Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +1 -0
- mlc-chat-config.json +44 -0
- ndarray-cache.json +1574 -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_24.bin +3 -0
- params_shard_25.bin +3 -0
- params_shard_26.bin +3 -0
- params_shard_27.bin +3 -0
- params_shard_28.bin +3 -0
- params_shard_29.bin +3 -0
- params_shard_3.bin +3 -0
- params_shard_30.bin +3 -0
- params_shard_31.bin +3 -0
- params_shard_32.bin +3 -0
- params_shard_33.bin +3 -0
- params_shard_34.bin +3 -0
- params_shard_35.bin +3 -0
- params_shard_36.bin +3 -0
- params_shard_37.bin +3 -0
- params_shard_38.bin +3 -0
- params_shard_39.bin +3 -0
- params_shard_4.bin +3 -0
- params_shard_40.bin +3 -0
- params_shard_41.bin +3 -0
- params_shard_42.bin +3 -0
- params_shard_43.bin +3 -0
- params_shard_44.bin +3 -0
- params_shard_45.bin +3 -0
- params_shard_46.bin +3 -0
- params_shard_47.bin +3 -0
- params_shard_48.bin +3 -0
- params_shard_5.bin +3 -0
- params_shard_6.bin +3 -0
- params_shard_7.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
mlc-chat-config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "gemma",
|
| 3 |
+
"quantization": "q0f16",
|
| 4 |
+
"model_config": {
|
| 5 |
+
"hidden_size": 2048,
|
| 6 |
+
"hidden_act": "gelu",
|
| 7 |
+
"intermediate_size": 16384,
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"num_attention_heads": 8,
|
| 10 |
+
"num_key_value_heads": 1,
|
| 11 |
+
"head_dim": 256,
|
| 12 |
+
"num_hidden_layers": 18,
|
| 13 |
+
"rms_norm_eps": 1e-06,
|
| 14 |
+
"vocab_size": 256000,
|
| 15 |
+
"position_embedding_base": 10000.0,
|
| 16 |
+
"context_window_size": 8192,
|
| 17 |
+
"prefill_chunk_size": 8192,
|
| 18 |
+
"tensor_parallel_shards": 1,
|
| 19 |
+
"max_batch_size": 80
|
| 20 |
+
},
|
| 21 |
+
"vocab_size": 256000,
|
| 22 |
+
"context_window_size": 8192,
|
| 23 |
+
"sliding_window_size": -1,
|
| 24 |
+
"prefill_chunk_size": 8192,
|
| 25 |
+
"attention_sink_size": -1,
|
| 26 |
+
"tensor_parallel_shards": 1,
|
| 27 |
+
"mean_gen_len": 128,
|
| 28 |
+
"max_gen_len": 512,
|
| 29 |
+
"shift_fill_factor": 0.3,
|
| 30 |
+
"temperature": 0.7,
|
| 31 |
+
"repetition_penalty": 1.0,
|
| 32 |
+
"frequency_penalty": 1.0,
|
| 33 |
+
"top_p": 0.95,
|
| 34 |
+
"conv_template": "gemma_instruction",
|
| 35 |
+
"pad_token_id": 0,
|
| 36 |
+
"bos_token_id": 2,
|
| 37 |
+
"eos_token_id": 1,
|
| 38 |
+
"tokenizer_files": [
|
| 39 |
+
"tokenizer.model",
|
| 40 |
+
"tokenizer.json",
|
| 41 |
+
"tokenizer_config.json"
|
| 42 |
+
],
|
| 43 |
+
"version": "0.1.0"
|
| 44 |
+
}
|
ndarray-cache.json
ADDED
|
@@ -0,0 +1,1574 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"ParamSize": 110,
|
| 4 |
+
"ParamBytes": 5012344832.0,
|
| 5 |
+
"BitsPerParam": 16.0
|
| 6 |
+
},
|
| 7 |
+
"records": [
|
| 8 |
+
{
|
| 9 |
+
"dataPath": "params_shard_0.bin",
|
| 10 |
+
"format": "raw-shard",
|
| 11 |
+
"nbytes": 1048576000,
|
| 12 |
+
"records": [
|
| 13 |
+
{
|
| 14 |
+
"name": "model.embed_tokens.weight",
|
| 15 |
+
"shape": [
|
| 16 |
+
256000,
|
| 17 |
+
2048
|
| 18 |
+
],
|
| 19 |
+
"dtype": "float16",
|
| 20 |
+
"format": "f32-to-bf16",
|
| 21 |
+
"nbytes": 1048576000,
|
| 22 |
+
"byteOffset": 0
|
| 23 |
+
}
|
| 24 |
+
],
|
| 25 |
+
"md5sum": "206485d87a22f62128d5b2494bafe7db"
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"dataPath": "params_shard_1.bin",
|
| 29 |
+
"format": "raw-shard",
|
| 30 |
+
"nbytes": 67108864,
|
| 31 |
+
"records": [
|
| 32 |
+
{
|
| 33 |
+
"name": "model.layers.0.mlp.down_proj.weight",
|
| 34 |
+
"shape": [
|
| 35 |
+
2048,
|
| 36 |
+
16384
|
| 37 |
+
],
|
| 38 |
+
"dtype": "float16",
|
| 39 |
+
"format": "f32-to-bf16",
|
| 40 |
+
"nbytes": 67108864,
|
| 41 |
+
"byteOffset": 0
|
| 42 |
+
}
|
| 43 |
+
],
|
| 44 |
+
"md5sum": "0af16f8f82b18456b292f26c2e72f63b"
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"dataPath": "params_shard_2.bin",
|
| 48 |
+
"format": "raw-shard",
|
| 49 |
+
"nbytes": 134217728,
|
| 50 |
+
"records": [
|
| 51 |
+
{
|
| 52 |
+
"name": "model.layers.0.mlp.gate_up_proj.weight",
|
| 53 |
+
"shape": [
|
| 54 |
+
32768,
|
| 55 |
+
2048
|
| 56 |
+
],
|
| 57 |
+
"dtype": "float16",
|
| 58 |
+
"format": "f32-to-bf16",
|
| 59 |
+
"nbytes": 134217728,
|
| 60 |
+
"byteOffset": 0
|
| 61 |
+
}
|
| 62 |
+
],
|
| 63 |
+
"md5sum": "2ba31ef002c5e642855d91dbaf959171"
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"dataPath": "params_shard_3.bin",
|
| 67 |
+
"format": "raw-shard",
|
| 68 |
+
"nbytes": 67108864,
|
| 69 |
+
"records": [
|
| 70 |
+
{
|
| 71 |
+
"name": "model.layers.1.mlp.down_proj.weight",
|
| 72 |
+
"shape": [
|
| 73 |
+
2048,
|
| 74 |
+
16384
|
| 75 |
+
],
|
| 76 |
+
"dtype": "float16",
|
| 77 |
+
"format": "f32-to-bf16",
|
| 78 |
+
"nbytes": 67108864,
|
| 79 |
+
"byteOffset": 0
|
| 80 |
+
}
|
| 81 |
+
],
|
| 82 |
+
"md5sum": "c7d1d36c62d66bea4696e965fff1917e"
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"dataPath": "params_shard_4.bin",
|
| 86 |
+
"format": "raw-shard",
|
| 87 |
+
"nbytes": 134217728,
|
| 88 |
+
"records": [
|
| 89 |
+
{
|
| 90 |
+
"name": "model.layers.1.mlp.gate_up_proj.weight",
|
| 91 |
+
"shape": [
|
| 92 |
+
32768,
|
| 93 |
+
2048
|
| 94 |
+
],
|
| 95 |
+
"dtype": "float16",
|
| 96 |
+
"format": "f32-to-bf16",
|
| 97 |
+
"nbytes": 134217728,
|
| 98 |
+
"byteOffset": 0
|
| 99 |
+
}
|
| 100 |
+
],
|
| 101 |
+
"md5sum": "362ff38d501c9881a63569d0cfa88605"
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"dataPath": "params_shard_5.bin",
|
| 105 |
+
"format": "raw-shard",
|
| 106 |
+
"nbytes": 29376512,
|
| 107 |
+
"records": [
|
| 108 |
+
{
|
| 109 |
+
"name": "model.layers.0.input_layernorm.weight",
|
| 110 |
+
"shape": [
|
| 111 |
+
2048
|
| 112 |
+
],
|
| 113 |
+
"dtype": "float16",
|
| 114 |
+
"format": "f32-to-bf16",
|
| 115 |
+
"nbytes": 4096,
|
| 116 |
+
"byteOffset": 0
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"name": "model.layers.0.post_attention_layernorm.weight",
|
| 120 |
+
"shape": [
|
| 121 |
+
2048
|
| 122 |
+
],
|
| 123 |
+
"dtype": "float16",
|
| 124 |
+
"format": "f32-to-bf16",
|
| 125 |
+
"nbytes": 4096,
|
| 126 |
+
"byteOffset": 4096
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"name": "model.layers.0.self_attn.qkv_proj.weight",
|
| 130 |
+
"shape": [
|
| 131 |
+
2560,
|
| 132 |
+
2048
|
| 133 |
+
],
|
| 134 |
+
"dtype": "float16",
|
| 135 |
+
"format": "f32-to-bf16",
|
| 136 |
+
"nbytes": 10485760,
|
| 137 |
+
"byteOffset": 8192
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"name": "model.layers.0.self_attn.o_proj.weight",
|
| 141 |
+
"shape": [
|
| 142 |
+
2048,
|
| 143 |
+
2048
|
| 144 |
+
],
|
| 145 |
+
"dtype": "float16",
|
| 146 |
+
"format": "f32-to-bf16",
|
| 147 |
+
"nbytes": 8388608,
|
| 148 |
+
"byteOffset": 10493952
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"name": "model.layers.1.input_layernorm.weight",
|
| 152 |
+
"shape": [
|
| 153 |
+
2048
|
| 154 |
+
],
|
| 155 |
+
"dtype": "float16",
|
| 156 |
+
"format": "f32-to-bf16",
|
| 157 |
+
"nbytes": 4096,
|
| 158 |
+
