32-to-bf16",
|
124 |
+
"nbytes": 1441792,
|
125 |
+
"byteOffset": 26218496
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"name": "model.layers.0.post_attention_layernorm.weight",
|
129 |
+
"shape": [
|
130 |
+
2048
|
131 |
+
],
|
132 |
+
"dtype": "float32",
|
133 |
+
"format": "f32-to-bf16",
|
134 |
+
"nbytes": 4096,
|
135 |
+
"byteOffset": 27660288
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"name": "model.layers.0.self_attn.qkv_proj.q_weight",
|
139 |
+
"shape": [
|
140 |
+
2560,
|
141 |
+
256
|
142 |
+
],
|
143 |
+
"dtype": "uint32",
|
144 |
+
"format": "f32-to-bf16",
|
145 |
+
"nbytes": 2621440,
|
146 |
+
"byteOffset": 27664384
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"name": "model.layers.0.self_attn.qkv_proj.q_scale",
|
150 |
+
"shape": [
|
151 |
+
2560,
|
152 |
+
64
|
153 |
+
],
|
154 |
+
"dtype": "float32",
|
155 |
+
"format": "f32-to-bf16",
|
156 |
+
"nbytes": 327680,
|
157 |
+
"byteOffset": 30285824
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"name": "model.layers.0.self_attn.o_proj.q_weight",
|
161 |
+
"shape": [
|
162 |
+
2048,
|
163 |
+
256
|
164 |
+
],
|
165 |
+
"dtype": "uint32",
|
166 |
+
"format": "f32-to-bf16",
|
167 |
+
"nbytes": 2097152,
|
168 |
+
"byteOffset": 30613504
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"name": "model.layers.0.self_attn.o_proj.q_scale",
|
172 |
+
"shape": [
|
173 |
+
2048,
|
174 |
+
64
|
175 |
+
],
|
176 |
+
"dtype": "float32",
|
177 |
+
"format": "f32-to-bf16",
|
178 |
+
"nbytes": 262144,
|
179 |
+
"byteOffset": 32710656
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"name": "model.layers.1.input_layernorm.weight",
|
183 |
+
"shape": [
|
184 |
+
2048
|
185 |
+
],
|
186 |
+
"dtype": "float32",
|
187 |
+
"format": "f32-to-bf16",
|
188 |
+
"nbytes": 4096,
|
189 |
+
"byteOffset": 32972800
|
190 |
+
}
|
191 |
+
],
|
192 |
+
"md5sum": "b8052fae94b2f9484c7fed0f270034b6"
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"dataPath": "params_shard_3.bin",
|
196 |
+
"format": "raw-shard",
|
197 |
+
"nbytes": 31268864,
|
198 |
+
"records": [
|
199 |
+
{
|
200 |
+
"name": "model.layers.1.mlp.down_proj.q_weight",
|
201 |
+
"shape": [
|
202 |
+
2048,
|
203 |
+
704
|
204 |
+
],
|
205 |
+
"dtype": "uint32",
|
206 |
+
"format": "f32-to-bf16",
|
207 |
+
"nbytes": 5767168,
|
208 |
+
"byteOffset": 0
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"name": "model.layers.1.mlp.down_proj.q_scale",
|
212 |
+
"shape": [
|
213 |
+
2048,
|
214 |
+
176
|
215 |
+
],
|
216 |
+
"dtype": "float32",
|
217 |
+
"format": "f32-to-bf16",
|
218 |
+
"nbytes": 720896,
|
219 |
+
"byteOffset": 5767168
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"name": "model.layers.1.mlp.gate_up_proj.q_weight",
|
223 |
+
"shape": [
|
224 |
+
11264,
|
225 |
+
256
|
226 |
+
],
|
227 |
+
"dtype": "uint32",
|
228 |
+
"format": "f32-to-bf16",
|
229 |
+
"nbytes": 11534336,
|
230 |
+
"byteOffset": 6488064
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"name": "model.layers.1.mlp.gate_up_proj.q_scale",
|
234 |
+
"shape": [
|
235 |
+
11264,
|
236 |
+
64
|
237 |
+
],
|
238 |
+
"dtype": "float32",
|
239 |
+
"format": "f32-to-bf16",
|
240 |
+
"nbytes": 1441792,
|
241 |
+
"byteOffset": 18022400
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"name": "model.layers.1.post_attention_layernorm.weight",
|
245 |
+
"shape": [
|
246 |
+
2048
|
247 |
+
],
|
248 |
+
"dtype": "float32",
|
249 |
+
"format": "f32-to-bf16",
|
250 |
+
"nbytes": 4096,
|
251 |
+
"byteOffset": 19464192
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"name": "model.layers.1.self_attn.qkv_proj.q_weight",
|
255 |
+
"shape": [
|
256 |
+
2560,
|
257 |
+
256
|
258 |
+
],
|
259 |
+
"dtype": "uint32",
|
260 |
+
"format": "f32-to-bf16",
|
261 |
+
"nbytes": 2621440,
|
262 |
+
"byteOffset": 19468288
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"name": "model.layers.1.self_attn.qkv_proj.q_scale",
|
266 |
+
"shape": [
|
267 |
+
2560,
|
268 |
+
64
|
269 |
+
],
|
270 |
+
"dtype": "float32",
|
271 |
+
"format": "f32-to-bf16",
|
272 |
+
"nbytes": 327680,
|
273 |
+
"byteOffset": 22089728
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"name": "model.layers.1.self_attn.o_proj.q_weight",
|
277 |
+
"shape": [
|
278 |
+
2048,
|
279 |
+
256
|
280 |
+
],
|
281 |
+
"dtype": "uint32",
|
282 |
+
"format": "f32-to-bf16",
|
283 |
+
"nbytes": 2097152,
|
284 |
+
"byteOffset": 22417408
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"name": "model.layers.1.self_attn.o_proj.q_scale",
|
288 |
+
"shape": [
|
289 |
+
2048,
|
290 |
+
64
|
291 |
+
],
|
292 |
+
"dtype": "float32",
|
293 |
+
"format": "f32-to-bf16",
|
294 |
+
"nbytes": 262144,
|
295 |
+
"byteOffset": 24514560
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"name": "model.layers.10.input_layernorm.weight",
|
299 |
+
"shape": [
|
300 |
+
2048
|
301 |
+
],
|
302 |
+
"dtype": "float32",
|
303 |
+
"format": "f32-to-bf16",
|
304 |
+
"nbytes": 4096,
|
305 |
+
"byteOffset": 24776704
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"name": "model.layers.10.mlp.down_proj.q_weight",
|
309 |
+
"shape": [
|
310 |
+
2048,
|
311 |
+
704
|
312 |
+
],
|
313 |
+
"dtype": "uint32",
|
314 |
+
"format": "f32-to-bf16",
|
315 |
+
"nbytes": 5767168,
|
316 |
+
"byteOffset": 24780800
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"name": "model.layers.10.mlp.down_proj.q_scale",
|
320 |
+
"shape": [
|
321 |
+
2048,
|
322 |
+
176
|
323 |
+
],
|
324 |
+
"dtype": "float32",
|
325 |
+
"format": "f32-to-bf16",
|
326 |
+
"nbytes": 720896,
|
327 |
+
"byteOffset": 30547968
|
328 |
+
}
|
329 |
+
],
|
330 |
+
"md5sum": "236ea086fe698d15895a284f828cd334"
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"dataPath": "params_shard_4.bin",
|
334 |
+
"format": "raw-shard",
|
335 |
+
"nbytes": 24780800,
|
336 |
+
"records": [
|
337 |
+
{
|
338 |
+
"name": "model.layers.10.mlp.gate_up_proj.q_weight",
|
339 |
+
"shape": [
|
340 |
+
11264,
|
341 |
+
256
|
342 |
+
],
|
343 |
+
"dtype": "uint32",
|
344 |
+
"format": "f32-to-bf16",
|
345 |
+
"nbytes": 11534336,
|
346 |
+
"byteOffset": 0
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"name": "model.layers.10.mlp.gate_up_proj.q_scale",
|
350 |
+
"shape": [
|
351 |
+
11264,
|
352 |
+
64
|
353 |
+
],
|
354 |
+
"dtype": "float32",
|
355 |
+
"format": "f32-to-bf16",
|
356 |
+
"nbytes": 1441792,
|
357 |
+
"byteOffset": 11534336
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"name": "model.layers.10.post_attention_layernorm.weight",
|
361 |
+
"shape": [
|
362 |
+
2048
|
363 |
+
],
|
364 |
+
"dtype": "float32",
|
365 |
+
"format": "f32-to-bf16",
|
366 |
+
"nbytes": 4096,
|
367 |
+
"byteOffset": 12976128
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"name": "model.layers.10.self_attn.qkv_proj.q_weight",
|
371 |
+
"shape": [
|
372 |
+
2560,
|
373 |
+
256
|
374 |
+
],
|
375 |
+
"dtype": "uint32",
|
376 |
+
"format": "f32-to-bf16",
|
377 |
+
"nbytes": 2621440,
|
378 |
+
"byteOffset": 12980224
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"name": "model.layers.10.self_attn.qkv_proj.q_scale",
|
382 |
+
"shape": [
|
383 |
+
2560,
|
384 |
+
64
|
385 |
+
],
|
386 |
+
"dtype": "float32",
|
387 |
+
"format": "f32-to-bf16",
|
388 |
+
"nbytes": 327680,
|
389 |
+
"byteOffset": 15601664
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"name": "model.layers.10.self_attn.o_proj.q_weight",
|
393 |
+
"shape": [
|
394 |
+
2048,
|
395 |
+
256
|
396 |
+
],
|
397 |
+
"dtype": "uint32",
|
398 |
+
"format": "f32-to-bf16",
|
399 |
+
"nbytes": 2097152,
|
400 |
+
"byteOffset": 15929344
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"name": "model.layers.10.self_attn.o_proj.q_scale",
|
404 |
+
"shape": [
|
405 |
+
2048,
|
406 |
+
64
|
407 |
+
],
|
408 |
+
"dtype": "float32",
|
409 |
+
"format": "f32-to-bf16",
|
410 |
+
"nbytes": 262144,
|
411 |
+
"byteOffset": 18026496
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"name": "model.layers.11.input_layernorm.weight",
|
415 |
+
"shape": [
|
416 |
+
2048
|
417 |
+
],
|
418 |
+
"dtype": "float32",
|
419 |
+
"format": "f32-to-bf16",
|
420 |
+
"nbytes": 4096,
|
421 |
+
"byteOffset": 18288640
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"name": "model.layers.11.mlp.down_proj.q_weight",
|
425 |
+
"shape": [
|
426 |
+
2048,
|
427 |
+
704
|
428 |
+
],
|
429 |
+
"dtype": "uint32",
|
430 |
+
"format": "f32-to-bf16",
|
431 |
+
"nbytes": 5767168,
|
432 |
+
"byteOffset": 18292736
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"name": "model.layers.11.mlp.down_proj.q_scale",
|
436 |
+
"shape": [
|
437 |
+
2048,
|
438 |
+
176
|
439 |
+
],
|
440 |
+
"dtype": "float32",
|
441 |
+
"format": "f32-to-bf16",
|
442 |
+
"nbytes": 720896,
|
443 |
+
"byteOffset": 24059904
|
444 |
+
}
|
445 |
+
],
|
446 |
+
"md5sum": "9f801a8ec12c49b630b273561a4d9554"
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"dataPath": "params_shard_5.bin",
|
450 |
+
"format": "raw-shard",
|
451 |
+
"nbytes": 24780800,
|
452 |
+
"records": [
|
453 |
+
{
|
454 |
+
