Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- added_tokens.json +5 -0
- merges.txt +0 -0
- mlc-chat-config.json +82 -0
- ndarray-cache.json +1541 -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_49.bin +3 -0
- params_shard_5.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
| 5 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
mlc-chat-config.json
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "0.1.0",
|
| 3 |
+
"model_type": "qwen2",
|
| 4 |
+
"quantization": "q0f16",
|
| 5 |
+
"model_config": {
|
| 6 |
+
"hidden_act": "silu",
|
| 7 |
+
"hidden_size": 3584,
|
| 8 |
+
"intermediate_size": 18944,
|
| 9 |
+
"num_attention_heads": 28,
|
| 10 |
+
"num_hidden_layers": 14,
|
| 11 |
+
"num_key_value_heads": 4,
|
| 12 |
+
"rms_norm_eps": 1e-06,
|
| 13 |
+
"rope_theta": 1000000.0,
|
| 14 |
+
"vocab_size": 152064,
|
| 15 |
+
"tie_word_embeddings": false,
|
| 16 |
+
"context_window_size": 384,
|
| 17 |
+
"prefill_chunk_size": 384,
|
| 18 |
+
"tensor_parallel_shards": 1,
|
| 19 |
+
"head_dim": 128,
|
| 20 |
+
"dtype": "float32",
|
| 21 |
+
"max_batch_size": 1
|
| 22 |
+
},
|
| 23 |
+
"vocab_size": 152064,
|
| 24 |
+
"context_window_size": 384,
|
| 25 |
+
"sliding_window_size": -1,
|
| 26 |
+
"prefill_chunk_size": 384,
|
| 27 |
+
"attention_sink_size": -1,
|
| 28 |
+
"tensor_parallel_shards": 1,
|
| 29 |
+
"pipeline_parallel_stages": 1,
|
| 30 |
+
"temperature": 1.0,
|
| 31 |
+
"presence_penalty": 0.0,
|
| 32 |
+
"frequency_penalty": 0.0,
|
| 33 |
+
"repetition_penalty": 1.0,
|
| 34 |
+
"top_p": 1.0,
|
| 35 |
+
"tokenizer_files": [
|
| 36 |
+
"tokenizer.json",
|
| 37 |
+
"vocab.json",
|
| 38 |
+
"merges.txt",
|
| 39 |
+
"added_tokens.json",
|
| 40 |
+
"tokenizer_config.json"
|
| 41 |
+
],
|
| 42 |
+
"tokenizer_info": {
|
| 43 |
+
"token_postproc_method": "byte_level",
|
| 44 |
+
"prepend_space_in_encode": false,
|
| 45 |
+
"strip_space_in_decode": false
|
| 46 |
+
},
|
| 47 |
+
"conv_template": {
|
| 48 |
+
"name": "qwen2",
|
| 49 |
+
"system_template": "<|im_start|>system\n{system_message}<|im_end|>\n",
|
| 50 |
+
"system_message": "You are a helpful assistant.",
|
| 51 |
+
"system_prefix_token_ids": null,
|
| 52 |
+
"add_role_after_system_message": true,
|
| 53 |
+
"roles": {
|
| 54 |
+
"user": "<|im_start|>user",
|
| 55 |
+
"assistant": "<|im_start|>assistant"
|
| 56 |
+
},
|
| 57 |
+
"role_templates": {
|
| 58 |
+
"user": "{user_message}",
|
| 59 |
+
"assistant": "{assistant_message}",
|
| 60 |
+
"tool": "{tool_message}"
|
| 61 |
+
},
|
| 62 |
+
"messages": [],
|
| 63 |
+
"seps": [
|
| 64 |
+
"<|im_end|>\n"
|
| 65 |
+
],
|
| 66 |
+
"role_content_sep": "\n",
|
| 67 |
+
"role_empty_sep": "\n",
|
| 68 |
+
"stop_str": [
|
| 69 |
+
"<|endoftext|>",
|
| 70 |
+
"<|im_end|>"
|
| 71 |
+
],
|
| 72 |
+
"stop_token_ids": [
|
| 73 |
+
151643,
|
| 74 |