"byteOffset": 18882560
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"name": "model.layers.1.post_attention_layernorm.weight",
|
| 162 |
+
"shape": [
|
| 163 |
+
2048
|
| 164 |
+
],
|
| 165 |
+
"dtype": "float16",
|
| 166 |
+
"format": "f32-to-bf16",
|
| 167 |
+
"nbytes": 4096,
|
| 168 |
+
"byteOffset": 18886656
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"name": "model.layers.1.self_attn.qkv_proj.weight",
|
| 172 |
+
"shape": [
|
| 173 |
+
2560,
|
| 174 |
+
2048
|
| 175 |
+
],
|
| 176 |
+
"dtype": "float16",
|
| 177 |
+
"format": "f32-to-bf16",
|
| 178 |
+
"nbytes": 10485760,
|
| 179 |
+
"byteOffset": 18890752
|
| 180 |
+
}
|
| 181 |
+
],
|
| 182 |
+
"md5sum": "5d30e8d1452ab145a0564794c26cd791"
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"dataPath": "params_shard_6.bin",
|
| 186 |
+
"format": "raw-shard",
|
| 187 |
+
"nbytes": 67108864,
|
| 188 |
+
"records": [
|
| 189 |
+
{
|
| 190 |
+
"name": "model.layers.10.mlp.down_proj.weight",
|
| 191 |
+
"shape": [
|
| 192 |
+
2048,
|
| 193 |
+
16384
|
| 194 |
+
],
|
| 195 |
+
"dtype": "float16",
|
| 196 |
+
"format": "f32-to-bf16",
|
| 197 |
+
"nbytes": 67108864,
|
| 198 |
+
"byteOffset": 0
|
| 199 |
+
}
|
| 200 |
+
],
|
| 201 |
+
"md5sum": "fe63b3dbe2543296f8112fac2ade5290"
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"dataPath": "params_shard_7.bin",
|
| 205 |
+
"format": "raw-shard",
|
| 206 |
+
"nbytes": 134217728,
|
| 207 |
+
"records": [
|
| 208 |
+
{
|
| 209 |
+
"name": "model.layers.10.mlp.gate_up_proj.weight",
|
| 210 |
+
"shape": [
|
| 211 |
+
32768,
|
| 212 |
+
2048
|
| 213 |
+
],
|
| 214 |
+
"dtype": "float16",
|
| 215 |
+
"format": "f32-to-bf16",
|
| 216 |
+
"nbytes": 134217728,
|
| 217 |
+
"byteOffset": 0
|
| 218 |
+
}
|
| 219 |
+
],
|
| 220 |
+
"md5sum": "629331e7d43d063ae03d036060febb5f"
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"dataPath": "params_shard_8.bin",
|
| 224 |
+
"format": "raw-shard",
|
| 225 |
+
"nbytes": 67108864,
|
| 226 |
+
"records": [
|
| 227 |
+
{
|
| 228 |
+
"name": "model.layers.11.mlp.down_proj.weight",
|
| 229 |
+
"shape": [
|
| 230 |
+
2048,
|
| 231 |
+
16384
|
| 232 |
+
],
|
| 233 |
+
"dtype": "float16",
|
| 234 |
+
"format": "f32-to-bf16",
|
| 235 |
+
"nbytes": 67108864,
|
| 236 |
+
"byteOffset": 0
|
| 237 |
+
}
|
| 238 |
+
],
|
| 239 |
+
"md5sum": "cd3f99f63fc39b1170222cb6f4717b72"
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"dataPath": "params_shard_9.bin",
|
| 243 |
+
"format": "raw-shard",
|
| 244 |
+
"nbytes": 134217728,
|
| 245 |
+
"records": [
|
| 246 |
+
{
|
| 247 |
+
"name": "model.layers.11.mlp.gate_up_proj.weight",
|
| 248 |
+
"shape": [
|
| 249 |
+
32768,
|
| 250 |
+
2048
|
| 251 |
+
],
|
| 252 |
+
"dtype": "float16",
|
| 253 |
+
"format": "f32-to-bf16",
|
| 254 |
+
"nbytes": 134217728,
|
| 255 |
+
"byteOffset": 0
|
| 256 |
+
}
|
| 257 |
+
],
|
| 258 |
+
"md5sum": "c9193e83b6a383f990b1d7d703a6f80f"
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"dataPath": "params_shard_10.bin",
|
| 262 |
+
"format": "raw-shard",
|
| 263 |
+
"nbytes": 27279360,
|
| 264 |
+
"records": [
|
| 265 |
+
{
|
| 266 |
+
"name": "model.layers.1.self_attn.o_proj.weight",
|
| 267 |
+
"shape": [
|
| 268 |
+
2048,
|
| 269 |
+
2048
|
| 270 |
+
],
|
| 271 |
+
"dtype": "float16",
|
| 272 |
+
"format": "f32-to-bf16",
|
| 273 |
+
"nbytes": 8388608,
|
| 274 |
+
"byteOffset": 0
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"name": "model.layers.10.input_layernorm.weight",
|
| 278 |
+
"shape": [
|
| 279 |
+
2048
|
| 280 |
+
],
|
| 281 |
+
"dtype": "float16",
|
| 282 |
+
"format": "f32-to-bf16",
|
| 283 |
+
"nbytes": 4096,
|
| 284 |
+
"byteOffset": 8388608
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"name": "model.layers.10.post_attention_layernorm.weight",
|
| 288 |
+
"shape": [
|
| 289 |
+
2048
|
| 290 |
+
],
|
| 291 |
+
"dtype": "float16",
|
| 292 |
+
"format": "f32-to-bf16",
|
| 293 |
+
"nbytes": 4096,
|
| 294 |
+
"byteOffset": 8392704
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"name": "model.layers.10.self_attn.qkv_proj.weight",
|
| 298 |
+
"shape": [
|
| 299 |
+
2560,
|
| 300 |
+
2048
|
| 301 |
+
],
|
| 302 |
+
"dtype": "float16",
|
| 303 |
+
"format": "f32-to-bf16",
|
| 304 |
+
"nbytes": 10485760,
|
| 305 |
+
"byteOffset": 8396800
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"name": "model.layers.10.self_attn.o_proj.weight",
|
| 309 |
+
"shape": [
|
| 310 |
+
2048,
|
| 311 |
+
2048
|
| 312 |
+
],
|
| 313 |
+
"dtype": "float16",
|
| 314 |
+
"format": "f32-to-bf16",
|
| 315 |
+
"nbytes": 8388608,
|
| 316 |
+
"byteOffset": 18882560
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"name": "model.layers.11.input_layernorm.weight",
|
| 320 |
+
"shape": [
|
| 321 |
+
2048
|
| 322 |
+
],
|
| 323 |
+
"dtype": "float16",
|
| 324 |
+
"format": "f32-to-bf16",
|
| 325 |
+
"nbytes": 4096,
|
| 326 |
+
"byteOffset": 27271168
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"name": "model.layers.11.post_attention_layernorm.weight",
|
| 330 |
+
"shape": [
|
| 331 |
+
2048
|
| 332 |
+
],
|
| 333 |
+
"dtype": "float16",
|
| 334 |
+
"format": "f32-to-bf16",
|
| 335 |
+
"nbytes": 4096,
|
| 336 |
+
"byteOffset": 27275264
|
| 337 |
+
}
|
| 338 |
+
],
|
| 339 |
+
"md5sum": "59d0b4f1bd55ceeda6e5ab96633e9451"
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"dataPath": "params_shard_11.bin",
|
| 343 |
+
"format": "raw-shard",
|
| 344 |
+
"nbytes": 67108864,
|
| 345 |
+
"records": [
|
| 346 |
+
{
|
| 347 |
+
"name": "model.layers.12.mlp.down_proj.weight",
|
| 348 |
+
"shape": [
|
| 349 |
+
2048,
|
| 350 |
+
16384
|
| 351 |
+
],
|
| 352 |
+
"dtype": "float16",
|
| 353 |
+
"format": "f32-to-bf16",
|
| 354 |
+
"nbytes": 67108864,
|
| 355 |
+
"byteOffset": 0
|
| 356 |
+
}
|
| 357 |
+
],
|
| 358 |
+
"md5sum": "820b534e89d40aa248659ca0081f0674"
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"dataPath": "params_shard_12.bin",
|
| 362 |
+
"format": "raw-shard",
|
| 363 |
+
"nbytes": 134217728,
|
| 364 |
+
"records": [
|
| 365 |
+
{
|
| 366 |
+
"name": "model.layers.12.mlp.gate_up_proj.weight",
|
| 367 |
+
"shape": [
|
| 368 |
+
32768,
|
| 369 |
+
2048
|
| 370 |
+
],
|
| 371 |
+
"dtype": "float16",
|
| 372 |
+
"format": "f32-to-bf16",
|
| 373 |
+
"nbytes": 134217728,
|
| 374 |
+
"byteOffset": 0
|
| 375 |
+
}
|
| 376 |
+
],
|
| 377 |
+
"md5sum": "256dabcc684ebacdfdbbcfa0adc035e1"
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"dataPath": "params_shard_13.bin",
|
| 381 |
+
"format": "raw-shard",
|
| 382 |
+
"nbytes": 29368320,
|
| 383 |
+
"records": [
|
| 384 |
+
{
|
| 385 |
+
"name": "model.layers.11.self_attn.qkv_proj.weight",
|
| 386 |
+
"shape": [
|
| 387 |
+
2560,
|
| 388 |
+
2048
|
| 389 |
+
],
|
| 390 |
+
"dtype": "float16",
|
| 391 |
+
"format": "f32-to-bf16",
|
| 392 |
+
"nbytes": 10485760,
|
| 393 |
+
"byteOffset": 0
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"name": "model.layers.11.self_attn.o_proj.weight",
|
| 397 |
+
"shape": [
|
| 398 |
+
2048,
|
| 399 |
+
2048
|