"name": "model.layers.11.mlp.gate_up_proj.q_weight",
|
455 |
+
"shape": [
|
456 |
+
11264,
|
457 |
+
256
|
458 |
+
],
|
459 |
+
"dtype": "uint32",
|
460 |
+
"format": "f32-to-bf16",
|
461 |
+
"nbytes": 11534336,
|
462 |
+
"byteOffset": 0
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"name": "model.layers.11.mlp.gate_up_proj.q_scale",
|
466 |
+
"shape": [
|
467 |
+
11264,
|
468 |
+
64
|
469 |
+
],
|
470 |
+
"dtype": "float32",
|
471 |
+
"format": "f32-to-bf16",
|
472 |
+
"nbytes": 1441792,
|
473 |
+
"byteOffset": 11534336
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"name": "model.layers.11.post_attention_layernorm.weight",
|
477 |
+
"shape": [
|
478 |
+
2048
|
479 |
+
],
|
480 |
+
"dtype": "float32",
|
481 |
+
"format": "f32-to-bf16",
|
482 |
+
"nbytes": 4096,
|
483 |
+
"byteOffset": 12976128
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"name": "model.layers.11.self_attn.qkv_proj.q_weight",
|
487 |
+
"shape": [
|
488 |
+
2560,
|
489 |
+
256
|
490 |
+
],
|
491 |
+
"dtype": "uint32",
|
492 |
+
"format": "f32-to-bf16",
|
493 |
+
"nbytes": 2621440,
|
494 |
+
"byteOffset": 12980224
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"name": "model.layers.11.self_attn.qkv_proj.q_scale",
|
498 |
+
"shape": [
|
499 |
+
2560,
|
500 |
+
64
|
501 |
+
],
|
502 |
+
"dtype": "float32",
|
503 |
+
"format": "f32-to-bf16",
|
504 |
+
"nbytes": 327680,
|
505 |
+
"byteOffset": 15601664
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"name": "model.layers.11.self_attn.o_proj.q_weight",
|
509 |
+
"shape": [
|
510 |
+
2048,
|
511 |
+
256
|
512 |
+
],
|
513 |
+
"dtype": "uint32",
|
514 |
+
"format": "f32-to-bf16",
|
515 |
+
"nbytes": 2097152,
|
516 |
+
"byteOffset": 15929344
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"name": "model.layers.11.self_attn.o_proj.q_scale",
|
520 |
+
"shape": [
|
521 |
+
2048,
|
522 |
+
64
|
523 |
+
],
|
524 |
+
"dtype": "float32",
|
525 |
+
"format": "f32-to-bf16",
|
526 |
+
"nbytes": 262144,
|
527 |
+
"byteOffset": 18026496
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"name": "model.layers.12.input_layernorm.weight",
|
531 |
+
"shape": [
|
532 |
+
2048
|
533 |
+
],
|
534 |
+
"dtype": "float32",
|
535 |
+
"format": "f32-to-bf16",
|
536 |
+
"nbytes": 4096,
|
537 |
+
"byteOffset": 18288640
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"name": "model.layers.12.mlp.down_proj.q_weight",
|
541 |
+
"shape": [
|
542 |
+
2048,
|
543 |
+
704
|
544 |
+
],
|
545 |
+
"dtype": "uint32",
|
546 |
+
"format": "f32-to-bf16",
|
547 |
+
"nbytes": 5767168,
|
548 |
+
"byteOffset": 18292736
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"name": "model.layers.12.mlp.down_proj.q_scale",
|
552 |
+
"shape": [
|
553 |
+
2048,
|
554 |
+
176
|
555 |
+
],
|
556 |
+
"dtype": "float32",
|
557 |
+
"format": "f32-to-bf16",
|
558 |
+
"nbytes": 720896,
|
559 |
+
"byteOffset": 24059904
|
560 |
+
}
|
561 |
+
],
|
562 |
+
"md5sum": "4a90502242460bc5d815ab87dcc2c3fc"
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"dataPath": "params_shard_6.bin",
|
566 |
+
"format": "raw-shard",
|
567 |
+
"nbytes": 24780800,
|
568 |
+
"records": [
|
569 |
+
{
|
570 |
+
"name": "model.layers.12.mlp.gate_up_proj.q_weight",
|
571 |
+
"shape": [
|
572 |
+
11264,
|
573 |
+
256
|
574 |
+
],
|
575 |
+
"dtype": "uint32",
|
576 |
+
"format": "f32-to-bf16",
|
577 |
+
"nbytes": 11534336,
|
578 |
+
"byteOffset": 0
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"name": "model.layers.12.mlp.gate_up_proj.q_scale",
|
582 |
+
"shape": [
|
583 |
+
11264,
|
584 |
+
64
|
585 |
+
],
|
586 |
+
"dtype": "float32",
|
587 |
+
"format": "f32-to-bf16",
|
588 |
+
"nbytes": 1441792,
|
589 |
+
"byteOffset": 11534336
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"name": "model.layers.12.post_attention_layernorm.weight",
|
593 |
+
"shape": [
|
594 |
+
2048
|
595 |
+
],
|
596 |
+
"dtype": "float32",
|
597 |
+
"format": "f32-to-bf16",
|
598 |
+
"nbytes": 4096,
|
599 |
+
"byteOffset": 12976128
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"name": "model.layers.12.self_attn.qkv_proj.q_weight",
|
603 |
+
"shape": [
|
604 |
+
2560,
|
605 |
+
256
|
606 |
+
],
|
607 |
+
"dtype": "uint32",
|
608 |
+
"format": "f32-to-bf16",
|
609 |
+
"nbytes": 2621440,
|
610 |
+
"byteOffset": 12980224
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"name": "model.layers.12.self_attn.qkv_proj.q_scale",
|
614 |
+
"shape": [
|
615 |
+
2560,
|
616 |
+
64
|
617 |
+
],
|
618 |
+
"dtype": "float32",
|
619 |
+
"format": "f32-to-bf16",
|
620 |
+
"nbytes": 327680,
|
621 |
+
"byteOffset": 15601664
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"name": "model.layers.12.self_attn.o_proj.q_weight",
|
625 |
+
"shape": [
|
626 |
+
2048,
|
627 |
+
256
|
628 |
+
],
|
629 |
+
"dtype": "uint32",
|
630 |
+
"format": "f32-to-bf16",
|
631 |
+
"nbytes": 2097152,
|
632 |
+
"byteOffset": 15929344
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"name": "model.layers.12.self_attn.o_proj.q_scale",
|
636 |
+
"shape": [
|
637 |
+
2048,
|
638 |
+
64
|
639 |
+
],
|
640 |
+
"dtype": "float32",
|
641 |
+
"format": "f32-to-bf16",
|
642 |
+
"nbytes": 262144,
|
643 |
+
"byteOffset": 18026496
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"name": "model.layers.13.input_layernorm.weight",
|
647 |
+
"shape": [
|
648 |
+
2048
|
649 |
+
],
|
650 |
+
"dtype": "float32",
|
651 |
+
"format": "f32-to-bf16",
|
652 |
+
"nbytes": 4096,
|
653 |
+
"byteOffset": 18288640
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"name": "model.layers.13.mlp.down_proj.q_weight",
|
657 |
+
"shape": [
|
658 |
+
2048,
|
659 |
+
704
|
660 |
+
],
|
661 |
+
"dtype": "uint32",
|
662 |
+
"format": "f32-to-bf16",
|
663 |
+
"nbytes": 5767168,
|
664 |
+
"byteOffset": 18292736
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"name": "model.layers.13.mlp.down_proj.q_scale",
|
668 |
+
"shape": [
|
669 |
+
2048,
|
670 |
+
176
|
671 |
+
],
|
672 |
+
"dtype": "float32",
|
673 |
+
"format": "f32-to-bf16",
|
674 |
+
"nbytes": 720896,
|
675 |
+
"byteOffset": 24059904
|
676 |
+
}
|
677 |
+
],
|
678 |
+
"md5sum": "4bc1e064d362ffbf9bae57c15e735e8d"
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"dataPath": "params_shard_7.bin",
|
682 |
+
"format": "raw-shard",
|
683 |
+
"nbytes": 24780800,
|
684 |
+
"records": [
|
685 |
+
{
|
686 |
+
"name": "model.layers.13.mlp.gate_up_proj.q_weight",
|
687 |
+
"shape": [
|
688 |
+
11264,
|
689 |
+
256
|
690 |
+
],
|
691 |
+
"dtype": "uint32",
|
692 |
+
"format": "f32-to-bf16",
|
693 |
+
"nbytes": 11534336,
|
694 |
+
"byteOffset": 0
|
695 |
+
},
|
696 |
+
{
|
697 |
+
"name": "model.layers.13.mlp.gate_up_proj.q_scale",
|
698 |
+
"shape": [
|
699 |
+
11264,
|
700 |
+
64
|
701 |
+
],
|
702 |
+
"dtype": "float32",
|
703 |
+
"format": "f32-to-bf16",
|
704 |
+
"nbytes": 1441792,
|
705 |
+
"byteOffset": 11534336
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"name": "model.layers.13.post_attention_layernorm.weight",
|
709 |
+
"shape": [
|
710 |
+
2048
|
711 |
+
],
|
712 |
+
"dtype": "float32",
|
713 |
+
"format": "f32-to-bf16",
|
714 |
+
"nbytes": 4096,
|
715 |
+
"byteOffset": 12976128
|
716 |
+
},
|
717 |
+
{
|
718 |
+
"name": "model.layers.13.self_attn.qkv_proj.q_weight",
|
719 |
+
"shape": [
|
720 |
+
2560,
|
721 |
+
256
|
722 |
+
],
|
723 |
+
"dtype": "uint32",
|
724 |
+
"format": "f32-to-bf16",
|
725 |
+
"nbytes": 2621440,
|
726 |
+
"byteOffset": 12980224
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"name": "model.layers.13.self_attn.qkv_proj.q_scale",
|
730 |
+
"shape": [
|
731 |
+
2560,
|
732 |
+
64
|
733 |
+
],
|
734 |
+
"dtype": "float32",
|
735 |
+
"format": "f32-to-bf16",
|
736 |
+
"nbytes": 327680,
|
737 |
+
"byteOffset": 15601664
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"name": "model.layers.13.self_attn.o_proj.q_weight",
|
741 |
+
"shape": [
|
742 |
+
2048,
|
743 |
+
256
|
744 |
+
],
|
745 |
+
"dtype": "uint32",
|
746 |
+
"format": "f32-to-bf16",
|
747 |
+
"nbytes": 2097152,
|
748 |
+
"byteOffset": 15929344
|
749 |
+
},
|
750 |
+
{
|
751 |
+
"name": "model.layers.13.self_attn.o_proj.q_scale",
|
752 |
+
"shape": [
|
753 |
+
2048,
|
754 |
+
64
|
755 |
+
],
|
756 |
+
"dtype": "float32",
|
757 |
+
"format": "f32-to-bf16",
|
758 |
+
"nbytes": 262144,
|
759 |
+
"byteOffset": 18026496
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"name": "model.layers.14.input_layernorm.weight",
|
763 |
+
"shape": [
|
764 |
+
2048
|
765 |
+
],
|
766 |
+
"dtype": "float32",
|
767 |
+
"format": "f32-to-bf16",
|
768 |
+
"nbytes": 4096,
|
769 |
+
"byteOffset": 18288640
|
770 |
+
},
|
771 |
+
{
|
772 |
+
"name": "model.layers.14.mlp.down_proj.q_weight",
|
773 |
+
"shape": [
|
774 |
+
2048,
|
775 |
+
704
|
776 |
+
],
|
777 |
+
"dtype": "uint32",
|
778 |
+
"format": "f32-to-bf16",
|
779 |
+
"nbytes": 5767168,
|
780 |
+
"byteOffset": 18292736
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"name": "model.layers.14.mlp.down_proj.q_scale",
|
784 |
+
"shape": [
|
785 |
+
2048,
|
786 |
+
176
|
787 |
+
],
|
788 |
+
"dtype": "float32",