+
151645
|
| 75 |
+
],
|
| 76 |
+
"function_string": "",
|
| 77 |
+
"use_function_calling": false
|
| 78 |
+
},
|
| 79 |
+
"pad_token_id": 0,
|
| 80 |
+
"bos_token_id": 151643,
|
| 81 |
+
"eos_token_id": 151645
|
| 82 |
+
}
|
ndarray-cache.json
ADDED
|
@@ -0,0 +1,1541 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"ParamSize": 101,
|
| 4 |
+
"ParamBytes": 8705614848.0,
|
| 5 |
+
"BitsPerParam": 16.0
|
| 6 |
+
},
|
| 7 |
+
"records": [
|
| 8 |
+
{
|
| 9 |
+
"dataPath": "params_shard_0.bin",
|
| 10 |
+
"format": "raw-shard",
|
| 11 |
+
"nbytes": 1089994752,
|
| 12 |
+
"records": [
|
| 13 |
+
{
|
| 14 |
+
"name": "lm_head.weight",
|
| 15 |
+
"shape": [
|
| 16 |
+
152064,
|
| 17 |
+
3584
|
| 18 |
+
],
|
| 19 |
+
"dtype": "float16",
|
| 20 |
+
"format": "f32-to-bf16",
|
| 21 |
+
"nbytes": 1089994752,
|
| 22 |
+
"byteOffset": 0
|
| 23 |
+
}
|
| 24 |
+
],
|
| 25 |
+
"md5sum": "14ba0c2cb884467368ed3bd2c255170b"
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"dataPath": "params_shard_1.bin",
|
| 29 |
+
"format": "raw-shard",
|
| 30 |
+
"nbytes": 135790592,
|
| 31 |
+
"records": [
|
| 32 |
+
{
|
| 33 |
+
"name": "model.layers.10.mlp.down_proj.weight",
|
| 34 |
+
"shape": [
|
| 35 |
+
3584,
|
| 36 |
+
18944
|
| 37 |
+
],
|
| 38 |
+
"dtype": "float16",
|
| 39 |
+
"format": "f32-to-bf16",
|
| 40 |
+
"nbytes": 135790592,
|
| 41 |
+
"byteOffset": 0
|
| 42 |
+
}
|
| 43 |
+
],
|
| 44 |
+
"md5sum": "b243720fa330a40c781d73598bb37311"
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"dataPath": "params_shard_2.bin",
|
| 48 |
+
"format": "raw-shard",
|
| 49 |
+
"nbytes": 271581184,
|
| 50 |
+
"records": [
|
| 51 |
+
{
|
| 52 |
+
"name": "model.layers.10.mlp.gate_up_proj.weight",
|
| 53 |
+
"shape": [
|
| 54 |
+
37888,
|
| 55 |
+
3584
|
| 56 |
+
],
|
| 57 |
+
"dtype": "float16",
|
| 58 |
+
"format": "f32-to-bf16",
|
| 59 |
+
"nbytes": 271581184,
|
| 60 |
+
"byteOffset": 0
|
| 61 |
+
}
|
| 62 |
+
],
|
| 63 |
+
"md5sum": "16ebdd0e55b7acfaca83243d5e9c1040"
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"dataPath": "params_shard_3.bin",
|
| 67 |
+
"format": "raw-shard",
|
| 68 |
+
"nbytes": 25690112,
|
| 69 |
+
"records": [
|
| 70 |
+
{
|
| 71 |
+
"name": "model.layers.10.self_attn.o_proj.weight",
|
| 72 |
+
"shape": [
|
| 73 |
+
3584,
|
| 74 |
+
3584
|
| 75 |
+
],
|
| 76 |
+
"dtype": "float16",
|
| 77 |
+
"format": "f32-to-bf16",
|
| 78 |
+
"nbytes": 25690112,
|
| 79 |
+
"byteOffset": 0
|
| 80 |
+
}
|
| 81 |
+
],
|
| 82 |
+
"md5sum": "3271d95707ec063482a601c950cc28fc"
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"dataPath": "params_shard_4.bin",
|
| 86 |
+
"format": "raw-shard",
|
| 87 |
+
"nbytes": 135790592,
|
| 88 |
+
"records": [
|
| 89 |
+
{
|
| 90 |
+
"name": "model.layers.11.mlp.down_proj.weight",
|
| 91 |
+
"shape": [
|
| 92 |
+
3584,
|
| 93 |