| 400 |
+
],
|
| 401 |
+
"dtype": "float16",
|
| 402 |
+
"format": "f32-to-bf16",
|
| 403 |
+
"nbytes": 8388608,
|
| 404 |
+
"byteOffset": 10485760
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"name": "model.layers.12.input_layernorm.weight",
|
| 408 |
+
"shape": [
|
| 409 |
+
2048
|
| 410 |
+
],
|
| 411 |
+
"dtype": "float16",
|
| 412 |
+
"format": "f32-to-bf16",
|
| 413 |
+
"nbytes": 4096,
|
| 414 |
+
"byteOffset": 18874368
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"name": "model.layers.12.post_attention_layernorm.weight",
|
| 418 |
+
"shape": [
|
| 419 |
+
2048
|
| 420 |
+
],
|
| 421 |
+
"dtype": "float16",
|
| 422 |
+
"format": "f32-to-bf16",
|
| 423 |
+
"nbytes": 4096,
|
| 424 |
+
"byteOffset": 18878464
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"name": "model.layers.12.self_attn.qkv_proj.weight",
|
| 428 |
+
"shape": [
|
| 429 |
+
2560,
|
| 430 |
+
2048
|
| 431 |
+
],
|
| 432 |
+
"dtype": "float16",
|
| 433 |
+
"format": "f32-to-bf16",
|
| 434 |
+
"nbytes": 10485760,
|
| 435 |
+
"byteOffset": 18882560
|
| 436 |
+
}
|
| 437 |
+
],
|
| 438 |
+
"md5sum": "7d790e2cfa6142474ac62a0ec5aea10c"
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"dataPath": "params_shard_14.bin",
|
| 442 |
+
"format": "raw-shard",
|
| 443 |
+
"nbytes": 67108864,
|
| 444 |
+
"records": [
|
| 445 |
+
{
|
| 446 |
+
"name": "model.layers.13.mlp.down_proj.weight",
|
| 447 |
+
"shape": [
|
| 448 |
+
2048,
|
| 449 |
+
16384
|
| 450 |
+
],
|
| 451 |
+
"dtype": "float16",
|
| 452 |
+
"format": "f32-to-bf16",
|
| 453 |
+
"nbytes": 67108864,
|
| 454 |
+
"byteOffset": 0
|
| 455 |
+
}
|
| 456 |
+
],
|
| 457 |
+
"md5sum": "908e1855eb654380dfcd3cfd85a1e631"
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"dataPath": "params_shard_15.bin",
|
| 461 |
+
"format": "raw-shard",
|
| 462 |
+
"nbytes": 134217728,
|
| 463 |
+
"records": [
|
| 464 |
+
{
|
| 465 |
+
"name": "model.layers.13.mlp.gate_up_proj.weight",
|
| 466 |
+
"shape": [
|
| 467 |
+
32768,
|
| 468 |
+
2048
|
| 469 |
+
],
|
| 470 |
+
"dtype": "float16",
|
| 471 |
+
"format": "f32-to-bf16",
|
| 472 |
+
"nbytes": 134217728,
|
| 473 |
+
"byteOffset": 0
|
| 474 |
+
}
|
| 475 |
+
],
|
| 476 |
+
"md5sum": "ea87b38d7fde1e77b55f18aa11c0ed31"
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"dataPath": "params_shard_16.bin",
|
| 480 |
+
"format": "raw-shard",
|
| 481 |
+
"nbytes": 67108864,
|
| 482 |
+
"records": [
|
| 483 |
+
{
|
| 484 |
+
"name": "model.layers.14.mlp.down_proj.weight",
|
| 485 |
+
"shape": [
|
| 486 |
+
2048,
|
| 487 |
+
16384
|
| 488 |
+
],
|
| 489 |
+
"dtype": "float16",
|
| 490 |
+
"format": "f32-to-bf16",
|
| 491 |
+
"nbytes": 67108864,
|
| 492 |
+
"byteOffset": 0
|
| 493 |
+
}
|
| 494 |
+
],
|
| 495 |
+
"md5sum": "f795202d6edb9f663561fa0cf03fa27a"
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"dataPath": "params_shard_17.bin",
|
| 499 |
+
"format": "raw-shard",
|
| 500 |
+
"nbytes": 134217728,
|
| 501 |
+
"records": [
|
| 502 |
+
{
|
| 503 |
+
"name": "model.layers.14.mlp.gate_up_proj.weight",
|
| 504 |
+
"shape": [
|
| 505 |
+
32768,
|
| 506 |
+
2048
|
| 507 |
+
],
|
| 508 |
+
"dtype": "float16",
|
| 509 |
+
"format": "f32-to-bf16",
|
| 510 |
+
"nbytes": 134217728,
|
| 511 |
+
"byteOffset": 0
|
| 512 |
+
}
|
| 513 |
+
],
|
| 514 |
+
"md5sum": "88378b8b2905d8b91937c001c73403cb"
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"dataPath": "params_shard_18.bin",
|
| 518 |
+
"format": "raw-shard",
|
| 519 |
+
"nbytes": 27279360,
|
| 520 |
+
"records": [
|
| 521 |
+
{
|
| 522 |
+
"name": "model.layers.12.self_attn.o_proj.weight",
|
| 523 |
+
"shape": [
|
| 524 |
+
2048,
|
| 525 |
+
2048
|
| 526 |
+
],
|
| 527 |
+
"dtype": "float16",
|
| 528 |
+
"format": "f32-to-bf16",
|
| 529 |
+
"nbytes": 8388608,
|
| 530 |
+
"byteOffset": 0
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"name": "model.layers.13.input_layernorm.weight",
|
| 534 |
+
"shape": [
|
| 535 |
+
2048
|
| 536 |
+
],
|
| 537 |
+
"dtype": "float16",
|
| 538 |
+
"format": "f32-to-bf16",
|
| 539 |
+
"nbytes": 4096,
|
| 540 |
+
"byteOffset": 8388608
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"name": "model.layers.13.post_attention_layernorm.weight",
|
| 544 |
+
"shape": [
|
| 545 |
+
2048
|
| 546 |
+
],
|
| 547 |
+
"dtype": "float16",
|
| 548 |
+
"format": "f32-to-bf16",
|
| 549 |
+
"nbytes": 4096,
|
| 550 |
+
"byteOffset": 8392704
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"name": "model.layers.13.self_attn.qkv_proj.weight",
|
| 554 |
+
"shape": [
|
| 555 |
+
2560,
|
| 556 |
+
2048
|
| 557 |
+
],
|
| 558 |
+
"dtype": "float16",
|
| 559 |
+
"format": "f32-to-bf16",
|
| 560 |
+
"nbytes": 10485760,
|
| 561 |
+
"byteOffset": 8396800
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"name": "model.layers.13.self_attn.o_proj.weight",
|
| 565 |
+
"shape": [
|
| 566 |
+
2048,
|
| 567 |
+
2048
|
| 568 |
+
],
|
| 569 |
+
"dtype": "float16",
|
| 570 |
+
"format": "f32-to-bf16",
|
| 571 |
+
"nbytes": 8388608,
|
| 572 |
+
"byteOffset": 18882560
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"name": "model.layers.14.input_layernorm.weight",
|
| 576 |
+
"shape": [
|
| 577 |
+
2048
|
| 578 |
+
],
|
| 579 |
+
"dtype": "float16",
|
| 580 |
+
"format": "f32-to-bf16",
|
| 581 |
+
"nbytes": 4096,
|
| 582 |
+
"byteOffset": 27271168
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"name": "model.layers.14.post_attention_layernorm.weight",
|
| 586 |
+
"shape": [
|
| 587 |
+
2048
|
| 588 |
+
],
|
| 589 |
+
"dtype": "float16",
|
| 590 |
+
"format": "f32-to-bf16",
|
| 591 |
+
"nbytes": 4096,
|
| 592 |
+
"byteOffset": 27275264
|
| 593 |
+
}
|
| 594 |
+
],
|
| 595 |
+
"md5sum": "071c71fc33170a2d3a1a2ae1f03b140d"
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"dataPath": "params_shard_19.bin",
|
| 599 |
+
"format": "raw-shard",
|
| 600 |
+
"nbytes": 67108864,
|
| 601 |
+
"records": [
|
| 602 |
+
{
|
| 603 |
+
"name": "model.layers.15.mlp.down_proj.weight",
|
| 604 |
+
"shape": [
|
| 605 |
+
2048,
|
| 606 |
+
16384
|
| 607 |
+
],
|
| 608 |
+
"dtype": "float16",
|
| 609 |
+
"format": "f32-to-bf16",
|
| 610 |
+
"nbytes": 67108864,
|
| 611 |
+
"byteOffset": 0
|
| 612 |
+
}
|
| 613 |
+
],
|
| 614 |
+
"md5sum": "b58913c0a9d042f1469b2c4929efb8d3"
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"dataPath": "params_shard_20.bin",
|
| 618 |
+
"format": "raw-shard",
|
| 619 |
+
"nbytes": 134217728,
|
| 620 |
+
"records": [
|
| 621 |
+
{
|
| 622 |
+
"name": "model.layers.15.mlp.gate_up_proj.weight",
|
| 623 |
+
"shape": [
|
| 624 |
+
32768,
|
| 625 |
+
2048
|
| 626 |
+
],
|
| 627 |
+
"dtype": "float16",
|
| 628 |
+
"format": "f32-to-bf16",
|
| 629 |
+
"nbytes": 134217728,
|
| 630 |
+
"byteOffset": 0
|
| 631 |
+
}
|
| 632 |
+
],
|
| 633 |
+
"md5sum": "7f3594a3e54595cf7f92b5901e0f6465"
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"dataPath": "params_shard_21.bin",
|
| 637 |
+
"format": "raw-shard",
|
| 638 |
+
"nbytes": 29368320,
|
| 639 |
+
"records": [
|
| 640 |
+
{
|