|
789 |
+
"format": "f32-to-bf16",
|
790 |
+
"nbytes": 720896,
|
791 |
+
"byteOffset": 24059904
|
792 |
+
}
|
793 |
+
],
|
794 |
+
"md5sum": "85a8f0c3b9857df7a6fa1b9cbbb5d927"
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"dataPath": "params_shard_8.bin",
|
798 |
+
"format": "raw-shard",
|
799 |
+
"nbytes": 24780800,
|
800 |
+
"records": [
|
801 |
+
{
|
802 |
+
"name": "model.layers.14.mlp.gate_up_proj.q_weight",
|
803 |
+
"shape": [
|
804 |
+
11264,
|
805 |
+
256
|
806 |
+
],
|
807 |
+
"dtype": "uint32",
|
808 |
+
"format": "f32-to-bf16",
|
809 |
+
"nbytes": 11534336,
|
810 |
+
"byteOffset": 0
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"name": "model.layers.14.mlp.gate_up_proj.q_scale",
|
814 |
+
"shape": [
|
815 |
+
11264,
|
816 |
+
64
|
817 |
+
],
|
818 |
+
"dtype": "float32",
|
819 |
+
"format": "f32-to-bf16",
|
820 |
+
"nbytes": 1441792,
|
821 |
+
"byteOffset": 11534336
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"name": "model.layers.14.post_attention_layernorm.weight",
|
825 |
+
"shape": [
|
826 |
+
2048
|
827 |
+
],
|
828 |
+
"dtype": "float32",
|
829 |
+
"format": "f32-to-bf16",
|
830 |
+
"nbytes": 4096,
|
831 |
+
"byteOffset": 12976128
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"name": "model.layers.14.self_attn.qkv_proj.q_weight",
|
835 |
+
"shape": [
|
836 |
+
2560,
|
837 |
+
256
|
838 |
+
],
|
839 |
+
"dtype": "uint32",
|
840 |
+
"format": "f32-to-bf16",
|
841 |
+
"nbytes": 2621440,
|
842 |
+
"byteOffset": 12980224
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"name": "model.layers.14.self_attn.qkv_proj.q_scale",
|
846 |
+
"shape": [
|
847 |
+
2560,
|
848 |
+
64
|
849 |
+
],
|
850 |
+
"dtype": "float32",
|
851 |
+
"format": "f32-to-bf16",
|
852 |
+
"nbytes": 327680,
|
853 |
+
"byteOffset": 15601664
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"name": "model.layers.14.self_attn.o_proj.q_weight",
|
857 |
+
"shape": [
|
858 |
+
2048,
|
859 |
+
256
|
860 |
+
],
|
861 |
+
"dtype": "uint32",
|
862 |
+
"format": "f32-to-bf16",
|
863 |
+
"nbytes": 2097152,
|
864 |
+
"byteOffset": 15929344
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"name": "model.layers.14.self_attn.o_proj.q_scale",
|
868 |
+
"shape": [
|
869 |
+
2048,
|
870 |
+
64
|
871 |
+
],
|
872 |
+
"dtype": "float32",
|
873 |
+
"format": "f32-to-bf16",
|
874 |
+
"nbytes": 262144,
|
875 |
+
"byteOffset": 18026496
|
876 |
+
},
|
877 |
+
{
|
878 |
+
"name": "model.layers.15.input_layernorm.weight",
|
879 |
+
"shape": [
|
880 |
+
2048
|
881 |
+
],
|
882 |
+
"dtype": "float32",
|
883 |
+
"format": "f32-to-bf16",
|
884 |
+
"nbytes": 4096,
|
885 |
+
"byteOffset": 18288640
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"name": "model.layers.15.mlp.down_proj.q_weight",
|
889 |
+
"shape": [
|
890 |
+
2048,
|
891 |
+
704
|
892 |
+
],
|
893 |
+
"dtype": "uint32",
|
894 |
+
"format": "f32-to-bf16",
|
895 |
+
"nbytes": 5767168,
|
896 |
+
"byteOffset": 18292736
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"name": "model.layers.15.mlp.down_proj.q_scale",
|
900 |
+
"shape": [
|
901 |
+
2048,
|
902 |
+
176
|
903 |
+
],
|
904 |
+
"dtype": "float32",
|
905 |
+
"format": "f32-to-bf16",
|
906 |
+
"nbytes": 720896,
|
907 |
+
"byteOffset": 24059904
|
908 |
+
}
|
909 |
+
],
|
910 |
+
"md5sum": "18e9c491a88f7adc43ed17d6f940f080"
|
911 |
+
},
|
912 |
+
{
|
913 |
+
"dataPath": "params_shard_9.bin",
|
914 |
+
"format": "raw-shard",
|
915 |
+
"nbytes": 24780800,
|
916 |
+
"records": [
|
917 |
+
{
|
918 |
+
"name": "model.layers.15.mlp.gate_up_proj.q_weight",
|
919 |
+
"shape": [
|
920 |
+
11264,
|
921 |
+
256
|
922 |
+
],
|
923 |
+
"dtype": "uint32",
|
924 |
+
"format": "f32-to-bf16",
|
925 |
+
"nbytes": 11534336,
|
926 |
+
"byteOffset": 0
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"name": "model.layers.15.mlp.gate_up_proj.q_scale",
|
930 |
+
"shape": [
|
931 |
+
11264,
|
932 |
+
64
|
933 |
+
],
|
934 |
+
"dtype": "float32",
|
935 |
+
"format": "f32-to-bf16",
|
936 |
+
"nbytes": 1441792,
|
937 |
+
"byteOffset": 11534336
|
938 |
+
},
|
939 |
+
{
|
940 |
+
"name": "model.layers.15.post_attention_layernorm.weight",
|
941 |
+
"shape": [
|
942 |
+
2048
|
943 |
+
],
|
944 |
+
"dtype": "float32",
|
945 |
+
"format": "f32-to-bf16",
|
946 |
+
"nbytes": 4096,
|
947 |
+
"byteOffset": 12976128
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"name": "model.layers.15.self_attn.qkv_proj.q_weight",
|
951 |
+
"shape": [
|
952 |
+
2560,
|
953 |
+
256
|
954 |
+
],
|
955 |
+
"dtype": "uint32",
|
956 |
+
"format": "f32-to-bf16",
|
957 |
+
"nbytes": 2621440,
|
958 |
+
"byteOffset": 12980224
|
959 |
+
},
|
960 |
+
{
|
961 |
+
"name": "model.layers.15.self_attn.qkv_proj.q_scale",
|
962 |
+
"shape": [
|
963 |
+
2560,
|
964 |
+
64
|
965 |
+
],
|
966 |
+
"dtype": "float32",
|
967 |
+
"format": "f32-to-bf16",
|
968 |
+
"nbytes": 327680,
|
969 |
+
"byteOffset": 15601664
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"name": "model.layers.15.self_attn.o_proj.q_weight",
|
973 |
+
"shape": [
|
974 |
+
2048,
|
975 |
+
256
|
976 |
+
],
|
977 |
+
"dtype": "uint32",
|
978 |
+
"format": "f32-to-bf16",
|
979 |
+
"nbytes": 2097152,
|
980 |
+
"byteOffset": 15929344
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"name": "model.layers.15.self_attn.o_proj.q_scale",
|
984 |
+
"shape": [
|
985 |
+
2048,
|
986 |
+
64
|
987 |
+
],
|
988 |
+
"dtype": "float32",
|
989 |
+
"format": "f32-to-bf16",
|
990 |
+
"nbytes": 262144,
|
991 |
+
"byteOffset": 18026496
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"name": "model.layers.16.input_layernorm.weight",
|
995 |
+
"shape": [
|
996 |
+
2048
|
997 |
+
],
|
998 |
+
"dtype": "float32",
|
999 |
+
"format": "f32-to-bf16",
|
1000 |
+
"nbytes": 4096,
|
1001 |
+
"byteOffset": 18288640
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"name": "model.layers.16.mlp.down_proj.q_weight",
|
1005 |
+
"shape": [
|
1006 |
+
2048,
|
1007 |
+
704
|
1008 |
+
],
|
1009 |
+
"dtype": "uint32",
|
1010 |
+
"format": "f32-to-bf16",
|
1011 |
+
"nbytes": 5767168,
|
1012 |
+
"byteOffset": 18292736
|
1013 |
+
},
|
1014 |
+
{
|
1015 |
+
"name": "model.layers.16.mlp.down_proj.q_scale",
|
1016 |
+
"shape": [
|
1017 |
+
2048,
|
1018 |
+
176
|
1019 |
+
],
|
1020 |
+
"dtype": "float32",
|
1021 |
+
"format": "f32-to-bf16",
|
1022 |
+
"nbytes": 720896,
|
1023 |
+
"byteOffset": 24059904
|
1024 |
+
}
|
1025 |
+
],
|
1026 |
+
"md5sum": "ebe88a618b7cb4980864878efb2bdbb7"
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"dataPath": "params_shard_10.bin",
|
1030 |
+
"format": "raw-shard",
|
1031 |
+
"nbytes": 24780800,
|
1032 |
+
"records": [
|
1033 |
+
{
|
1034 |
+
"name": "model.layers.16.mlp.gate_up_proj.q_weight",
|
1035 |
+
"shape": [
|
1036 |
+
11264,
|
1037 |
+
256
|
1038 |
+
],
|
1039 |
+
"dtype": "uint32",
|
1040 |
+
"format": "f32-to-bf16",
|
1041 |
+
"nbytes": 11534336,
|
1042 |
+
"byteOffset": 0
|
1043 |
+
},
|
1044 |
+
{
|
1045 |
+
"name": "model.layers.16.mlp.gate_up_proj.q_scale",
|
1046 |
+
"shape": [
|
1047 |
+
11264,
|
1048 |
+
64
|
1049 |
+
],
|
1050 |
+
"dtype": "float32",
|
1051 |
+
"format": "f32-to-bf16",
|
1052 |
+
"nbytes": 1441792,
|
1053 |
+
"byteOffset": 11534336
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"name": "model.layers.16.post_attention_layernorm.weight",
|
1057 |
+
"shape": [
|
1058 |
+
2048
|
1059 |
+
],
|
1060 |
+
"dtype": "float32",
|
1061 |
+
"format": "f32-to-bf16",
|
1062 |
+
"nbytes": 4096,
|
1063 |
+
"byteOffset": 12976128
|
1064 |
+
},
|
1065 |
+
{
|
1066 |
+
"name": "model.layers.16.self_attn.qkv_proj.q_weight",
|
1067 |
+
"shape": [
|
1068 |
+
2560,
|
1069 |
+
256
|
1070 |
+
],
|
1071 |
+
"dtype": "uint32",
|
1072 |
+
"format": "f32-to-bf16",
|
1073 |
+
"nbytes": 2621440,
|
1074 |
+
"byteOffset": 12980224
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"name": "model.layers.16.self_attn.qkv_proj.q_scale",
|
1078 |
+
"shape": [
|
1079 |
+
2560,
|
1080 |
+
64
|
1081 |
+
],
|
1082 |
+
"dtype": "float32",
|
1083 |
+
"format": "f32-to-bf16",
|
1084 |
+
"nbytes": 327680,
|
1085 |
+
"byteOffset": 15601664
|
1086 |
+
},
|
1087 |
+
{
|
1088 |
+
"name": "model.layers.16.self_attn.o_proj.q_weight",
|
1089 |
+
"shape": [
|
1090 |
+
2048,
|
1091 |
+
256
|
1092 |
+
],
|
1093 |
+
"dtype": "uint32",
|
1094 |
+
"format": "f32-to-bf16",
|
1095 |
+
"nbytes": 2097152,
|
1096 |
+
"byteOffset": 15929344
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"name": "model.layers.16.self_attn.o_proj.q_scale",
|
1100 |
+
"shape": [
|
1101 |
+
2048,
|
1102 |
+
64
|
1103 |
+
],
|
1104 |
+
"dtype": "float32",
|
1105 |
+
"format": "f32-to-bf16",
|
1106 |
+
"nbytes": 262144,
|
1107 |
+
"byteOffset": 18026496
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"name": "model.layers.17.input_layernorm.weight",
|
1111 |
+
"shape": [
|
1112 |
+
2048
|
1113 |
+
],
|
1114 |
+
"dtype": "float32",
|
1115 |
+
"format": "f32-to-bf16",
|
1116 |
+
"nbytes": 4096,
|
1117 |
+
"byteOffset": 18288640
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"name": "model.layers.17.mlp.down_proj.q_weight",