+
18944
|
| 94 |
+
],
|
| 95 |
+
"dtype": "float16",
|
| 96 |
+
"format": "f32-to-bf16",
|
| 97 |
+
"nbytes": 135790592,
|
| 98 |
+
"byteOffset": 0
|
| 99 |
+
}
|
| 100 |
+
],
|
| 101 |
+
"md5sum": "9760646c6e45dd5a3c545151ca3f61c3"
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"dataPath": "params_shard_5.bin",
|
| 105 |
+
"format": "raw-shard",
|
| 106 |
+
"nbytes": 271581184,
|
| 107 |
+
"records": [
|
| 108 |
+
{
|
| 109 |
+
"name": "model.layers.11.mlp.gate_up_proj.weight",
|
| 110 |
+
"shape": [
|
| 111 |
+
37888,
|
| 112 |
+
3584
|
| 113 |
+
],
|
| 114 |
+
"dtype": "float16",
|
| 115 |
+
"format": "f32-to-bf16",
|
| 116 |
+
"nbytes": 271581184,
|
| 117 |
+
"byteOffset": 0
|
| 118 |
+
}
|
| 119 |
+
],
|
| 120 |
+
"md5sum": "634764c08b440390fcb395e399c9ec73"
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"dataPath": "params_shard_6.bin",
|
| 124 |
+
"format": "raw-shard",
|
| 125 |
+
"nbytes": 33030144,
|
| 126 |
+
"records": [
|
| 127 |
+
{
|
| 128 |
+
"name": "model.layers.11.self_attn.c_attn.weight",
|
| 129 |
+
"shape": [
|
| 130 |
+
4608,
|
| 131 |
+
3584
|
| 132 |
+
],
|
| 133 |
+
"dtype": "float16",
|
| 134 |
+
"format": "f32-to-bf16",
|
| 135 |
+
"nbytes": 33030144,
|
| 136 |
+
"byteOffset": 0
|
| 137 |
+
}
|
| 138 |
+
],
|
| 139 |
+
"md5sum": "ec5255945d6deb54edeeb3b61f7c2bbd"
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"dataPath": "params_shard_7.bin",
|
| 143 |
+
"format": "raw-shard",
|
| 144 |
+
"nbytes": 25690112,
|
| 145 |
+
"records": [
|
| 146 |
+
{
|
| 147 |
+
"name": "model.layers.11.self_attn.o_proj.weight",
|
| 148 |
+
"shape": [
|
| 149 |
+
3584,
|
| 150 |
+
3584
|
| 151 |
+
],
|
| 152 |
+
"dtype": "float16",
|
| 153 |
+
"format": "f32-to-bf16",
|
| 154 |
+
"nbytes": 25690112,
|
| 155 |
+
"byteOffset": 0
|
| 156 |
+
}
|
| 157 |
+
],
|
| 158 |
+
"md5sum": "73d9112c5255f6d8d6b60e8a87e1ac01"
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"dataPath": "params_shard_8.bin",
|
| 162 |
+
"format": "raw-shard",
|
| 163 |
+
"nbytes": 135790592,
|
| 164 |
+
"records": [
|
| 165 |
+
{
|
| 166 |
+
"name": "model.layers.12.mlp.down_proj.weight",
|
| 167 |
+
"shape": [
|
| 168 |
+
3584,
|
| 169 |
+
18944
|
| 170 |
+
],
|
| 171 |
+
"dtype": "float16",
|
| 172 |
+
"format": "f32-to-bf16",
|
| 173 |
+
"nbytes": 135790592,
|
| 174 |
+
"byteOffset": 0
|
| 175 |
+
}
|
| 176 |
+
],
|
| 177 |
+
"md5sum": "b82847c0943bd1551f3b84eeab216ed4"
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"dataPath": "params_shard_9.bin",
|
| 181 |
+
"format": "raw-shard",
|
| 182 |
+
"nbytes": 271581184,
|
| 183 |
+
"records": [
|
| 184 |
+
{
|
| 185 |
+
"name": "model.layers.12.mlp.gate_up_proj.weight",
|
| 186 |
+
"shape": [
|
| 187 |
+
37888,
|
| 188 |
+
3584
|
| 189 |
+
],
|
| 190 |
+
"dtype": "float16",
|
| 191 |
+
"format": "f32-to-bf16",