| 641 |
+
"name": "model.layers.14.self_attn.qkv_proj.weight",
|
| 642 |
+
"shape": [
|
| 643 |
+
2560,
|
| 644 |
+
2048
|
| 645 |
+
],
|
| 646 |
+
"dtype": "float16",
|
| 647 |
+
"format": "f32-to-bf16",
|
| 648 |
+
"nbytes": 10485760,
|
| 649 |
+
"byteOffset": 0
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"name": "model.layers.14.self_attn.o_proj.weight",
|
| 653 |
+
"shape": [
|
| 654 |
+
2048,
|
| 655 |
+
2048
|
| 656 |
+
],
|
| 657 |
+
"dtype": "float16",
|
| 658 |
+
"format": "f32-to-bf16",
|
| 659 |
+
"nbytes": 8388608,
|
| 660 |
+
"byteOffset": 10485760
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"name": "model.layers.15.input_layernorm.weight",
|
| 664 |
+
"shape": [
|
| 665 |
+
2048
|
| 666 |
+
],
|
| 667 |
+
"dtype": "float16",
|
| 668 |
+
"format": "f32-to-bf16",
|
| 669 |
+
"nbytes": 4096,
|
| 670 |
+
"byteOffset": 18874368
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"name": "model.layers.15.post_attention_layernorm.weight",
|
| 674 |
+
"shape": [
|
| 675 |
+
2048
|
| 676 |
+
],
|
| 677 |
+
"dtype": "float16",
|
| 678 |
+
"format": "f32-to-bf16",
|
| 679 |
+
"nbytes": 4096,
|
| 680 |
+
"byteOffset": 18878464
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"name": "model.layers.15.self_attn.qkv_proj.weight",
|
| 684 |
+
"shape": [
|
| 685 |
+
2560,
|
| 686 |
+
2048
|
| 687 |
+
],
|
| 688 |
+
"dtype": "float16",
|
| 689 |
+
"format": "f32-to-bf16",
|
| 690 |
+
"nbytes": 10485760,
|
| 691 |
+
"byteOffset": 18882560
|
| 692 |
+
}
|
| 693 |
+
],
|
| 694 |
+
"md5sum": "b7c100b48dd50547c5c74f03a68863aa"
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"dataPath": "params_shard_22.bin",
|
| 698 |
+
"format": "raw-shard",
|
| 699 |
+
"nbytes": 67108864,
|
| 700 |
+
"records": [
|
| 701 |
+
{
|
| 702 |
+
"name": "model.layers.16.mlp.down_proj.weight",
|
| 703 |
+
"shape": [
|
| 704 |
+
2048,
|
| 705 |
+
16384
|
| 706 |
+
],
|
| 707 |
+
"dtype": "float16",
|
| 708 |
+
"format": "f32-to-bf16",
|
| 709 |
+
"nbytes": 67108864,
|
| 710 |
+
"byteOffset": 0
|
| 711 |
+
}
|
| 712 |
+
],
|
| 713 |
+
"md5sum": "497e575ba76a1ae6e33393fd7c9c4c12"
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"dataPath": "params_shard_23.bin",
|
| 717 |
+
"format": "raw-shard",
|
| 718 |
+
"nbytes": 134217728,
|
| 719 |
+
"records": [
|
| 720 |
+
{
|
| 721 |
+
"name": "model.layers.16.mlp.gate_up_proj.weight",
|
| 722 |
+
"shape": [
|
| 723 |
+
32768,
|
| 724 |
+
2048
|
| 725 |
+
],
|
| 726 |
+
"dtype": "float16",
|
| 727 |
+
"format": "f32-to-bf16",
|
| 728 |
+
"nbytes": 134217728,
|
| 729 |
+
"byteOffset": 0
|
| 730 |
+
}
|
| 731 |
+
],
|
| 732 |
+
"md5sum": "7e13a326187148b0ea54878998af1dbe"
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"dataPath": "params_shard_24.bin",
|
| 736 |
+
"format": "raw-shard",
|
| 737 |
+
"nbytes": 134217728,
|
| 738 |
+
"records": [
|
| 739 |
+
{
|
| 740 |
+
"name": "model.layers.17.mlp.gate_up_proj.weight",
|
| 741 |
+
"shape": [
|
| 742 |
+
32768,
|
| 743 |
+
2048
|
| 744 |
+
],
|
| 745 |
+
"dtype": "float16",
|
| 746 |
+
"format": "f32-to-bf16",
|
| 747 |
+
"nbytes": 134217728,
|
| 748 |
+
"byteOffset": 0
|
| 749 |
+
}
|
| 750 |
+
],
|
| 751 |
+
"md5sum": "3e8d823c128094965bc0b63996bd30e0"
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"dataPath": "params_shard_25.bin",
|
| 755 |
+
"format": "raw-shard",
|
| 756 |
+
"nbytes": 27271168,
|
| 757 |
+
"records": [
|
| 758 |
+
{
|
| 759 |
+
"name": "model.layers.15.self_attn.o_proj.weight",
|
| 760 |
+
"shape": [
|
| 761 |
+
2048,
|
| 762 |
+
2048
|
| 763 |
+
],
|
| 764 |
+
"dtype": "float16",
|
| 765 |
+
"format": "f32-to-bf16",
|
| 766 |
+
"nbytes": 8388608,
|
| 767 |
+
"byteOffset": 0
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"name": "model.layers.16.input_layernorm.weight",
|
| 771 |
+
"shape": [
|
| 772 |
+
2048
|
| 773 |
+
],
|
| 774 |
+
"dtype": "float16",
|
| 775 |
+
"format": "f32-to-bf16",
|
| 776 |
+
"nbytes": 4096,
|
| 777 |
+
"byteOffset": 8388608
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"name": "model.layers.16.post_attention_layernorm.weight",
|
| 781 |
+
"shape": [
|
| 782 |
+
2048
|
| 783 |
+
],
|
| 784 |
+
"dtype": "float16",
|
| 785 |
+
"format": "f32-to-bf16",
|
| 786 |
+
"nbytes": 4096,
|
| 787 |
+
"byteOffset": 8392704
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"name": "model.layers.16.self_attn.qkv_proj.weight",
|
| 791 |
+
"shape": [
|
| 792 |
+
2560,
|
| 793 |
+
2048
|
| 794 |
+
],
|
| 795 |
+
"dtype": "float16",
|
| 796 |
+
"format": "f32-to-bf16",
|
| 797 |
+
"nbytes": 10485760,
|
| 798 |
+
"byteOffset": 8396800
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"name": "model.layers.16.self_attn.o_proj.weight",
|
| 802 |
+
"shape": [
|
| 803 |
+
2048,
|
| 804 |
+
2048
|
| 805 |
+
],
|
| 806 |
+
"dtype": "float16",
|
| 807 |
+
"format": "f32-to-bf16",
|
| 808 |
+
"nbytes": 8388608,
|
| 809 |
+
"byteOffset": 18882560
|
| 810 |
+
}
|
| 811 |
+
],
|
| 812 |
+
"md5sum": "c51345fdd445c9c55206b86ee31d704a"
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"dataPath": "params_shard_26.bin",
|
| 816 |
+
"format": "raw-shard",
|
| 817 |
+
"nbytes": 67108864,
|
| 818 |
+
"records": [
|
| 819 |
+
{
|
| 820 |
+
"name": "model.layers.2.mlp.down_proj.weight",
|
| 821 |
+
"shape": [
|
| 822 |
+
2048,
|
| 823 |
+
16384
|
| 824 |
+
],
|
| 825 |
+
"dtype": "float16",
|
| 826 |
+
"format": "f32-to-bf16",
|
| 827 |
+
"nbytes": 67108864,
|
| 828 |
+
"byteOffset": 0
|
| 829 |
+
}
|
| 830 |
+
],
|
| 831 |
+
"md5sum": "708872d176d1deddd88435c817e93d2f"
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"dataPath": "params_shard_27.bin",
|
| 835 |
+
"format": "raw-shard",
|
| 836 |
+
"nbytes": 134217728,
|
| 837 |
+
"records": [
|
| 838 |
+
{
|
| 839 |
+
"name": "model.layers.2.mlp.gate_up_proj.weight",
|
| 840 |
+
"shape": [
|
| 841 |
+
32768,
|
| 842 |
+
2048
|
| 843 |
+
],
|
| 844 |
+
"dtype": "float16",
|
| 845 |
+
"format": "f32-to-bf16",
|
| 846 |
+
"nbytes": 134217728,
|
| 847 |
+
"byteOffset": 0
|
| 848 |
+
}
|
| 849 |
+
],
|
| 850 |
+
"md5sum": "0eef3929b28890b79faf9d02dfa2487f"
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"dataPath": "params_shard_28.bin",
|
| 854 |
+
"format": "raw-shard",
|
| 855 |
+
"nbytes": 29368320,
|
| 856 |
+
"records": [
|
| 857 |
+
{
|
| 858 |
+
"name": "model.layers.17.self_attn.qkv_proj.weight",
|
| 859 |
+
"shape": [
|
| 860 |
+
2560,
|
| 861 |
+
2048
|
| 862 |
+
],
|
| 863 |
+
"dtype": "float16",
|
| 864 |
+
"format": "f32-to-bf16",
|
| 865 |
+
"nbytes": 10485760,
|
| 866 |
+
"byteOffset": 0
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"name": "model.layers.17.self_attn.o_proj.weight",
|
| 870 |
+
"shape": [
|
| 871 |
+
2048,
|
| 872 |
+
2048
|
| 873 |
+
],
|
| 874 |
+
"dtype": "float16",
|
| 875 |
+
"format": "f32-to-bf16",
|
| 876 |
+
"nbytes": 8388608,
|
| 877 |
+
"byteOffset": 10485760
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"name": "model.layers.2.input_layernorm.weight",
|
| 881 |
+
"shape": [
|
| 882 |