|
1121 |
+
"shape": [
|
1122 |
+
2048,
|
1123 |
+
704
|
1124 |
+
],
|
1125 |
+
"dtype": "uint32",
|
1126 |
+
"format": "f32-to-bf16",
|
1127 |
+
"nbytes": 5767168,
|
1128 |
+
"byteOffset": 18292736
|
1129 |
+
},
|
1130 |
+
{
|
1131 |
+
"name": "model.layers.17.mlp.down_proj.q_scale",
|
1132 |
+
"shape": [
|
1133 |
+
2048,
|
1134 |
+
176
|
1135 |
+
],
|
1136 |
+
"dtype": "float32",
|
1137 |
+
"format": "f32-to-bf16",
|
1138 |
+
"nbytes": 720896,
|
1139 |
+
"byteOffset": 24059904
|
1140 |
+
}
|
1141 |
+
],
|
1142 |
+
"md5sum": "2a298c0af58f1e1a208b199e40b49972"
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"dataPath": "params_shard_11.bin",
|
1146 |
+
"format": "raw-shard",
|
1147 |
+
"nbytes": 24780800,
|
1148 |
+
"records": [
|
1149 |
+
{
|
1150 |
+
"name": "model.layers.17.mlp.gate_up_proj.q_weight",
|
1151 |
+
"shape": [
|
1152 |
+
11264,
|
1153 |
+
256
|
1154 |
+
],
|
1155 |
+
"dtype": "uint32",
|
1156 |
+
"format": "f32-to-bf16",
|
1157 |
+
"nbytes": 11534336,
|
1158 |
+
"byteOffset": 0
|
1159 |
+
},
|
1160 |
+
{
|
1161 |
+
"name": "model.layers.17.mlp.gate_up_proj.q_scale",
|
1162 |
+
"shape": [
|
1163 |
+
11264,
|
1164 |
+
64
|
1165 |
+
],
|
1166 |
+
"dtype": "float32",
|
1167 |
+
"format": "f32-to-bf16",
|
1168 |
+
"nbytes": 1441792,
|
1169 |
+
"byteOffset": 11534336
|
1170 |
+
},
|
1171 |
+
{
|
1172 |
+
"name": "model.layers.17.post_attention_layernorm.weight",
|
1173 |
+
"shape": [
|
1174 |
+
2048
|
1175 |
+
],
|
1176 |
+
"dtype": "float32",
|
1177 |
+
"format": "f32-to-bf16",
|
1178 |
+
"nbytes": 4096,
|
1179 |
+
"byteOffset": 12976128
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"name": "model.layers.17.self_attn.qkv_proj.q_weight",
|
1183 |
+
"shape": [
|
1184 |
+
2560,
|
1185 |
+
256
|
1186 |
+
],
|
1187 |
+
"dtype": "uint32",
|
1188 |
+
"format": "f32-to-bf16",
|
1189 |
+
"nbytes": 2621440,
|
1190 |
+
"byteOffset": 12980224
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"name": "model.layers.17.self_attn.qkv_proj.q_scale",
|
1194 |
+
"shape": [
|
1195 |
+
2560,
|
1196 |
+
64
|
1197 |
+
],
|
1198 |
+
"dtype": "float32",
|
1199 |
+
"format": "f32-to-bf16",
|
1200 |
+
"nbytes": 327680,
|
1201 |
+
"byteOffset": 15601664
|
1202 |
+
},
|
1203 |
+
{
|
1204 |
+
"name": "model.layers.17.self_attn.o_proj.q_weight",
|
1205 |
+
"shape": [
|
1206 |
+
2048,
|
1207 |
+
256
|
1208 |
+
],
|
1209 |
+
"dtype": "uint32",
|
1210 |
+
"format": "f32-to-bf16",
|
1211 |
+
"nbytes": 2097152,
|
1212 |
+
"byteOffset": 15929344
|
1213 |
+
},
|
1214 |
+
{
|
1215 |
+
"name": "model.layers.17.self_attn.o_proj.q_scale",
|
1216 |
+
"shape": [
|
1217 |
+
2048,
|
1218 |
+
64
|
1219 |
+
],
|
1220 |
+
"dtype": "float32",
|
1221 |
+
"format": "f32-to-bf16",
|
1222 |
+
"nbytes": 262144,
|
1223 |
+
"byteOffset": 18026496
|
1224 |
+
},
|
1225 |
+
{
|
1226 |
+
"name": "model.layers.18.input_layernorm.weight",
|
1227 |
+
"shape": [
|
1228 |
+
2048
|
1229 |
+
],
|
1230 |
+
"dtype": "float32",
|
1231 |
+
"format": "f32-to-bf16",
|
1232 |
+
"nbytes": 4096,
|
1233 |
+
"byteOffset": 18288640
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"name": "model.layers.18.mlp.down_proj.q_weight",
|
1237 |
+
"shape": [
|
1238 |
+
2048,
|
1239 |
+
704
|
1240 |
+
],
|
1241 |
+
"dtype": "uint32",
|
1242 |
+
"format": "f32-to-bf16",
|
1243 |
+
"nbytes": 5767168,
|
1244 |
+
"byteOffset": 18292736
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"name": "model.layers.18.mlp.down_proj.q_scale",
|
1248 |
+
"shape": [
|
1249 |
+
2048,
|
1250 |
+
176
|
1251 |
+
],
|
1252 |
+
"dtype": "float32",
|
1253 |
+
"format": "f32-to-bf16",
|
1254 |
+
"nbytes": 720896,
|
1255 |
+
"byteOffset": 24059904
|
1256 |
+
}
|
1257 |
+
],
|
1258 |
+
"md5sum": "8a6ef364911a1049b2c0531be0fc15b6"
|
1259 |
+
},
|
1260 |
+
{
|
1261 |
+
"dataPath": "params_shard_12.bin",
|
1262 |
+
"format": "raw-shard",
|
1263 |
+
"nbytes": 24780800,
|
1264 |
+
"records": [
|
1265 |
+
{
|
1266 |
+
"name": "model.layers.18.mlp.gate_up_proj.q_weight",
|
1267 |
+
"shape": [
|
1268 |
+
11264,
|
1269 |
+
256
|
1270 |
+
],
|
1271 |
+
"dtype": "uint32",
|
1272 |
+
"format": "f32-to-bf16",
|
1273 |
+
"nbytes": 11534336,
|
1274 |
+
"byteOffset": 0
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"name": "model.layers.18.mlp.gate_up_proj.q_scale",
|
1278 |
+
"shape": [
|
1279 |
+
11264,
|
1280 |
+
64
|
1281 |
+
],
|
1282 |
+
"dtype": "float32",
|
1283 |
+
"format": "f32-to-bf16",
|
1284 |
+
"nbytes": 1441792,
|
1285 |
+
"byteOffset": 11534336
|
1286 |
+
},
|
1287 |
+
{
|
1288 |
+
"name": "model.layers.18.post_attention_layernorm.weight",
|
1289 |
+
"shape": [
|
1290 |
+
2048
|
1291 |
+
],
|
1292 |
+
"dtype": "float32",
|
1293 |
+
"format": "f32-to-bf16",
|
1294 |
+
"nbytes": 4096,
|
1295 |
+
"byteOffset": 12976128
|
1296 |
+
},
|
1297 |
+
{
|
1298 |
+
"name": "model.layers.18.self_attn.qkv_proj.q_weight",
|
1299 |
+
"shape": [
|
1300 |
+
2560,
|
1301 |
+
256
|
1302 |
+
],
|
1303 |
+
"dtype": "uint32",
|
1304 |
+
"format": "f32-to-bf16",
|
1305 |
+
"nbytes": 2621440,
|
1306 |
+
"byteOffset": 12980224
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"name": "model.layers.18.self_attn.qkv_proj.q_scale",
|
1310 |
+
"shape": [
|
1311 |
+
2560,
|
1312 |
+
64
|
1313 |
+
],
|
1314 |
+
"dtype": "float32",
|
1315 |
+
"format": "f32-to-bf16",
|
1316 |
+
"nbytes": 327680,
|
1317 |
+
"byteOffset": 15601664
|
1318 |
+
},
|
1319 |
+
{
|
1320 |
+
"name": "model.layers.18.self_attn.o_proj.q_weight",
|
1321 |
+
"shape": [
|
1322 |
+
2048,
|
1323 |
+
256
|
1324 |
+
],
|
1325 |
+
"dtype": "uint32",
|
1326 |
+
"format": "f32-to-bf16",
|
1327 |
+
"nbytes": 2097152,
|
1328 |
+
"byteOffset": 15929344
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"name": "model.layers.18.self_attn.o_proj.q_scale",
|
1332 |
+
"shape": [
|
1333 |
+
2048,
|
1334 |
+
64
|
1335 |
+
],
|
1336 |
+
"dtype": "float32",
|
1337 |
+
"format": "f32-to-bf16",
|
1338 |
+
"nbytes": 262144,
|
1339 |
+
"byteOffset": 18026496
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"name": "model.layers.19.input_layernorm.weight",
|
1343 |
+
"shape": [
|
1344 |
+
2048
|
1345 |
+
],
|
1346 |
+
"dtype": "float32",
|
1347 |
+
"format": "f32-to-bf16",
|
1348 |
+
"nbytes": 4096,
|
1349 |
+
"byteOffset": 18288640
|
1350 |
+
},
|
1351 |
+
{
|
1352 |
+
"name": "model.layers.19.mlp.down_proj.q_weight",
|
1353 |
+
"shape": [
|
1354 |
+
2048,
|
1355 |
+
704
|
1356 |
+
],
|
1357 |
+
"dtype": "uint32",
|
1358 |
+
"format": "f32-to-bf16",
|
1359 |
+
"nbytes": 5767168,
|
1360 |
+
"byteOffset": 18292736
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"name": "model.layers.19.mlp.down_proj.q_scale",
|
1364 |
+
"shape": [
|
1365 |
+
2048,
|
1366 |
+
176
|
1367 |
+
],
|
1368 |
+
"dtype": "float32",
|
1369 |
+
"format": "f32-to-bf16",
|
1370 |
+
"nbytes": 720896,
|
1371 |
+
"byteOffset": 24059904
|
1372 |
+
}
|
1373 |
+
],
|
1374 |
+
"md5sum": "13ffdc8591e96c1c5f27090d70144bd0"
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"dataPath": "params_shard_13.bin",
|
1378 |
+
"format": "raw-shard",
|
1379 |
+
"nbytes": 24780800,
|
1380 |
+
"records": [
|
1381 |
+
{
|
1382 |
+
"name": "model.layers.19.mlp.gate_up_proj.q_weight",
|
1383 |
+
"shape": [
|
1384 |
+
11264,
|
1385 |
+
256
|
1386 |
+
],
|
1387 |
+
"dtype": "uint32",
|
1388 |
+
"format": "f32-to-bf16",
|
1389 |
+
"nbytes": 11534336,
|
1390 |
+
"byteOffset": 0
|
1391 |
+
},
|
1392 |
+
{
|
1393 |
+
"name": "model.layers.19.mlp.gate_up_proj.q_scale",
|
1394 |
+
"shape": [
|
1395 |
+
11264,
|
1396 |
+
64
|
1397 |
+
],
|
1398 |
+
"dtype": "float32",
|
1399 |
+
"format": "f32-to-bf16",
|
1400 |
+
"nbytes": 1441792,
|
1401 |
+
"byteOffset": 11534336
|
1402 |
+
},
|
1403 |
+
{
|
1404 |
+
"name": "model.layers.19.post_attention_layernorm.weight",
|
1405 |
+
"shape": [
|
1406 |
+
2048
|
1407 |
+
],
|
1408 |
+
"dtype": "float32",
|
1409 |
+
"format": "f32-to-bf16",
|
1410 |
+
"nbytes": 4096,
|
1411 |
+
"byteOffset": 12976128
|
1412 |
+
},
|
1413 |
+
{
|
1414 |
+
"name": "model.layers.19.self_attn.qkv_proj.q_weight",
|
1415 |
+
"shape": [
|
1416 |
+
2560,
|
1417 |
+
256
|
1418 |
+
],
|
1419 |
+
"dtype": "uint32",
|
1420 |
+
"format": "f32-to-bf16",
|
1421 |
+
"nbytes": 2621440,
|
1422 |
+
"byteOffset": 12980224
|
1423 |
+
},
|
1424 |
+
{
|
1425 |
+
"name": "model.layers.19.self_attn.qkv_proj.q_scale",
|
1426 |
+
"shape": [
|
1427 |
+
2560,
|
1428 |
+
64
|
1429 |
+
],
|
1430 |
+
"dtype": "float32",
|
1431 |
+
"format": "f32-to-bf16",
|
1432 |
+
"nbytes": 327680,
|
1433 |
+
"byteOffset": 15601664
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"name": "model.layers.19.self_attn.o_proj.q_weight",
|
1437 |
+
"shape": [
|
1438 |
+
2048,
|
1439 |
+
256
|
1440 |
+
],
|
1441 |
+
"dtype": "uint32",
|
1442 |
+
"format": "f32-to-bf16",
|
1443 |
+
"nbytes": 2097152,
|
1444 |
+
"byteOffset": 15929344
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"name": "model.layers.19.self_attn.o_proj.q_scale",
|
1448 |
+
"shape": [
|
1449 |
+
2048,
|
1450 |
+
64
|