+
2048
|
| 883 |
+
],
|
| 884 |
+
"dtype": "float16",
|
| 885 |
+
"format": "f32-to-bf16",
|
| 886 |
+
"nbytes": 4096,
|
| 887 |
+
"byteOffset": 18874368
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"name": "model.layers.2.post_attention_layernorm.weight",
|
| 891 |
+
"shape": [
|
| 892 |
+
2048
|
| 893 |
+
],
|
| 894 |
+
"dtype": "float16",
|
| 895 |
+
"format": "f32-to-bf16",
|
| 896 |
+
"nbytes": 4096,
|
| 897 |
+
"byteOffset": 18878464
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"name": "model.layers.2.self_attn.qkv_proj.weight",
|
| 901 |
+
"shape": [
|
| 902 |
+
2560,
|
| 903 |
+
2048
|
| 904 |
+
],
|
| 905 |
+
"dtype": "float16",
|
| 906 |
+
"format": "f32-to-bf16",
|
| 907 |
+
"nbytes": 10485760,
|
| 908 |
+
"byteOffset": 18882560
|
| 909 |
+
}
|
| 910 |
+
],
|
| 911 |
+
"md5sum": "6328df0ffee1d1160e0fc6fa300f4c9a"
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"dataPath": "params_shard_29.bin",
|
| 915 |
+
"format": "raw-shard",
|
| 916 |
+
"nbytes": 67108864,
|
| 917 |
+
"records": [
|
| 918 |
+
{
|
| 919 |
+
"name": "model.layers.3.mlp.down_proj.weight",
|
| 920 |
+
"shape": [
|
| 921 |
+
2048,
|
| 922 |
+
16384
|
| 923 |
+
],
|
| 924 |
+
"dtype": "float16",
|
| 925 |
+
"format": "f32-to-bf16",
|
| 926 |
+
"nbytes": 67108864,
|
| 927 |
+
"byteOffset": 0
|
| 928 |
+
}
|
| 929 |
+
],
|
| 930 |
+
"md5sum": "30f748096a7ec18a6e349c49a7d14822"
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"dataPath": "params_shard_30.bin",
|
| 934 |
+
"format": "raw-shard",
|
| 935 |
+
"nbytes": 134217728,
|
| 936 |
+
"records": [
|
| 937 |
+
{
|
| 938 |
+
"name": "model.layers.3.mlp.gate_up_proj.weight",
|
| 939 |
+
"shape": [
|
| 940 |
+
32768,
|
| 941 |
+
2048
|
| 942 |
+
],
|
| 943 |
+
"dtype": "float16",
|
| 944 |
+
"format": "f32-to-bf16",
|
| 945 |
+
"nbytes": 134217728,
|
| 946 |
+
"byteOffset": 0
|
| 947 |
+
}
|
| 948 |
+
],
|
| 949 |
+
"md5sum": "a15a4fe50c6c5b78f36ec6351732a345"
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"dataPath": "params_shard_31.bin",
|
| 953 |
+
"format": "raw-shard",
|
| 954 |
+
"nbytes": 67108864,
|
| 955 |
+
"records": [
|
| 956 |
+
{
|
| 957 |
+
"name": "model.layers.4.mlp.down_proj.weight",
|
| 958 |
+
"shape": [
|
| 959 |
+
2048,
|
| 960 |
+
16384
|
| 961 |
+
],
|
| 962 |
+
"dtype": "float16",
|
| 963 |
+
"format": "f32-to-bf16",
|
| 964 |
+
"nbytes": 67108864,
|
| 965 |
+
"byteOffset": 0
|
| 966 |
+
}
|
| 967 |
+
],
|
| 968 |
+
"md5sum": "5b697bbb99453187d0eee6b6127d2008"
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"dataPath": "params_shard_32.bin",
|
| 972 |
+
"format": "raw-shard",
|
| 973 |
+
"nbytes": 134217728,
|
| 974 |
+
"records": [
|
| 975 |
+
{
|
| 976 |
+
"name": "model.layers.4.mlp.gate_up_proj.weight",
|
| 977 |
+
"shape": [
|
| 978 |
+
32768,
|
| 979 |
+
2048
|
| 980 |
+
],
|
| 981 |
+
"dtype": "float16",
|
| 982 |
+
"format": "f32-to-bf16",
|
| 983 |
+
"nbytes": 134217728,
|
| 984 |
+
"byteOffset": 0
|
| 985 |
+
}
|
| 986 |
+
],
|
| 987 |
+
"md5sum": "76327282d65a9c80614e17129cb9e5f2"
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"dataPath": "params_shard_33.bin",
|
| 991 |
+
"format": "raw-shard",
|
| 992 |
+
"nbytes": 27279360,
|
| 993 |
+
"records": [
|
| 994 |
+
{
|
| 995 |
+
"name": "model.layers.2.self_attn.o_proj.weight",
|
| 996 |
+
"shape": [
|
| 997 |
+
2048,
|
| 998 |
+
2048
|
| 999 |
+
],
|
| 1000 |
+
"dtype": "float16",
|
| 1001 |
+
"format": "f32-to-bf16",
|
| 1002 |
+
"nbytes": 8388608,
|
| 1003 |
+
"byteOffset": 0
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"name": "model.layers.3.input_layernorm.weight",
|
| 1007 |
+
"shape": [
|
| 1008 |
+
2048
|
| 1009 |
+
],
|
| 1010 |
+
"dtype": "float16",
|
| 1011 |
+
"format": "f32-to-bf16",
|
| 1012 |
+
"nbytes": 4096,
|
| 1013 |
+
"byteOffset": 8388608
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"name": "model.layers.3.post_attention_layernorm.weight",
|
| 1017 |
+
"shape": [
|
| 1018 |
+
2048
|
| 1019 |
+
],
|
| 1020 |
+
"dtype": "float16",
|
| 1021 |
+
"format": "f32-to-bf16",
|
| 1022 |
+
"nbytes": 4096,
|
| 1023 |
+
"byteOffset": 8392704
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"name": "model.layers.3.self_attn.qkv_proj.weight",
|
| 1027 |
+
"shape": [
|
| 1028 |
+
2560,
|
| 1029 |
+
2048
|
| 1030 |
+
],
|
| 1031 |
+
"dtype": "float16",
|
| 1032 |
+
"format": "f32-to-bf16",
|
| 1033 |
+
"nbytes": 10485760,
|
| 1034 |
+
"byteOffset": 8396800
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"name": "model.layers.3.self_attn.o_proj.weight",
|
| 1038 |
+
"shape": [
|
| 1039 |
+
2048,
|
| 1040 |
+
2048
|
| 1041 |
+
],
|
| 1042 |
+
"dtype": "float16",
|
| 1043 |
+
"format": "f32-to-bf16",
|
| 1044 |
+
"nbytes": 8388608,
|
| 1045 |
+
"byteOffset": 18882560
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"name": "model.layers.4.input_layernorm.weight",
|
| 1049 |
+
"shape": [
|
| 1050 |
+
2048
|
| 1051 |
+
],
|
| 1052 |
+
"dtype": "float16",
|
| 1053 |
+
"format": "f32-to-bf16",
|
| 1054 |
+
"nbytes": 4096,
|
| 1055 |
+
"byteOffset": 27271168
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"name": "model.layers.4.post_attention_layernorm.weight",
|
| 1059 |
+
"shape": [
|
| 1060 |
+
2048
|
| 1061 |
+
],
|
| 1062 |
+
"dtype": "float16",
|
| 1063 |
+
"format": "f32-to-bf16",
|
| 1064 |
+
"nbytes": 4096,
|
| 1065 |
+
"byteOffset": 27275264
|
| 1066 |
+
}
|
| 1067 |
+
],
|
| 1068 |
+
"md5sum": "1f73ecde85ffc44fa98fba7534c55356"
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"dataPath": "params_shard_34.bin",
|
| 1072 |
+
"format": "raw-shard",
|
| 1073 |
+
"nbytes": 67108864,
|
| 1074 |
+
"records": [
|
| 1075 |
+
{
|
| 1076 |
+
"name": "model.layers.5.mlp.down_proj.weight",
|
| 1077 |
+
"shape": [
|
| 1078 |
+
2048,
|
| 1079 |
+
16384
|
| 1080 |
+
],
|
| 1081 |
+
"dtype": "float16",
|
| 1082 |
+
"format": "f32-to-bf16",
|
| 1083 |
+
"nbytes": 67108864,
|
| 1084 |
+
"byteOffset": 0
|
| 1085 |
+
}
|
| 1086 |
+
],
|
| 1087 |
+
"md5sum": "c983dfde03cb18ee85a7d80d50f4d165"
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"dataPath": "params_shard_35.bin",
|
| 1091 |
+
"format": "raw-shard",
|
| 1092 |
+
"nbytes": 134217728,
|
| 1093 |
+
"records": [
|
| 1094 |
+
{
|
| 1095 |
+
"name": "model.layers.5.mlp.gate_up_proj.weight",
|
| 1096 |
+
"shape": [
|
| 1097 |
+
32768,
|
| 1098 |
+
2048
|
| 1099 |
+
],
|
| 1100 |
+
"dtype": "float16",
|
| 1101 |
+
"format": "f32-to-bf16",
|
| 1102 |
+
"nbytes": 134217728,
|
| 1103 |
+
"byteOffset": 0
|
| 1104 |
+
}
|
| 1105 |
+
],
|
| 1106 |
+
"md5sum": "afb45d7056b90f804e2c75489be5792e"
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"dataPath": "params_shard_36.bin",
|
| 1110 |
+
"format": "raw-shard",
|
| 1111 |
+
"nbytes": 29368320,
|
| 1112 |
+
"records": [
|
| 1113 |
+
{
|
| 1114 |
+
"name": "model.layers.4.self_attn.qkv_proj.weight",
|
| 1115 |
+
"shape": [
|
| 1116 |
+
2560,
|
| 1117 |
+
2048
|
| 1118 |
+
],
|
| 1119 |
+
"dtype": "float16",
|
| 1120 |
+
"format": "f32-to-bf16",
|