1451 |
+
],
|
1452 |
+
"dtype": "float32",
|
1453 |
+
"format": "f32-to-bf16",
|
1454 |
+
"nbytes": 262144,
|
1455 |
+
"byteOffset": 18026496
|
1456 |
+
},
|
1457 |
+
{
|
1458 |
+
"name": "model.layers.2.input_layernorm.weight",
|
1459 |
+
"shape": [
|
1460 |
+
2048
|
1461 |
+
],
|
1462 |
+
"dtype": "float32",
|
1463 |
+
"format": "f32-to-bf16",
|
1464 |
+
"nbytes": 4096,
|
1465 |
+
"byteOffset": 18288640
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"name": "model.layers.2.mlp.down_proj.q_weight",
|
1469 |
+
"shape": [
|
1470 |
+
2048,
|
1471 |
+
704
|
1472 |
+
],
|
1473 |
+
"dtype": "uint32",
|
1474 |
+
"format": "f32-to-bf16",
|
1475 |
+
"nbytes": 5767168,
|
1476 |
+
"byteOffset": 18292736
|
1477 |
+
},
|
1478 |
+
{
|
1479 |
+
"name": "model.layers.2.mlp.down_proj.q_scale",
|
1480 |
+
"shape": [
|
1481 |
+
2048,
|
1482 |
+
176
|
1483 |
+
],
|
1484 |
+
"dtype": "float32",
|
1485 |
+
"format": "f32-to-bf16",
|
1486 |
+
"nbytes": 720896,
|
1487 |
+
"byteOffset": 24059904
|
1488 |
+
}
|
1489 |
+
],
|
1490 |
+
"md5sum": "35244475eb557462112a7fa2d3db4dc9"
|
1491 |
+
},
|
1492 |
+
{
|
1493 |
+
"dataPath": "params_shard_14.bin",
|
1494 |
+
"format": "raw-shard",
|
1495 |
+
"nbytes": 24780800,
|
1496 |
+
"records": [
|
1497 |
+
{
|
1498 |
+
"name": "model.layers.2.mlp.gate_up_proj.q_weight",
|
1499 |
+
"shape": [
|
1500 |
+
11264,
|
1501 |
+
256
|
1502 |
+
],
|
1503 |
+
"dtype": "uint32",
|
1504 |
+
"format": "f32-to-bf16",
|
1505 |
+
"nbytes": 11534336,
|
1506 |
+
"byteOffset": 0
|
1507 |
+
},
|
1508 |
+
{
|
1509 |
+
"name": "model.layers.2.mlp.gate_up_proj.q_scale",
|
1510 |
+
"shape": [
|
1511 |
+
11264,
|
1512 |
+
64
|
1513 |
+
],
|
1514 |
+
"dtype": "float32",
|
1515 |
+
"format": "f32-to-bf16",
|
1516 |
+
"nbytes": 1441792,
|
1517 |
+
"byteOffset": 11534336
|
1518 |
+
},
|
1519 |
+
{
|
1520 |
+
"name": "model.layers.2.post_attention_layernorm.weight",
|
1521 |
+
"shape": [
|
1522 |
+
2048
|
1523 |
+
],
|
1524 |
+
"dtype": "float32",
|
1525 |
+
"format": "f32-to-bf16",
|
1526 |
+
"nbytes": 4096,
|
1527 |
+
"byteOffset": 12976128
|
1528 |
+
},
|
1529 |
+
{
|
1530 |
+
"name": "model.layers.2.self_attn.qkv_proj.q_weight",
|
1531 |
+
"shape": [
|
1532 |
+
2560,
|
1533 |
+
256
|
1534 |
+
],
|
1535 |
+
"dtype": "uint32",
|
1536 |
+
"format": "f32-to-bf16",
|
1537 |
+
"nbytes": 2621440,
|
1538 |
+
"byteOffset": 12980224
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"name": "model.layers.2.self_attn.qkv_proj.q_scale",
|
1542 |
+
"shape": [
|
1543 |
+
2560,
|
1544 |
+
64
|
1545 |
+
],
|
1546 |
+
"dtype": "float32",
|
1547 |
+
"format": "f32-to-bf16",
|
1548 |
+
"nbytes": 327680,
|
1549 |
+
"byteOffset": 15601664
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"name": "model.layers.2.self_attn.o_proj.q_weight",
|
1553 |
+
"shape": [
|
1554 |
+
2048,
|
1555 |
+
256
|
1556 |
+
],
|
1557 |
+
"dtype": "uint32",
|
1558 |
+
"format": "f32-to-bf16",
|
1559 |
+
"nbytes": 2097152,
|
1560 |
+
"byteOffset": 15929344
|
1561 |
+
},
|
1562 |
+
{
|
1563 |
+
"name": "model.layers.2.self_attn.o_proj.q_scale",
|
1564 |
+
"shape": [
|
1565 |
+
2048,
|
1566 |
+
64
|
1567 |
+
],
|
1568 |
+
"dtype": "float32",
|
1569 |
+
"format": "f32-to-bf16",
|
1570 |
+
"nbytes": 262144,
|
1571 |
+
"byteOffset": 18026496
|
1572 |
+
},
|
1573 |
+
{
|
1574 |
+
"name": "model.layers.20.input_layernorm.weight",
|
1575 |
+
"shape": [
|
1576 |
+
2048
|
1577 |
+
],
|
1578 |
+
"dtype": "float32",
|
1579 |
+
"format": "f32-to-bf16",
|
1580 |
+
"nbytes": 4096,
|
1581 |
+
"byteOffset": 18288640
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"name": "model.layers.20.mlp.down_proj.q_weight",
|
1585 |
+
"shape": [
|
1586 |
+
2048,
|
1587 |
+
704
|
1588 |
+
],
|
1589 |
+
"dtype": "uint32",
|
1590 |
+
"format": "f32-to-bf16",
|
1591 |
+
"nbytes": 5767168,
|
1592 |
+
"byteOffset": 18292736
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"name": "model.layers.20.mlp.down_proj.q_scale",
|
1596 |
+
"shape": [
|
1597 |
+
2048,
|
1598 |
+
176
|
1599 |
+
],
|
1600 |
+
"dtype": "float32",
|
1601 |
+
"format": "f32-to-bf16",
|
1602 |
+
"nbytes": 720896,
|
1603 |
+
"byteOffset": 24059904
|
1604 |
+
}
|
1605 |
+
],
|
1606 |
+
"md5sum": "f87ee6617b7866df37b8c66980d7144f"
|
1607 |
+
},
|
1608 |
+
{
|
1609 |
+
"dataPath": "params_shard_15.bin",
|
1610 |
+
"format": "raw-shard",
|
1611 |
+
"nbytes": 24780800,
|
1612 |
+
"records": [
|
1613 |
+
{
|
1614 |
+
"name": "model.layers.20.mlp.gate_up_proj.q_weight",
|
1615 |
+
"shape": [
|
1616 |
+
11264,
|
1617 |
+
256
|
1618 |
+
],
|
1619 |
+
"dtype": "uint32",
|
1620 |
+
"format": "f32-to-bf16",
|
1621 |
+
"nbytes": 11534336,
|
1622 |
+
"byteOffset": 0
|
1623 |
+
},
|
1624 |
+
{
|
1625 |
+
"name": "model.layers.20.mlp.gate_up_proj.q_scale",
|
1626 |
+
"shape": [
|
1627 |
+
11264,
|
1628 |
+
64
|
1629 |
+
],
|
1630 |
+
"dtype": "float32",
|
1631 |
+
"format": "f32-to-bf16",
|
1632 |
+
"nbytes": 1441792,
|
1633 |
+
"byteOffset": 11534336
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"name": "model.layers.20.post_attention_layernorm.weight",
|
1637 |
+
"shape": [
|
1638 |
+
2048
|
1639 |
+
],
|
1640 |
+
"dtype": "float32",
|
1641 |
+
"format": "f32-to-bf16",
|
1642 |
+
"nbytes": 4096,
|
1643 |
+
"byteOffset": 12976128
|
1644 |
+
},
|
1645 |
+
{
|
1646 |
+
"name": "model.layers.20.self_attn.qkv_proj.q_weight",
|
1647 |
+
"shape": [
|
1648 |
+
2560,
|
1649 |
+
256
|
1650 |
+
],
|
1651 |
+
"dtype": "uint32",
|
1652 |
+
"format": "f32-to-bf16",
|
1653 |
+
"nbytes": 2621440,
|
1654 |
+
"byteOffset": 12980224
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"name": "model.layers.20.self_attn.qkv_proj.q_scale",
|
1658 |
+
"shape": [
|
1659 |
+
2560,
|
1660 |
+
64
|
1661 |
+
],
|
1662 |
+
"dtype": "float32",
|
1663 |
+
"format": "f32-to-bf16",
|
1664 |
+
"nbytes": 327680,
|
1665 |
+
"byteOffset": 15601664
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"name": "model.layers.20.self_attn.o_proj.q_weight",
|
1669 |
+
"shape": [
|
1670 |
+
2048,
|
1671 |
+
256
|
1672 |
+
],
|
1673 |
+
"dtype": "uint32",
|
1674 |
+
"format": "f32-to-bf16",
|
1675 |
+
"nbytes": 2097152,
|
1676 |
+
"byteOffset": 15929344
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"name": "model.layers.20.self_attn.o_proj.q_scale",
|
1680 |
+
"shape": [
|
1681 |
+
2048,
|
1682 |
+
64
|
1683 |
+
],
|
1684 |
+
"dtype": "float32",
|
1685 |
+
"format": "f32-to-bf16",
|
1686 |
+
"nbytes": 262144,
|
1687 |
+
"byteOffset": 18026496
|
1688 |
+
},
|
1689 |
+
{
|
1690 |
+
"name": "model.layers.21.input_layernorm.weight",
|
1691 |
+
"shape": [
|
1692 |
+
2048
|
1693 |
+
],
|
1694 |
+
"dtype": "float32",
|
1695 |
+
"format": "f32-to-bf16",
|
1696 |
+
"nbytes": 4096,
|
1697 |
+
"byteOffset": 18288640
|
1698 |
+
},
|
1699 |
+
{
|
1700 |
+
"name": "model.layers.21.mlp.down_proj.q_weight",
|
1701 |
+
"shape": [
|
1702 |
+
2048,
|
1703 |
+
704
|
1704 |
+
],
|
1705 |
+
"dtype": "uint32",
|
1706 |
+
"format": "f32-to-bf16",
|
1707 |
+
"nbytes": 5767168,
|
1708 |
+
"byteOffset": 18292736
|
1709 |
+
},
|
1710 |
+
{
|
1711 |
+
"name": "model.layers.21.mlp.down_proj.q_scale",
|
1712 |
+
"shape": [
|
1713 |
+
2048,
|
1714 |
+
176
|
1715 |
+
],
|
1716 |
+
"dtype": "float32",
|
1717 |
+
"format": "f32-to-bf16",
|
1718 |
+
"nbytes": 720896,
|
1719 |
+
"byteOffset": 24059904
|
1720 |
+
}
|
1721 |
+
],
|
1722 |
+
"md5sum": "b1864fe4abf3244367e8fedd502eb8ca"
|
1723 |
+
},
|
1724 |
+
{
|
1725 |
+
"dataPath": "params_shard_16.bin",
|
1726 |
+
"format": "raw-shard",
|
1727 |
+
"nbytes": 24780800,
|
1728 |
+
"records": [
|
1729 |
+
{
|
1730 |
+
"name": "model.layers.21.mlp.gate_up_proj.q_weight",
|
1731 |
+
"shape": [
|
1732 |
+
11264,
|
1733 |
+
256
|
1734 |
+
],
|
1735 |
+
"dtype": "uint32",
|
1736 |
+
"format": "f32-to-bf16",
|
1737 |
+
"nbytes": 11534336,
|
1738 |
+
"byteOffset": 0
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"name": "model.layers.21.mlp.gate_up_proj.q_scale",
|
1742 |
+
"shape": [
|
1743 |
+
11264,
|
1744 |
+
64
|
1745 |
+
],
|
1746 |
+
"dtype": "float32",
|
1747 |
+
"format": "f32-to-bf16",
|
1748 |
+
"nbytes": 1441792,
|
1749 |
+
"byteOffset": 11534336
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"name": "model.layers.21.post_attention_layernorm.weight",
|
1753 |
+
"shape": [
|
1754 |
+
2048
|
1755 |
+
],
|
1756 |
+
"dtype": "float32",
|
1757 |
+
"format": "f32-to-bf16",
|
1758 |
+
"nbytes": 4096,
|
1759 |
+
"byteOffset": 12976128
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"name": "model.layers.21.self_attn.qkv_proj.q_weight",
|
1763 |
+
"shape": [
|
1764 |
+
2560,
|
1765 |
+
256
|
1766 |
+
],
|
1767 |
+
"dtype": "uint32",
|
1768 |
+
"format": "f32-to-bf16",
|
1769 |
+
"nbytes": 2621440,
|
1770 |
+
"byteOffset": 12980224
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"name": "model.layers.21.self_attn.qkv_proj.q_scale",
|
1774 |
+
"shape": [
|
1775 |
+
2560,
|
1776 |
+
64
|
1777 |
+
],
|
1778 |
+
"dtype": "float32",
|
1779 |
+
"format": "f32-to-bf16",
|
1780 |
+
"nbytes": 327680,
|
1781 |
+
"byteOffset": 15601664
|
1782 |
+
},
|
1783 |
+
{
|
1784 |
+
"name": "model.layers.21.self_attn.o_proj.q_weight",
|
1785 |
+
"shape": [
|
1786 |
+
2048,
|
1787 |
+
256
|
1788 |
+
],
|
1789 |
+
"dtype": "uint32",
|
1790 |
+
"format": "f32-to-bf16",
|
1791 |
+
"nbytes": 2097152,
|
1792 |
+
"byteOffset": 15929344
|
1793 |
+
},
|
1794 |
+
{
|
1795 |
+
"name": "model.layers.21.self_attn.o_proj.q_scale",
|
1796 |
+
"shape": [
|
1797 |
+
2048,
|
1798 |
+
64
|
1799 |
+
],
|
1800 |
+
"dtype": "float32",
|
1801 |
+
"format": "f32-to-bf16",
|
1802 |
+
"nbytes": 262144,
|
1803 |
+
"byteOffset": 18026496
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"name": "model.layers.3.input_layernorm.weight",
|
1807 |
+
"shape": [
|
1808 |
+
2048
|
1809 |
+
],
|
1810 |
+
"dtype": "float32",
|
1811 |
+
"format": "f32-to-bf16",
|
1812 |
+
"nbytes": 4096,
|
1813 |
+
"byteOffset": 18288640
|
1814 |
+
},
|
1815 |
+
{
|
1816 |
+
"name": "model.layers.3.mlp.down_proj.q_weight",
|
1817 |
+
"shape": [
|
1818 |
+
2048,
|
1819 |
+
704
|
1820 |
+
],
|
1821 |
+
"dtype": "uint32",
|
1822 |
+
"format": "f32-to-bf16",
|
1823 |
+
"nbytes": 5767168,
|
1824 |
+
"byteOffset": 18292736
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"name": "model.layers.3.mlp.down_proj.q_scale",
|
1828 |
+
"shape": [
|
1829 |
+
2048,
|
1830 |
+
176
|
1831 |
+
],
|
1832 |
+
"dtype": "float32",
|
1833 |
+
"format": "f32-to-bf16",
|
1834 |
+
"nbytes": 720896,
|
1835 |
+
"byteOffset": 24059904
|
1836 |
+
}
|
1837 |
+
],
|
1838 |
+
"md5sum": "505cab1c1b2228b83fd2c1d2240f0959"
|
1839 |
+
},
|
1840 |
+
{
|
1841 |
+
"dataPath": "params_shard_17.bin",
|
1842 |
+
"format": "raw-shard",
|
1843 |
+
"nbytes": 24780800,
|
1844 |
+
"records": [
|
1845 |
+
{
|
1846 |
+
"name": "model.layers.3.mlp.gate_up_proj.q_weight",
|
1847 |
+
"shape": [
|
1848 |
+
11264,
|
1849 |
+
256
|
1850 |
+
],
|
1851 |
+
"dtype": "uint32",
|
1852 |
+
"format": "f32-to-bf16",
|
1853 |
+
"nbytes": 11534336,
|
1854 |
+
"byteOffset": 0
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"name": "model.layers.3.mlp.gate_up_proj.q_scale",
|
1858 |
+
"shape": [
|
1859 |
+
11264,
|
1860 |
+
64
|
1861 |
+
],
|
1862 |
+
"dtype": "float32",
|
1863 |
+
"format": "f32-to-bf16",
|
1864 |
+
"nbytes": 1441792,
|
1865 |
+
"byteOffset": 11534336
|
1866 |
+
},
|
1867 |
+
{
|
1868 |
+
"name": "model.layers.3.post_attention_layernorm.weight",
|
1869 |
+
"shape": [
|
1870 |
+
2048
|
1871 |
+
],
|
1872 |
+
"dtype": "float32",
|
1873 |
+
"format": "f32-to-bf16",
|
1874 |
+
"nbytes": 4096,
|
1875 |
+
"byteOffset": 12976128
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"name": "model.layers.3.self_attn.qkv_proj.q_weight",
|
1879 |
+
"shape": [
|
1880 |
+
2560,
|
1881 |
+
256
|
1882 |
+
],
|
1883 |
+
"dtype": "uint32",
|
1884 |
+
"format": "f32-to-bf16",
|
1885 |
+
"nbytes": 2621440,
|
1886 |
+
"byteOffset": 12980224
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"name": "model.layers.3.self_attn.qkv_proj.q_scale",
|
1890 |
+
"shape": [
|
1891 |
+
2560,
|
1892 |
+
64
|
1893 |
+
],
|
1894 |
+
"dtype": "float32",
|
1895 |
+
"format": "f32-to-bf16",
|
1896 |
+
"nbytes": 327680,
|
1897 |
+
"byteOffset": 15601664
|
1898 |
+
},
|
1899 |
+
{
|
1900 |
+
"name": "model.layers.3.self_attn.o_proj.q_weight",
|
1901 |
+
"shape": [
|
1902 |
+
2048,
|
1903 |
+
256
|
1904 |
+
],
|
1905 |
+
"dtype": "uint32",
|
1906 |
+
"format": "f32-to-bf16",
|
1907 |
+
"nbytes": 2097152,
|
1908 |
+
"byteOffset": 15929344
|
1909 |
+
},
|
1910 |
+
{
|
1911 |
+
"name": "model.layers.3.self_attn.o_proj.q_scale",
|
1912 |
+
"shape": [
|
1913 |
+
2048,
|
1914 |
+
64
|
1915 |
+
],
|
1916 |
+
"dtype": "float32",
|
1917 |
+
"format": "f32-to-bf16",
|
1918 |
+
"nbytes": 262144,
|
1919 |
+
"byteOffset": 18026496
|
1920 |
+
},
|
1921 |
+
{
|
1922 |
+
"name": "model.layers.4.input_layernorm.weight",
|
1923 |
+
"shape": [
|
1924 |
+
2048
|
1925 |
+
],
|
1926 |
+
"dtype": "float32",
|
1927 |
+
"format": "f32-to-bf16",
|
1928 |
+
"nbytes": 4096,
|
1929 |
+
"byteOffset": 18288640
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"name": "model.layers.4.mlp.down_proj.q_weight",
|
1933 |
+
"shape": [
|
1934 |
+
2048,
|
1935 |
+
704
|
1936 |
+
],
|
1937 |
+
"dtype": "uint32",
|
1938 |
+
"format": "f32-to-bf16",
|
1939 |
+
"nbytes": 5767168,
|
1940 |
+
"byteOffset": 18292736
|
1941 |
+
},
|
1942 |
+
{
|
1943 |
+
"name": "model.layers.4.mlp.down_proj.q_scale",
|
1944 |
+
"shape": [
|
1945 |
+
2048,
|
1946 |
+
176
|
1947 |
+
],
|
1948 |
+
"dtype": "float32",
|
1949 |
+
"format": "f32-to-bf16",
|
1950 |
+
"nbytes": 720896,
|
1951 |
+
"byteOffset": 24059904
|
1952 |
+
}
|
1953 |
+
],
|
1954 |
+
"md5sum": "a798beddbb6ccf6e8b76b51ae087c28e"
|
1955 |
+
},
|
1956 |
+
{
|
1957 |
+
"dataPath": "params_shard_18.bin",
|
1958 |
+
"format": "raw-shard",
|
1959 |
+
"nbytes": 24780800,
|
1960 |
+
"records": [
|
1961 |
+
{
|
1962 |
+
"name": "model.layers.4.mlp.gate_up_proj.q_weight",
|
1963 |
+
"shape": [
|
1964 |
+
11264,
|
1965 |
+
256
|
1966 |
+
],
|
1967 |
+
"dtype": "uint32",
|
1968 |
+
"format": "f32-to-bf16",
|
1969 |
+
"nbytes": 11534336,
|
1970 |
+
"byteOffset": 0
|
1971 |
+
},
|
1972 |
+
{
|
1973 |
+
"name": "model.layers.4.mlp.gate_up_proj.q_scale",
|
1974 |
+
"shape": [
|
1975 |
+
11264,
|
1976 |
+
64
|
1977 |
+
],
|
1978 |
+
"dtype": "float32",
|
1979 |
+
"format": "f32-to-bf16",
|
1980 |
+
"nbytes": 1441792,
|
1981 |
+
"byteOffset": 11534336
|
1982 |
+
},
|
1983 |
+
{
|
1984 |
+
"name": "model.layers.4.post_attention_layernorm.weight",
|
1985 |
+
"shape": [
|
1986 |
+
2048
|
1987 |
+
],
|
1988 |
+
"dtype": "float32",
|
1989 |
+
"format": "f32-to-bf16",
|
1990 |
+
"nbytes": 4096,
|
1991 |
+
"byteOffset": 12976128
|
1992 |
+
},
|
1993 |
+
{
|
1994 |
+
"name": "model.layers.4.self_attn.qkv_proj.q_weight",
|
1995 |
+
"shape": [
|
1996 |
+
2560,
|
1997 |
+
256
|
1998 |
+
],
|
1999 |
+
"dtype": "uint32",
|
2000 |
+
"format": "f32-to-bf16",
|
2001 |
+
"nbytes": 2621440,
|
2002 |
+
"byteOffset": 12980224
|
2003 |
+
},
|
2004 |
+
{
|
2005 |
+
"name": "model.layers.4.self_attn.qkv_proj.q_scale",
|
2006 |
+
"shape": [
|
2007 |
+
2560,
|
2008 |
+
64
|
2009 |
+
],
|
2010 |
+
"dtype": "float32",
|
2011 |
+
"format": "f32-to-bf16",
|
2012 |
+
"nbytes": 327680,
|
2013 |
+
"byteOffset": 15601664
|
2014 |
+
},
|
2015 |
+
{
|
2016 |
+
"name": "model.layers.4.self_attn.o_proj.q_weight",
|
2017 |
+
"shape": [
|
2018 |
+
2048,
|
2019 |
+
256
|
2020 |
+
],
|
2021 |
+
"dtype": "uint32",
|
2022 |
+
"format": "f32-to-bf16",
|
2023 |
+
"nbytes": 2097152,
|
2024 |
+
"byteOffset": 15929344
|
2025 |
+
},
|
2026 |
+
{
|
2027 |
+
"name": "model.layers.4.self_attn.o_proj.q_scale",
|
2028 |
+
"shape": [
|
2029 |
+
2048,
|
2030 |
+
64
|
2031 |
+
],
|
2032 |
+
"dtype": "float32",
|
2033 |
+
"format": "f32-to-bf16",
|
2034 |
+
"nbytes": 262144,
|
2035 |
+
"byteOffset": 18026496
|
2036 |
+
},
|
2037 |
+
{
|
2038 |
+
"name": "model.layers.5.input_layernorm.weight",
|
2039 |
+
"shape": [
|
2040 |
+
2048
|
2041 |
+
],
|
2042 |
+
"dtype": "float32",
|
2043 |
+
"format": "f32-to-bf16",
|
2044 |
+
"nbytes": 4096,
|
2045 |
+
"byteOffset": 18288640
|
2046 |
+
},
|
2047 |
+
{
|
2048 |
+
"name": "model.layers.5.mlp.down_proj.q_weight",
|
2049 |
+
"shape": [
|
2050 |
+
2048,
|
2051 |
+
704
|
2052 |
+
],
|
2053 |
+
"dtype": "uint32",
|
2054 |
+
"format": "f32-to-bf16",
|
2055 |
+
"nbytes": 5767168,
|
2056 |
+
"byteOffset": 18292736
|
2057 |
+
},
|
2058 |
+
{
|
2059 |
+
"name": "model.layers.5.mlp.down_proj.q_scale",
|
2060 |
+
"shape": [
|
2061 |
+
2048,
|
2062 |
+
176
|
2063 |
+
],
|
2064 |
+
"dtype": "float32",
|
2065 |
+
"format": "f32-to-bf16",
|
2066 |
+
"nbytes": 720896,
|
2067 |
+
"byteOffset": 24059904
|
2068 |
+
}
|
2069 |
+
],
|
2070 |
+
"md5sum": "4fc462bba2bb7ed3004b13350e52ce3f"
|
2071 |
+
},
|
2072 |
+
{
|
2073 |
+
"dataPath": "params_shard_19.bin",
|
2074 |
+
"format": "raw-shard",
|
2075 |
+
"nbytes": 24780800,
|
2076 |
+
"records": [
|
2077 |
+
{
|
2078 |
+
"name": "model.layers.5.mlp.gate_up_proj.q_weight",
|
2079 |
+
"shape": [
|
2080 |
+
11264,
|
2081 |
+
256
|
2082 |
+
],
|
2083 |
+
"dtype": "uint32",
|
2084 |
+
"format": "f32-to-bf16",
|
2085 |
+
"nbytes": 11534336,
|
2086 |
+
"byteOffset": 0
|
2087 |
+
},
|
2088 |
+
{
|
2089 |
+
"name": "model.layers.5.mlp.gate_up_proj.q_scale",
|
2090 |
+
"shape": [
|
2091 |
+
11264,
|
2092 |
+
64
|
2093 |
+
],
|
2094 |
+
"dtype": "float32",
|
2095 |
+
"format": "f32-to-bf16",
|
2096 |
+
"nbytes": 1441792,
|
2097 |
+
"byteOffset": 11534336
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"name": "model.layers.5.post_attention_layernorm.weight",
|
2101 |
+
"shape": [
|
2102 |
+
2048
|
2103 |
+
],
|
2104 |
+
"dtype": "float32",
|
2105 |
+
"format": "f32-to-bf16",
|
2106 |
+
"nbytes": 4096,
|
2107 |
+
"byteOffset": 12976128
|
2108 |
+
},
|
2109 |
+
{
|
2110 |
+
"name": "model.layers.5.self_attn.qkv_proj.q_weight",
|
2111 |
+
"shape": [
|
2112 |
+
2560,
|
2113 |
+
256
|
2114 |
+
],
|
2115 |
+
"dtype": "uint32",
|
2116 |
+