| 1121 |
+
"nbytes": 10485760,
|
| 1122 |
+
"byteOffset": 0
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"name": "model.layers.4.self_attn.o_proj.weight",
|
| 1126 |
+
"shape": [
|
| 1127 |
+
2048,
|
| 1128 |
+
2048
|
| 1129 |
+
],
|
| 1130 |
+
"dtype": "float16",
|
| 1131 |
+
"format": "f32-to-bf16",
|
| 1132 |
+
"nbytes": 8388608,
|
| 1133 |
+
"byteOffset": 10485760
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"name": "model.layers.5.input_layernorm.weight",
|
| 1137 |
+
"shape": [
|
| 1138 |
+
2048
|
| 1139 |
+
],
|
| 1140 |
+
"dtype": "float16",
|
| 1141 |
+
"format": "f32-to-bf16",
|
| 1142 |
+
"nbytes": 4096,
|
| 1143 |
+
"byteOffset": 18874368
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"name": "model.layers.5.post_attention_layernorm.weight",
|
| 1147 |
+
"shape": [
|
| 1148 |
+
2048
|
| 1149 |
+
],
|
| 1150 |
+
"dtype": "float16",
|
| 1151 |
+
"format": "f32-to-bf16",
|
| 1152 |
+
"nbytes": 4096,
|
| 1153 |
+
"byteOffset": 18878464
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"name": "model.layers.5.self_attn.qkv_proj.weight",
|
| 1157 |
+
"shape": [
|
| 1158 |
+
2560,
|
| 1159 |
+
2048
|
| 1160 |
+
],
|
| 1161 |
+
"dtype": "float16",
|
| 1162 |
+
"format": "f32-to-bf16",
|
| 1163 |
+
"nbytes": 10485760,
|
| 1164 |
+
"byteOffset": 18882560
|
| 1165 |
+
}
|
| 1166 |
+
],
|
| 1167 |
+
"md5sum": "a8c9cd2cc4d6179ffa0d181051ef4f7e"
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"dataPath": "params_shard_37.bin",
|
| 1171 |
+
"format": "raw-shard",
|
| 1172 |
+
"nbytes": 67108864,
|
| 1173 |
+
"records": [
|
| 1174 |
+
{
|
| 1175 |
+
"name": "model.layers.6.mlp.down_proj.weight",
|
| 1176 |
+
"shape": [
|
| 1177 |
+
2048,
|
| 1178 |
+
16384
|
| 1179 |
+
],
|
| 1180 |
+
"dtype": "float16",
|
| 1181 |
+
"format": "f32-to-bf16",
|
| 1182 |
+
"nbytes": 67108864,
|
| 1183 |
+
"byteOffset": 0
|
| 1184 |
+
}
|
| 1185 |
+
],
|
| 1186 |
+
"md5sum": "89e90749de11be2bc1ee29c5450a4f3d"
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"dataPath": "params_shard_38.bin",
|
| 1190 |
+
"format": "raw-shard",
|
| 1191 |
+
"nbytes": 134217728,
|
| 1192 |
+
"records": [
|
| 1193 |
+
{
|
| 1194 |
+
"name": "model.layers.6.mlp.gate_up_proj.weight",
|
| 1195 |
+
"shape": [
|
| 1196 |
+
32768,
|
| 1197 |
+
2048
|
| 1198 |
+
],
|
| 1199 |
+
"dtype": "float16",
|
| 1200 |
+
"format": "f32-to-bf16",
|
| 1201 |
+
"nbytes": 134217728,
|
| 1202 |
+
"byteOffset": 0
|
| 1203 |
+
}
|
| 1204 |
+
],
|
| 1205 |
+
"md5sum": "bde36e490b2c3a905f40e1285f4873dd"
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"dataPath": "params_shard_39.bin",
|
| 1209 |
+
"format": "raw-shard",
|
| 1210 |
+
"nbytes": 67108864,
|
| 1211 |
+
"records": [
|
| 1212 |
+
{
|
| 1213 |
+
"name": "model.layers.7.mlp.down_proj.weight",
|
| 1214 |
+
"shape": [
|
| 1215 |
+
2048,
|
| 1216 |
+
16384
|
| 1217 |
+
],
|
| 1218 |
+
"dtype": "float16",
|
| 1219 |
+
"format": "f32-to-bf16",
|
| 1220 |
+
"nbytes": 67108864,
|
| 1221 |
+
"byteOffset": 0
|
| 1222 |
+
}
|
| 1223 |
+
],
|
| 1224 |
+
"md5sum": "eefc32a2ccf311c1a95e01ca979aaa9f"
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"dataPath": "params_shard_40.bin",
|
| 1228 |
+
"format": "raw-shard",
|
| 1229 |
+
"nbytes": 134217728,
|
| 1230 |
+
"records": [
|
| 1231 |
+
{
|
| 1232 |
+
"name": "model.layers.7.mlp.gate_up_proj.weight",
|
| 1233 |
+
"shape": [
|
| 1234 |
+
32768,
|
| 1235 |
+
2048
|
| 1236 |
+
],
|
| 1237 |
+
"dtype": "float16",
|
| 1238 |
+
"format": "f32-to-bf16",
|
| 1239 |
+
"nbytes": 134217728,
|
| 1240 |
+
"byteOffset": 0
|
| 1241 |
+
}
|
| 1242 |
+
],
|
| 1243 |
+
"md5sum": "c31b3371a8c2294135e993653a25d153"
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"dataPath": "params_shard_41.bin",
|
| 1247 |
+
"format": "raw-shard",
|
| 1248 |
+
"nbytes": 27279360,
|
| 1249 |
+
"records": [
|
| 1250 |
+
{
|
| 1251 |
+
"name": "model.layers.5.self_attn.o_proj.weight",
|
| 1252 |
+
"shape": [
|
| 1253 |
+
2048,
|
| 1254 |
+
2048
|
| 1255 |
+
],
|
| 1256 |
+
"dtype": "float16",
|
| 1257 |
+
"format": "f32-to-bf16",
|
| 1258 |
+
"nbytes": 8388608,
|
| 1259 |
+
"byteOffset": 0
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"name": "model.layers.6.input_layernorm.weight",
|
| 1263 |
+
"shape": [
|
| 1264 |
+
2048
|
| 1265 |
+
],
|
| 1266 |
+
"dtype": "float16",
|
| 1267 |
+
"format": "f32-to-bf16",
|
| 1268 |
+
"nbytes": 4096,
|
| 1269 |
+
"byteOffset": 8388608
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"name": "model.layers.6.post_attention_layernorm.weight",
|
| 1273 |
+
"shape": [
|
| 1274 |
+
2048
|
| 1275 |
+
],
|
| 1276 |
+
"dtype": "float16",
|
| 1277 |
+
"format": "f32-to-bf16",
|
| 1278 |
+
"nbytes": 4096,
|
| 1279 |
+
"byteOffset": 8392704
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"name": "model.layers.6.self_attn.qkv_proj.weight",
|
| 1283 |
+
"shape": [
|
| 1284 |
+
2560,
|
| 1285 |
+
2048
|
| 1286 |
+
],
|
| 1287 |
+
"dtype": "float16",
|
| 1288 |
+
"format": "f32-to-bf16",
|
| 1289 |
+
"nbytes": 10485760,
|
| 1290 |
+
"byteOffset": 8396800
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"name": "model.layers.6.self_attn.o_proj.weight",
|
| 1294 |
+
"shape": [
|
| 1295 |
+
2048,
|
| 1296 |
+
2048
|
| 1297 |
+
],
|
| 1298 |
+
"dtype": "float16",
|
| 1299 |
+
"format": "f32-to-bf16",
|
| 1300 |
+
"nbytes": 8388608,
|
| 1301 |
+
"byteOffset": 18882560
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"name": "model.layers.7.input_layernorm.weight",
|
| 1305 |
+
"shape": [
|
| 1306 |
+
2048
|
| 1307 |
+
],
|
| 1308 |
+
"dtype": "float16",
|
| 1309 |
+
"format": "f32-to-bf16",
|
| 1310 |
+
"nbytes": 4096,
|
| 1311 |
+
"byteOffset": 27271168
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"name": "model.layers.7.post_attention_layernorm.weight",
|
| 1315 |
+
"shape": [
|
| 1316 |
+
2048
|
| 1317 |
+
],
|
| 1318 |
+
"dtype": "float16",
|
| 1319 |
+
"format": "f32-to-bf16",
|
| 1320 |
+
"nbytes": 4096,
|
| 1321 |
+
"byteOffset": 27275264
|
| 1322 |
+
}
|
| 1323 |
+
],
|
| 1324 |
+
"md5sum": "a9a738d8b541d5d1517049e641a72c6f"
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"dataPath": "params_shard_42.bin",
|
| 1328 |
+
"format": "raw-shard",
|
| 1329 |
+
"nbytes": 67108864,
|
| 1330 |
+
"records": [
|
| 1331 |
+
{
|
| 1332 |
+
"name": "model.layers.8.mlp.down_proj.weight",
|
| 1333 |
+
"shape": [
|
| 1334 |
+
2048,
|
| 1335 |
+
16384
|
| 1336 |
+
],
|
| 1337 |
+
"dtype": "float16",
|
| 1338 |
+
"format": "f32-to-bf16",
|
| 1339 |
+
"nbytes": 67108864,
|
| 1340 |
+
"byteOffset": 0
|
| 1341 |
+
}
|
| 1342 |
+
],
|
| 1343 |
+
"md5sum": "b4d55621d295f8693b39a501ea581847"
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"dataPath": "params_shard_43.bin",
|
| 1347 |
+
"format": "raw-shard",
|
| 1348 |
+
"nbytes": 134217728,
|
| 1349 |
+
"records": [
|
| 1350 |
+
{
|
| 1351 |
+
"name": "model.layers.8.mlp.gate_up_proj.weight",
|
| 1352 |
+
"shape": [
|
| 1353 |
+
32768,
|
| 1354 |
+
2048
|
| 1355 |
+
],
|
| 1356 |
+
"dtype": "float16",