"format": "f32-to-bf16",
|
2117 |
+
"nbytes": 2621440,
|
2118 |
+
"byteOffset": 12980224
|
2119 |
+
},
|
2120 |
+
{
|
2121 |
+
"name": "model.layers.5.self_attn.qkv_proj.q_scale",
|
2122 |
+
"shape": [
|
2123 |
+
2560,
|
2124 |
+
64
|
2125 |
+
],
|
2126 |
+
"dtype": "float32",
|
2127 |
+
"format": "f32-to-bf16",
|
2128 |
+
"nbytes": 327680,
|
2129 |
+
"byteOffset": 15601664
|
2130 |
+
},
|
2131 |
+
{
|
2132 |
+
"name": "model.layers.5.self_attn.o_proj.q_weight",
|
2133 |
+
"shape": [
|
2134 |
+
2048,
|
2135 |
+
256
|
2136 |
+
],
|
2137 |
+
"dtype": "uint32",
|
2138 |
+
"format": "f32-to-bf16",
|
2139 |
+
"nbytes": 2097152,
|
2140 |
+
"byteOffset": 15929344
|
2141 |
+
},
|
2142 |
+
{
|
2143 |
+
"name": "model.layers.5.self_attn.o_proj.q_scale",
|
2144 |
+
"shape": [
|
2145 |
+
2048,
|
2146 |
+
64
|
2147 |
+
],
|
2148 |
+
"dtype": "float32",
|
2149 |
+
"format": "f32-to-bf16",
|
2150 |
+
"nbytes": 262144,
|
2151 |
+
"byteOffset": 18026496
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"name": "model.layers.6.input_layernorm.weight",
|
2155 |
+
"shape": [
|
2156 |
+
2048
|
2157 |
+
],
|
2158 |
+
"dtype": "float32",
|
2159 |
+
"format": "f32-to-bf16",
|
2160 |
+
"nbytes": 4096,
|
2161 |
+
"byteOffset": 18288640
|
2162 |
+
},
|
2163 |
+
{
|
2164 |
+
"name": "model.layers.6.mlp.down_proj.q_weight",
|
2165 |
+
"shape": [
|
2166 |
+
2048,
|
2167 |
+
704
|
2168 |
+
],
|
2169 |
+
"dtype": "uint32",
|
2170 |
+
"format": "f32-to-bf16",
|
2171 |
+
"nbytes": 5767168,
|
2172 |
+
"byteOffset": 18292736
|
2173 |
+
},
|
2174 |
+
{
|
2175 |
+
"name": "model.layers.6.mlp.down_proj.q_scale",
|
2176 |
+
"shape": [
|
2177 |
+
2048,
|
2178 |
+
176
|
2179 |
+
],
|
2180 |
+
"dtype": "float32",
|
2181 |
+
"format": "f32-to-bf16",
|
2182 |
+
"nbytes": 720896,
|
2183 |
+
"byteOffset": 24059904
|
2184 |
+
}
|
2185 |
+
],
|
2186 |
+
"md5sum": "6f0b3e5f9da341272077d653a0983dfe"
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"dataPath": "params_shard_20.bin",
|
2190 |
+
"format": "raw-shard",
|
2191 |
+
"nbytes": 24780800,
|
2192 |
+
"records": [
|
2193 |
+
{
|
2194 |
+
"name": "model.layers.6.mlp.gate_up_proj.q_weight",
|
2195 |
+
"shape": [
|
2196 |
+
11264,
|
2197 |
+
256
|
2198 |
+
],
|
2199 |
+
"dtype": "uint32",
|
2200 |
+
"format": "f32-to-bf16",
|
2201 |
+
"nbytes": 11534336,
|
2202 |
+
"byteOffset": 0
|
2203 |
+
},
|
2204 |
+
{
|
2205 |
+
"name": "model.layers.6.mlp.gate_up_proj.q_scale",
|
2206 |
+
"shape": [
|
2207 |
+
11264,
|
2208 |
+
64
|
2209 |
+
],
|
2210 |
+
"dtype": "float32",
|
2211 |
+
"format": "f32-to-bf16",
|
2212 |
+
"nbytes": 1441792,
|
2213 |
+
"byteOffset": 11534336
|
2214 |
+
},
|
2215 |
+
{
|
2216 |
+
"name": "model.layers.6.post_attention_layernorm.weight",
|
2217 |
+
"shape": [
|
2218 |
+
2048
|
2219 |
+
],
|
2220 |
+
"dtype": "float32",
|
2221 |
+
"format": "f32-to-bf16",
|
2222 |
+
"nbytes": 4096,
|
2223 |
+
"byteOffset": 12976128
|
2224 |
+
},
|
2225 |
+
{
|
2226 |
+
"name": "model.layers.6.self_attn.qkv_proj.q_weight",
|
2227 |
+
"shape": [
|
2228 |
+
2560,
|
2229 |
+
256
|
2230 |
+
],
|
2231 |
+
"dtype": "uint32",
|
2232 |
+
"format": "f32-to-bf16",
|
2233 |
+
"nbytes": 2621440,
|
2234 |
+
"byteOffset": 12980224
|
2235 |
+
},
|
2236 |
+
{
|
2237 |
+
"name": "model.layers.6.self_attn.qkv_proj.q_scale",
|
2238 |
+
"shape": [
|
2239 |
+
2560,
|
2240 |
+
64
|
2241 |
+
],
|
2242 |
+
"dtype": "float32",
|
2243 |
+
"format": "f32-to-bf16",
|
2244 |
+
"nbytes": 327680,
|
2245 |
+
"byteOffset": 15601664
|
2246 |
+
},
|
2247 |
+
{
|
2248 |
+
"name": "model.layers.6.self_attn.o_proj.q_weight",
|
2249 |
+
"shape": [
|
2250 |
+
2048,
|
2251 |
+
256
|
2252 |
+
],
|
2253 |
+
"dtype": "uint32",
|
2254 |
+
"format": "f32-to-bf16",
|
2255 |
+
"nbytes": 2097152,
|
2256 |
+
"byteOffset": 15929344
|
2257 |
+
},
|
2258 |
+
{
|
2259 |
+
"name": "model.layers.6.self_attn.o_proj.q_scale",
|
2260 |
+
"shape": [
|
2261 |
+
2048,
|
2262 |
+
64
|
2263 |
+
],
|
2264 |
+
"dtype": "float32",
|
2265 |
+
"format": "f32-to-bf16",
|
2266 |
+
"nbytes": 262144,
|
2267 |
+
"byteOffset": 18026496
|
2268 |
+
},
|
2269 |
+
{
|
2270 |
+
"name": "model.layers.7.input_layernorm.weight",
|
2271 |
+
"shape": [
|
2272 |
+
2048
|
2273 |
+
],
|
2274 |
+
"dtype": "float32",
|
2275 |
+
"format": "f32-to-bf16",
|
2276 |
+
"nbytes": 4096,
|
2277 |
+
"byteOffset": 18288640
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"name": "model.layers.7.mlp.down_proj.q_weight",
|
2281 |
+
"shape": [
|
2282 |
+
2048,
|
2283 |
+
704
|
2284 |
+
],
|
2285 |
+
"dtype": "uint32",
|
2286 |
+
"format": "f32-to-bf16",
|
2287 |
+
"nbytes": 5767168,
|
2288 |
+
"byteOffset": 18292736
|
2289 |
+
},
|
2290 |
+
{
|
2291 |
+
"name": "model.layers.7.mlp.down_proj.q_scale",
|
2292 |
+
"shape": [
|
2293 |
+
2048,
|
2294 |
+
176
|
2295 |
+
],
|
2296 |
+
"dtype": "float32",
|
2297 |
+
"format": "f32-to-bf16",
|
2298 |
+
"nbytes": 720896,
|
2299 |
+
"byteOffset": 24059904
|
2300 |
+
}
|
2301 |
+
],
|
2302 |
+
"md5sum": "686b2f5cffad40c9ede9515e7d23237e"
|
2303 |
+
},
|
2304 |
+
{
|
2305 |
+
"dataPath": "params_shard_21.bin",
|
2306 |
+
"format": "raw-shard",
|
2307 |
+
"nbytes": 24780800,
|
2308 |
+
"records": [
|
2309 |
+
{
|
2310 |
+
"name": "model.layers.7.mlp.gate_up_proj.q_weight",
|
2311 |
+
"shape": [
|
2312 |
+
11264,
|
2313 |
+
256
|
2314 |
+
],
|
2315 |
+
"dtype": "uint32",
|
2316 |
+
"format": "f32-to-bf16",
|
2317 |
+
"nbytes": 11534336,
|
2318 |
+
"byteOffset": 0
|
2319 |
+
},
|
2320 |
+
{
|
2321 |
+
"name": "model.layers.7.mlp.gate_up_proj.q_scale",
|
2322 |
+
"shape": [
|
2323 |
+
11264,
|
2324 |
+
64
|
2325 |
+
],
|
2326 |
+
"dtype": "float32",
|
2327 |
+
"format": "f32-to-bf16",
|
2328 |
+
"nbytes": 1441792,
|
2329 |
+
"byteOffset": 11534336
|
2330 |
+
},
|
2331 |
+
{
|
2332 |
+
"name": "model.layers.7.post_attention_layernorm.weight",
|
2333 |
+
"shape": [
|
2334 |
+
2048
|
2335 |
+
],
|
2336 |
+
"dtype": "float32",
|
2337 |
+
"format": "f32-to-bf16",
|
2338 |
+
"nbytes": 4096,
|
2339 |
+
"byteOffset": 12976128
|
2340 |
+
},
|
2341 |
+
{
|
2342 |
+
"name": "model.layers.7.self_attn.qkv_proj.q_weight",
|
2343 |
+
"shape": [
|
2344 |
+
2560,
|
2345 |
+
256
|
2346 |
+
],
|
2347 |
+
"dtype": "uint32",
|
2348 |
+
"format": "f32-to-bf16",
|
2349 |
+
"nbytes": 2621440,
|
2350 |
+
"byteOffset": 12980224
|
2351 |
+
},
|
2352 |
+
{
|
2353 |
+
"name": "model.layers.7.self_attn.qkv_proj.q_scale",
|
2354 |
+
"shape": [
|
2355 |
+
2560,
|
2356 |
+
64
|
2357 |
+
],
|
2358 |
+
"dtype": "float32",
|
2359 |
+
"format": "f32-to-bf16",
|
2360 |
+
"nbytes": 327680,
|
2361 |
+
"byteOffset": 15601664
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"name": "model.layers.7.self_attn.o_proj.q_weight",
|
2365 |
+
"shape": [
|
2366 |
+
2048,
|
2367 |
+
256
|
2368 |
+
],
|
2369 |
+
"dtype": "uint32",
|
2370 |
+
"format": "f32-to-bf16",
|
2371 |
+
"nbytes": 2097152,
|
2372 |
+
"byteOffset": 15929344
|
2373 |
+
},
|
2374 |
+
{
|
2375 |
+
"name": "model.layers.7.self_attn.o_proj.q_scale",
|
2376 |
+
"shape": [
|
2377 |
+
2048,
|
2378 |
+
64
|
2379 |
+
],
|
2380 |
+
"dtype": "float32",
|
2381 |
+
"format": "f32-to-bf16",
|
2382 |
+
"nbytes": 262144,
|
2383 |
+
"byteOffset": 18026496
|
2384 |
+
},
|
2385 |
+
{
|
2386 |
+
"name": "model.layers.8.input_layernorm.weight",
|
2387 |
+
"shape": [
|
2388 |
+
2048
|
2389 |
+
],
|
2390 |
+
"dtype": "float32",
|
2391 |
+
"format": "f32-to-bf16",
|
2392 |
+
"nbytes": 4096,
|
2393 |
+
"byteOffset": 18288640
|
2394 |
+
},
|
2395 |
+
{
|
2396 |
+
"name": "model.layers.8.mlp.down_proj.q_weight",
|
2397 |
+
"shape": [
|
2398 |
+
2048,
|
2399 |
+
704
|
2400 |
+
],
|
2401 |
+
"dtype": "uint32",
|
2402 |
+
"format": "f32-to-bf16",
|
2403 |
+
"nbytes": 5767168,
|
2404 |
+
"byteOffset": 18292736
|
2405 |
+
},
|
2406 |
+
{
|
2407 |
+
"name": "model.layers.8.mlp.down_proj.q_scale",
|
2408 |
+
"shape": [
|
2409 |
+
2048,
|
2410 |
+
176
|
2411 |
+
],
|
2412 |
+
"dtype": "float32",
|
2413 |
+
"format": "f32-to-bf16",
|
2414 |
+
"nbytes": 720896,
|
2415 |
+
"byteOffset": 24059904
|
2416 |
+
}
|
2417 |
+
],
|
2418 |
+
"md5sum": "686faea393d9673351ea835a31d58d1c"
|
2419 |
+
},
|
2420 |
+
{
|
2421 |
+
"dataPath": "params_shard_22.bin",
|
2422 |
+
"format": "raw-shard",
|
2423 |
+
"nbytes": 24780800,
|
2424 |
+
"records": [
|
2425 |
+
{
|
2426 |
+
"name": "model.layers.8.mlp.gate_up_proj.q_weight",
|
2427 |
+
"shape": [
|
2428 |
+
11264,
|
2429 |
+
256
|
2430 |
+
],
|
2431 |
+
"dtype": "uint32",
|
2432 |
+
"format": "f32-to-bf16",
|
2433 |
+
"nbytes": 11534336,
|
2434 |
+
"byteOffset": 0
|
2435 |
+
},
|
2436 |
+
{
|
2437 |
+
"name": "model.layers.8.mlp.gate_up_proj.q_scale",
|
2438 |
+
"shape": [
|
2439 |
+
11264,
|
2440 |
+
64
|
2441 |
+
],
|
2442 |
+
"dtype": "float32",
|
2443 |
+
"format": "f32-to-bf16",
|
2444 |
+
"nbytes": 1441792,
|
2445 |
+
"byteOffset": 11534336
|
2446 |
+
},
|
2447 |
+
{
|
2448 |
+
"name": "model.layers.8.post_attention_layernorm.weight",
|
2449 |
+
"shape": [
|
2450 |
+
2048
|
2451 |
+
],
|
2452 |
+
"dtype": "float32",
|
2453 |
+
"format": "f32-to-bf16",
|
2454 |
+
"nbytes": 4096,
|
2455 |
+
"byteOffset": 12976128
|
2456 |
+
},
|
2457 |
+
{
|
2458 |
+
"name": "model.layers.8.self_attn.qkv_proj.q_weight",
|
2459 |
+
"shape": [
|
2460 |
+
2560,
|
2461 |
+
256
|
2462 |
+
],
|
2463 |
+
"dtype": "uint32",
|
2464 |
+
"format": "f32-to-bf16",
|
2465 |
+
"nbytes": 2621440,
|
2466 |
+
"byteOffset": 12980224
|
2467 |
+
},
|
2468 |
+
{
|
2469 |
+
"name": "model.layers.8.self_attn.qkv_proj.q_scale",
|
2470 |
+
"shape": [
|
2471 |
+
2560,
|
2472 |
+
64
|
2473 |
+
],
|
2474 |
+
"dtype": "float32",
|
2475 |
+
"format": "f32-to-bf16",
|
2476 |
+
"nbytes": 327680,
|
2477 |
+
"byteOffset": 15601664
|
2478 |
+
},
|
2479 |
+
{
|
2480 |
+
"name": "model.layers.8.self_attn.o_proj.q_weight",
|
2481 |
+
"shape": [
|
2482 |
+
2048,
|
2483 |
+
256
|
2484 |
+
],
|
2485 |
+
"dtype": "uint32",
|
2486 |
+
"format": "f32-to-bf16",
|
2487 |
+
"nbytes": 2097152,
|
2488 |
+
"byteOffset": 15929344
|
2489 |
+
},
|
2490 |
+
{
|
2491 |
+
"name": "model.layers.8.self_attn.o_proj.q_scale",
|
2492 |
+
"shape": [
|
2493 |
+
2048,
|
2494 |
+
64
|
2495 |
+
],
|
2496 |
+
"dtype": "float32",
|
2497 |
+
"format": "f32-to-bf16",
|
2498 |
+
"nbytes": 262144,
|
2499 |
+
"byteOffset": 18026496
|
2500 |
+
},
|
2501 |
+
{
|
2502 |
+
"name": "model.layers.9.input_layernorm.weight",
|
2503 |
+
"shape": [
|
2504 |
+
2048
|
2505 |
+
],
|
2506 |
+
"dtype": "float32",
|
2507 |
+
"format": "f32-to-bf16",
|
2508 |
+
"nbytes": 4096,
|
2509 |
+
"byteOffset": 18288640
|
2510 |
+
},
|
2511 |
+
{
|
2512 |
+
"name": "model.layers.9.mlp.down_proj.q_weight",
|
2513 |
+
"shape": [
|
2514 |
+
2048,
|
2515 |
+
704
|
2516 |
+
],
|
2517 |
+
"dtype": "uint32",
|
2518 |
+
"format": "f32-to-bf16",
|
2519 |
+
"nbytes": 5767168,
|
2520 |
+
"byteOffset": 18292736
|
2521 |
+
},
|
2522 |
+
{
|
2523 |
+
"name": "model.layers.9.mlp.down_proj.q_scale",
|
2524 |
+
"shape": [
|
2525 |
+
2048,
|
2526 |
+
176
|
2527 |
+
],
|
2528 |
+
"dtype": "float32",
|
2529 |
+
"format": "f32-to-bf16",
|
2530 |
+
"nbytes": 720896,
|
2531 |
+
"byteOffset": 24059904
|
2532 |
+
}
|
2533 |
+
],
|
2534 |
+
"md5sum": "5a11a5b68f457af4ae8df8926c2c02ff"
|
2535 |
+
},
|
2536 |
+
{
|
2537 |
+
"dataPath": "params_shard_23.bin",
|
2538 |
+
"format": "raw-shard",
|
2539 |
+
"nbytes": 18292736,
|
2540 |
+
"records": [
|
2541 |
+
{
|
2542 |
+
"name": "model.layers.9.mlp.gate_up_proj.q_weight",
|
2543 |
+
"shape": [
|
2544 |
+
11264,
|
2545 |
+
256
|
2546 |
+
],
|
2547 |
+
"dtype": "uint32",
|
2548 |
+
"format": "f32-to-bf16",
|
2549 |
+
"nbytes": 11534336,
|
2550 |
+
"byteOffset": 0
|
2551 |
+
},
|
2552 |
+
{
|
2553 |
+
"name": "model.layers.9.mlp.gate_up_proj.q_scale",
|
2554 |
+
"shape": [
|
2555 |
+
11264,
|
2556 |
+
64
|
2557 |
+
],
|
2558 |
+
"dtype": "float32",
|
2559 |
+
"format": "f32-to-bf16",
|
2560 |
+
"nbytes": 1441792,
|
2561 |
+
"byteOffset": 11534336
|
2562 |
+
},
|
2563 |
+
{
|
2564 |
+
"name": "model.layers.9.post_attention_layernorm.weight",
|
2565 |
+
"shape": [
|
2566 |
+
2048
|
2567 |
+
],
|
2568 |
+
"dtype": "float32",
|
2569 |
+
"format": "f32-to-bf16",
|
2570 |
+
"nbytes": 4096,
|
2571 |
+
"byteOffset": 12976128
|
2572 |
+
},
|
2573 |
+
{
|
2574 |
+
"name": "model.layers.9.self_attn.qkv_proj.q_weight",
|
2575 |
+
"shape": [
|
2576 |
+
2560,
|
2577 |
+
256
|
2578 |
+
],
|
2579 |
+
"dtype": "uint32",
|
2580 |
+
"format": "f32-to-bf16",
|
2581 |
+
"nbytes": 2621440,
|
2582 |
+
"byteOffset": 12980224
|
2583 |
+
},
|
2584 |
+
{
|
2585 |
+
"name": "model.layers.9.self_attn.qkv_proj.q_scale",
|
2586 |
+
"shape": [
|
2587 |
+
2560,
|
2588 |
+
64
|
2589 |
+
],
|
2590 |
+
"dtype": "float32",
|
2591 |
+
"format": "f32-to-bf16",
|
2592 |
+
"nbytes": 327680,
|
2593 |
+
"byteOffset": 15601664
|
2594 |
+
},
|
2595 |
+
{
|
2596 |
+
"name": "model.layers.9.self_attn.o_proj.q_weight",
|
2597 |
+
"shape": [
|
2598 |
+
2048,
|
2599 |
+
256
|
2600 |
+
],
|
2601 |
+
"dtype": "uint32",
|
2602 |
+
"format": "f32-to-bf16",
|
2603 |
+
"nbytes": 2097152,
|
2604 |
+
"byteOffset": 15929344
|
2605 |
+
},
|
2606 |
+
{
|
2607 |
+
"name": "model.layers.9.self_attn.o_proj.q_scale",
|
2608 |
+
"shape": [
|
2609 |
+
2048,
|
2610 |
+
64
|
2611 |
+
],
|
2612 |
+
"dtype": "float32",
|
2613 |
+
"format": "f32-to-bf16",
|
2614 |
+
"nbytes": 262144,
|
2615 |
+
"byteOffset": 18026496
|
2616 |
+
},
|
2617 |
+
{
|
2618 |
+
"name": "model.norm.weight",
|
2619 |
+
"shape": [
|
2620 |
+
2048
|
2621 |
+
],
|
2622 |
+
"dtype": "float32",
|
2623 |
+
"format": "f32-to-bf16",
|
2624 |
+
"nbytes": 4096,
|
2625 |
+
"byteOffset": 18288640
|
2626 |
+
}
|
2627 |
+
],
|
2628 |
+
"md5sum": "83f96e3340c8f435412897a17003888e"
|
2629 |
+
}
|
2630 |
+
]
|
2631 |
+
}
|
params_shard_0.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d3bad64c8100b0c52883e60e30dcd881fcefa6645e97c59063501e08faee552
|
3 |
+
size 32768000
|
params_shard_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:717885f20831eea8e64c31ac705354828f285ac0baaebb24fe4b7d29449eab47
|
3 |
+
size 32768000
|
params_shard_10.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:246789b20d4672f9c43545325d688becf849bd036640e016af021c9f3e04393c
|
3 |
+
size 24780800
|
params_shard_11.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0494f25f78e5d7e570ee3d2f9ecb2f78a535c6113eccc7bb71ff55d90b61371a
|
3 |
+
size 24780800
|
params_shard_12.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13036dd9822369d3cdce4adead967b2aca6d2299c785253133e98ff37520f631
|
3 |
+
size 24780800
|
params_shard_13.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d644489b58d5c35c74232133e2209a396aedef6b55999bad3a991051436a4094
|
3 |
+
size 24780800
|
params_shard_14.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7dc43a7af68bb20e7ede6f59575489ae36eb9c1322f59e8a7b67462fc869109a
|
3 |
+
size 24780800
|
params_shard_15.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73a6f9d55ada388a565294b1fb934ba816ad35cc5d0ff75a31e20e5bfd17ff5f
|
3 |
+
size 24780800
|
params_shard_16.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8157502cddcfba1f0dbb55d3d2d2b62729b84346cabfc0e60ac70c650675aa09
|
3 |
+
size 24780800
|
params_shard_17.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4735f98a0cf6266bb7e0b899338be6c050370e2017f27ec489362446c44d8da5
|
3 |
+
size 24780800
|
params_shard_18.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b60c99668a7180729c5ee51beb4ab67d390feda1f7047f9637db1a051edd6c86
|
3 |
+
size 24780800
|
params_shard_19.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62b1a25c22bcf96213a32ec90268cc5c588444b4408cf1070eb357e9749c7929
|
3 |
+
size 24780800
|
params_shard_2.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a80ebf330d101f10851b63818bdddf67db5d683a3dee564dc70738756c8dc74
|
3 |
+
size 32976896
|
params_shard_20.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecdfa79b4fb125356e6d7485eae4cc1d7b785ec6afd17776533893d820e77dc1
|
3 |
+
size 24780800
|
params_shard_21.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3efe47d0c09393ae9dea3b75b18e4d7cb6a679e7cc72f5e88dc0672b50d41b6
|
3 |
+
size 24780800
|
params_shard_22.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7102f63b0e8993992783465a175c72f87fbf3c10747ac1632feb5bc8036b079d
|
3 |
+
size 24780800
|
params_shard_23.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:368585032efc3cc0c6467e70c63d200b48da3cfbb2962391eeb567116985cd28
|
3 |
+
size 18292736
|
params_shard_3.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64b60ae5545af4a1d706c983020ff898b30b8e44c0fb9694d22a16723e1db0e3
|
3 |
+
size 31268864
|
params_shard_4.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22674cb033c36301ced8a514c2e1c6614f55d52bc195927dae2c93478f8de0af
|
3 |
+
size 24780800
|
params_shard_5.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3eaecc43a8b233fefca2fefdfa818887948707417e9d739ab7f3b95cb47066fa
|
3 |
+
size 24780800
|
params_shard_6.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7223f832e3b068a95de71f7c5eb295550e31369f7274ab42c5effc8bca8d1dbf
|
3 |
+
size 24780800
|
params_shard_7.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aab378797c3eff5859636e85702f4eca4c0c081e89d2ac9f4e8f8aa7730d5528
|
3 |
+
size 24780800
|
params_shard_8.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c857ac90783c9f041609835f618c6c99025cd5c401296f9ff830a459360c4470
|
3 |
+
size 24780800
|
params_shard_9.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64fb227256a0fa148d16190afa67c5ac1d29c5aa69c8f733c9289a95562558d6
|
3 |
+
size 24780800
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"bos_token": "<s>",
|
29 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
30 |
+
"clean_up_tokenization_spaces": false,
|
31 |
+
"eos_token": "</s>",
|
32 |
+
"legacy": false,
|
33 |
+
"model_max_length": 2048,
|
34 |
+
"pad_token": "</s>",
|
35 |
+
"padding_side": "right",
|
36 |
+
"sp_model_kwargs": {},
|
37 |
+
"tokenizer_class": "LlamaTokenizer",
|
38 |
+
"unk_token": "<unk>",
|
39 |
+
"use_default_system_prompt": false
|
40 |
+
}
|