|
| 1357 |
+
"format": "f32-to-bf16",
|
| 1358 |
+
"nbytes": 134217728,
|
| 1359 |
+
"byteOffset": 0
|
| 1360 |
+
}
|
| 1361 |
+
],
|
| 1362 |
+
"md5sum": "1031e7308cb30a67747b65b4fdaa94af"
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"dataPath": "params_shard_44.bin",
|
| 1366 |
+
"format": "raw-shard",
|
| 1367 |
+
"nbytes": 29368320,
|
| 1368 |
+
"records": [
|
| 1369 |
+
{
|
| 1370 |
+
"name": "model.layers.7.self_attn.qkv_proj.weight",
|
| 1371 |
+
"shape": [
|
| 1372 |
+
2560,
|
| 1373 |
+
2048
|
| 1374 |
+
],
|
| 1375 |
+
"dtype": "float16",
|
| 1376 |
+
"format": "f32-to-bf16",
|
| 1377 |
+
"nbytes": 10485760,
|
| 1378 |
+
"byteOffset": 0
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"name": "model.layers.7.self_attn.o_proj.weight",
|
| 1382 |
+
"shape": [
|
| 1383 |
+
2048,
|
| 1384 |
+
2048
|
| 1385 |
+
],
|
| 1386 |
+
"dtype": "float16",
|
| 1387 |
+
"format": "f32-to-bf16",
|
| 1388 |
+
"nbytes": 8388608,
|
| 1389 |
+
"byteOffset": 10485760
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"name": "model.layers.8.input_layernorm.weight",
|
| 1393 |
+
"shape": [
|
| 1394 |
+
2048
|
| 1395 |
+
],
|
| 1396 |
+
"dtype": "float16",
|
| 1397 |
+
"format": "f32-to-bf16",
|
| 1398 |
+
"nbytes": 4096,
|
| 1399 |
+
"byteOffset": 18874368
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"name": "model.layers.8.post_attention_layernorm.weight",
|
| 1403 |
+
"shape": [
|
| 1404 |
+
2048
|
| 1405 |
+
],
|
| 1406 |
+
"dtype": "float16",
|
| 1407 |
+
"format": "f32-to-bf16",
|
| 1408 |
+
"nbytes": 4096,
|
| 1409 |
+
"byteOffset": 18878464
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"name": "model.layers.8.self_attn.qkv_proj.weight",
|
| 1413 |
+
"shape": [
|
| 1414 |
+
2560,
|
| 1415 |
+
2048
|
| 1416 |
+
],
|
| 1417 |
+
"dtype": "float16",
|
| 1418 |
+
"format": "f32-to-bf16",
|
| 1419 |
+
"nbytes": 10485760,
|
| 1420 |
+
"byteOffset": 18882560
|
| 1421 |
+
}
|
| 1422 |
+
],
|
| 1423 |
+
"md5sum": "f74050232fb038c2c717ca99af7cdada"
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"dataPath": "params_shard_45.bin",
|
| 1427 |
+
"format": "raw-shard",
|
| 1428 |
+
"nbytes": 67108864,
|
| 1429 |
+
"records": [
|
| 1430 |
+
{
|
| 1431 |
+
"name": "model.layers.9.mlp.down_proj.weight",
|
| 1432 |
+
"shape": [
|
| 1433 |
+
2048,
|
| 1434 |
+
16384
|
| 1435 |
+
],
|
| 1436 |
+
"dtype": "float16",
|
| 1437 |
+
"format": "f32-to-bf16",
|
| 1438 |
+
"nbytes": 67108864,
|
| 1439 |
+
"byteOffset": 0
|
| 1440 |
+
}
|
| 1441 |
+
],
|
| 1442 |
+
"md5sum": "2639e2fc57901dac06e9d4183ce2ee34"
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"dataPath": "params_shard_46.bin",
|
| 1446 |
+
"format": "raw-shard",
|
| 1447 |
+
"nbytes": 134217728,
|
| 1448 |
+
"records": [
|
| 1449 |
+
{
|
| 1450 |
+
"name": "model.layers.9.mlp.gate_up_proj.weight",
|
| 1451 |
+
"shape": [
|
| 1452 |
+
32768,
|
| 1453 |
+
2048
|
| 1454 |
+
],
|
| 1455 |
+
"dtype": "float16",
|
| 1456 |
+
"format": "f32-to-bf16",
|
| 1457 |
+
"nbytes": 134217728,
|
| 1458 |
+
"byteOffset": 0
|
| 1459 |
+
}
|
| 1460 |
+
],
|
| 1461 |
+
"md5sum": "cdcce0c795b9df58125fb24aa22f62e8"
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"dataPath": "params_shard_47.bin",
|
| 1465 |
+
"format": "raw-shard",
|
| 1466 |
+
"nbytes": 67108864,
|
| 1467 |
+
"records": [
|
| 1468 |
+
{
|
| 1469 |
+
"name": "model.layers.17.mlp.down_proj.weight",
|
| 1470 |
+
"shape": [
|
| 1471 |
+
2048,
|
| 1472 |
+
16384
|
| 1473 |
+
],
|
| 1474 |
+
"dtype": "float16",
|
| 1475 |
+
"format": "f32-to-bf16",
|
| 1476 |
+
"nbytes": 67108864,
|
| 1477 |
+
"byteOffset": 0
|
| 1478 |
+
}
|
| 1479 |
+
],
|
| 1480 |
+
"md5sum": "135969d29acd56ae5e9ac553cb476528"
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"dataPath": "params_shard_48.bin",
|
| 1484 |
+
"format": "raw-shard",
|
| 1485 |
+
"nbytes": 27283456,
|
| 1486 |
+
"records": [
|
| 1487 |
+
{
|
| 1488 |
+
"name": "model.layers.8.self_attn.o_proj.weight",
|
| 1489 |
+
"shape": [
|
| 1490 |
+
2048,
|
| 1491 |
+
2048
|
| 1492 |
+
],
|
| 1493 |
+
"dtype": "float16",
|
| 1494 |
+
"format": "f32-to-bf16",
|
| 1495 |
+
"nbytes": 8388608,
|
| 1496 |
+
"byteOffset": 0
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"name": "model.layers.9.input_layernorm.weight",
|
| 1500 |
+
"shape": [
|
| 1501 |
+
2048
|
| 1502 |
+
],
|
| 1503 |
+
"dtype": "float16",
|
| 1504 |
+
"format": "f32-to-bf16",
|
| 1505 |
+
"nbytes": 4096,
|
| 1506 |
+
"byteOffset": 8388608
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"name": "model.layers.9.post_attention_layernorm.weight",
|
| 1510 |
+
"shape": [
|
| 1511 |
+
2048
|
| 1512 |
+
],
|
| 1513 |
+
"dtype": "float16",
|
| 1514 |
+
"format": "f32-to-bf16",
|
| 1515 |
+
"nbytes": 4096,
|
| 1516 |
+
"byteOffset": 8392704
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"name": "model.layers.9.self_attn.qkv_proj.weight",
|
| 1520 |
+
"shape": [
|
| 1521 |
+
2560,
|
| 1522 |
+
2048
|
| 1523 |
+
],
|
| 1524 |
+
"dtype": "float16",
|
| 1525 |
+
"format": "f32-to-bf16",
|
| 1526 |
+
"nbytes": 10485760,
|
| 1527 |
+
"byteOffset": 8396800
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"name": "model.layers.9.self_attn.o_proj.weight",
|
| 1531 |
+
"shape": [
|
| 1532 |
+
2048,
|
| 1533 |
+
2048
|
| 1534 |
+
],
|
| 1535 |
+
"dtype": "float16",
|
| 1536 |
+
"format": "f32-to-bf16",
|
| 1537 |
+
"nbytes": 8388608,
|
| 1538 |
+
"byteOffset": 18882560
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"name": "model.layers.17.input_layernorm.weight",
|
| 1542 |
+
"shape": [
|
| 1543 |
+
2048
|
| 1544 |
+
],
|
| 1545 |
+
"dtype": "float16",
|
| 1546 |
+
"format": "f32-to-bf16",
|
| 1547 |
+
"nbytes": 4096,
|
| 1548 |
+
"byteOffset": 27271168
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"name": "model.layers.17.post_attention_layernorm.weight",
|
| 1552 |
+
"shape": [
|
| 1553 |
+
2048
|
| 1554 |
+
],
|
| 1555 |
+
"dtype": "float16",
|
| 1556 |
+
"format": "f32-to-bf16",
|
| 1557 |
+
"nbytes": 4096,
|
| 1558 |
+
"byteOffset": 27275264
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"name": "model.norm.weight",
|
| 1562 |
+
"shape": [
|
| 1563 |
+
2048
|
| 1564 |
+
],
|
| 1565 |
+
"dtype": "float16",
|
| 1566 |
+
"format": "f32-to-bf16",
|
| 1567 |
+
"nbytes": 4096,
|
| 1568 |
+
"byteOffset": 27279360
|
| 1569 |
+
}
|
| 1570 |
+
],
|
| 1571 |
+
"md5sum": "7bca8fca53ef5ba8a977e4733d66824a"
|
| 1572 |
+
}
|
| 1573 |
+
]
|
| 1574 |
+
}
|
params_shard_0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17b87ab2c01c80657855a5413d0457b4a041afaeda0cc785080e44e2f04acf07
|
| 3 |
+
size 1048576000
|
params_shard_1.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2feb5eb3d572c57c5bafbf0ab506862df1160fe40965dcfe4b9fd855c08bed7
|
| 3 |
+
size 67108864
|
params_shard_10.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4288cfe3944cd6191f94ae6fd63104118d42b835452603ecb0f5e696e981c581
|
| 3 |
+
size 27279360
|
params_shard_11.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d10c790a4e3dc44c2dc36d96251ae97cdf30a4fa04d4c43e31bfbd038e6a7b7
|
| 3 |
+
size 67108864
|
params_shard_12.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:929a0a900fe314ea93709c197a4445238dba61029cf0af354bc16288e5c84677
|
| 3 |
+
size 134217728
|
params_shard_13.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72e09274b0fa41657ace50d78b2207c9dc4cf4406da769866baf5c33515f0b69
|
| 3 |
+
size 29368320
|
params_shard_14.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a07d3abbfcacf48ba028df2cab895be32cc15022d23389a745286e79c1b1d1fd
|
| 3 |
+
size 67108864
|
params_shard_15.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8cbd5f35ffa92cacb31f6207322b6c168c574685ad853e77aacb99578d7c7fb
|
| 3 |
+
size 134217728
|
params_shard_16.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef6694dff1e05820aac0cd2b22f39ac7788b4967afc9250775575554c66aab2c
|
| 3 |
+
size 67108864
|
params_shard_17.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84f1d49021144f3b5c1adb13f87eb0fd517b5a686694621efe9a0a00982c517e
|
| 3 |
+
size 134217728
|
params_shard_18.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:965a1e20c10241269df95ed52b8e0d5a93e9e025fbe2f34263c72c5bf6bb8b7c
|
| 3 |
+
size 27279360
|
params_shard_19.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d02eb439da852246d2ca67e9b7b6de0b090b80744355e64728a23e41926505b
|
| 3 |
+
size 67108864
|
params_shard_2.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c82659b0b4a5643b009e3dbf0444a36e6b43bd01115ebff385f2e06c98463a23
|
| 3 |
+
size 134217728
|
params_shard_20.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7a62e531fc6fde459eecb716576da9d34073a7b2a4857c0073a8b71d41b412c
|
| 3 |
+
size 134217728
|
params_shard_21.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57a37e915fc860f83056174c6f3bc0c2bed5349cc5333f91052f430369fb7558
|
| 3 |
+
size 29368320
|
params_shard_22.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14006f5e4acb2f9416271ae562e299359cd2585739c7fc77ccbca54495563948
|
| 3 |
+
size 67108864
|
params_shard_23.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1863a339688b84962200c43e2fb530bd2d702b124ac22f29996efb71df0f2058
|
| 3 |
+
size 134217728
|
params_shard_24.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d4ef29f4bf6d085ea2c19f51cebf3aa080722ab84140e51c67e3ed04de3e84c
|
| 3 |
+
size 134217728
|
params_shard_25.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea38daa1761e491f236e2064f7f82f8690a502936328d858cf184c07e10bf0c0
|
| 3 |
+
size 27271168
|
params_shard_26.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b970ff1b0b6494165defe2fbfa1d31425766ed71e64de9ec4e66ac3955c8bc5f
|
| 3 |
+
size 67108864
|
params_shard_27.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a30f91d2ca8ca264213e5907d5f61978224d57acf67c9bd507316dc07a97d565
|
| 3 |
+
size 134217728
|
params_shard_28.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83dd496a9e6d90035c1406fb35a6bb23a242ec93ef86a31008ada167940c927c
|
| 3 |
+
size 29368320
|
params_shard_29.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58821a8d87008d47d122427911c6fad5272aca70c448bbae223256a74bacd07e
|
| 3 |
+
size 67108864
|
params_shard_3.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ff53811038b661a7b8f2bfdf213bebfb185ec1a6060b662f063714f33584d79
|
| 3 |
+
size 67108864
|
params_shard_30.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56678666ffc37800588c58212de45e0a55320566354ae07d79bc0470b23d4fb7
|
| 3 |
+
size 134217728
|
params_shard_31.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d61e8856d8941d2b1fd138116d015f63840d0fa1e31e20e20a5ceca1536ceec
|
| 3 |
+
size 67108864
|
params_shard_32.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1c738e4f7968eecbbbf19e76459971d3820702d6cb7fee86a432ebe63783dc3
|
| 3 |
+
size 134217728
|
params_shard_33.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fe8c9f67714a936fa25f96fe1a424c4936a2bbcdd7d888566a0e8641b8d211d
|
| 3 |
+
size 27279360
|
params_shard_34.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9b0efd2212981f16d956d8571f054b68780ad01f4917033647e359b557a4653
|
| 3 |
+
size 67108864
|
params_shard_35.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c61e71814db43d2d486b377c0264e25e6741fbfe12edc118bfdfc98d952fff6d
|
| 3 |
+
size 134217728
|
params_shard_36.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9dda75e2e9d2dad79e4261ac571b953bde6c0f503be680e86cdf6b0bab69873d
|
| 3 |
+
size 29368320
|
params_shard_37.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:622dd1ce1706355cbc659a8ab2c4509678ffe0f3ad34258e5e25ed2a5d951bcd
|
| 3 |
+
size 67108864
|
params_shard_38.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b9aee3aa472a570ec238e4f36c2d8b90e3de2c9558379847dc68721a90ce2e2
|
| 3 |
+
size 134217728
|
params_shard_39.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e75db42468800849a9a7da603d0072c5e86c8ed2b4d8b20a312a51fb86a7a10
|
| 3 |
+
size 67108864
|
params_shard_4.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e685f76b32d22107033791ee3ff63793a388b06ab79cc0cf2bc3fd342eb0d3db
|
| 3 |
+
size 134217728
|
params_shard_40.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc165aa4ca15d220bcdb2f4acb46ebc75d30f265372c1c77b2ff0b16e7e51ba7
|
| 3 |
+
size 134217728
|
params_shard_41.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2dbabc5ff2074349355cc6072ad87d01e912cb022b9c337b2ee06320421fd43
|
| 3 |
+
size 27279360
|
params_shard_42.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd69d2c9172974fff154441b237b4787fb53b2d185325442d5048130ef5bc4ef
|
| 3 |
+
size 67108864
|
params_shard_43.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03a78c1c5b85b250c644f280d3067121aab38632646ce8e13e7bfac5e21ee210
|
| 3 |
+
size 134217728
|
params_shard_44.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5a6b1d6c5bf02832dd3acb1df723d3ecb411545935b0fed42f7baf7fe59cf8a
|
| 3 |
+
size 29368320
|
params_shard_45.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbf43ec84becb40c9359a181ab0e641fd7faae7d34b549501f7cfb7afdc3d764
|
| 3 |
+
size 67108864
|
params_shard_46.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:955153723aa8e3419e79bfd03af98fcabb4af95e8dcd5920f2f8956725be526d
|
| 3 |
+
size 134217728
|
params_shard_47.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c086166241e0664f8963fd1ca4ed74c737abfb2525ec20f8435821ff50158f3
|
| 3 |
+
size 67108864
|
params_shard_48.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29e03404838af61a8741de8cf35a5de1f6af115a1a5295319d83af4f64f3bf87
|
| 3 |
+
size 27283456
|
params_shard_5.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd15ff66098ec09268baef9fffb86f474faed2a678b173dac4260ecad9effc19
|
| 3 |
+
size 29376512
|
params_shard_6.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf3b3cb4cace435809ac7b4cc933f20853af12f1f272d3dcefe7f19c0f203b8b
|
| 3 |
+
size 67108864
|
params_shard_7.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57a66e0268cd685d66a96425a81b6f6042720fcc156b23faf56fa7ff13ce20bb
|
| 3 |
+
size 134217728
|