|
| 192 |
+
"nbytes": 271581184,
|
| 193 |
+
"byteOffset": 0
|
| 194 |
+
}
|
| 195 |
+
],
|
| 196 |
+
"md5sum": "0eabb14b984e1c015c670b77cffbf6be"
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"dataPath": "params_shard_10.bin",
|
| 200 |
+
"format": "raw-shard",
|
| 201 |
+
"nbytes": 33030144,
|
| 202 |
+
"records": [
|
| 203 |
+
{
|
| 204 |
+
"name": "model.layers.12.self_attn.c_attn.weight",
|
| 205 |
+
"shape": [
|
| 206 |
+
4608,
|
| 207 |
+
3584
|
| 208 |
+
],
|
| 209 |
+
"dtype": "float16",
|
| 210 |
+
"format": "f32-to-bf16",
|
| 211 |
+
"nbytes": 33030144,
|
| 212 |
+
"byteOffset": 0
|
| 213 |
+
}
|
| 214 |
+
],
|
| 215 |
+
"md5sum": "c187460e8359d387bfedaf934ac0f646"
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"dataPath": "params_shard_11.bin",
|
| 219 |
+
"format": "raw-shard",
|
| 220 |
+
"nbytes": 25690112,
|
| 221 |
+
"records": [
|
| 222 |
+
{
|
| 223 |
+
"name": "model.layers.12.self_attn.o_proj.weight",
|
| 224 |
+
"shape": [
|
| 225 |
+
3584,
|
| 226 |
+
3584
|
| 227 |
+
],
|
| 228 |
+
"dtype": "float16",
|
| 229 |
+
"format": "f32-to-bf16",
|
| 230 |
+
"nbytes": 25690112,
|
| 231 |
+
"byteOffset": 0
|
| 232 |
+
}
|
| 233 |
+
],
|
| 234 |
+
"md5sum": "e66daf90d5e1ed9dc217825dd96e46e4"
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"dataPath": "params_shard_12.bin",
|
| 238 |
+
"format": "raw-shard",
|
| 239 |
+
"nbytes": 135790592,
|
| 240 |
+
"records": [
|
| 241 |
+
{
|
| 242 |
+
"name": "model.layers.13.mlp.down_proj.weight",
|
| 243 |
+
"shape": [
|
| 244 |
+
3584,
|
| 245 |
+
18944
|
| 246 |
+
],
|
| 247 |
+
"dtype": "float16",
|
| 248 |
+
"format": "f32-to-bf16",
|
| 249 |
+
"nbytes": 135790592,
|
| 250 |
+
"byteOffset": 0
|
| 251 |
+
}
|
| 252 |
+
],
|
| 253 |
+
"md5sum": "540c0388ba638d23234f3dd385e26774"
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"dataPath": "params_shard_13.bin",
|
| 257 |
+
"format": "raw-shard",
|
| 258 |
+
"nbytes": 271581184,
|
| 259 |
+
"records": [
|
| 260 |
+
{
|
| 261 |
+
"name": "model.layers.13.mlp.gate_up_proj.weight",
|
| 262 |
+
"shape": [
|
| 263 |
+
37888,
|
| 264 |
+
3584
|
| 265 |
+
],
|
| 266 |
+
"dtype": "float16",
|
| 267 |
+
"format": "f32-to-bf16",
|
| 268 |
+
"nbytes": 271581184,
|
| 269 |
+
"byteOffset": 0
|
| 270 |
+
}
|
| 271 |
+
],
|
| 272 |
+
"md5sum": "c8e0523e2d976808d58b54f889d97ee8"
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"dataPath": "params_shard_14.bin",
|
| 276 |
+
"format": "raw-shard",
|
| 277 |
+
"nbytes": 33030144,
|
| 278 |
+
"records": [
|
| 279 |
+
{
|
| 280 |
+
"name": "model.layers.13.self_attn.c_attn.weight",
|
| 281 |
+
"shape": [
|
| 282 |
+
4608,
|
| 283 |
+
3584
|
| 284 |
+
],
|
| 285 |
+
"dtype": "float16",
|
| 286 |
+
"format": "f32-to-bf16",
|
| 287 |
+
"nbytes": 33030144,
|
| 288 |
+
"byteOffset": 0
|
| 289 |
+
}
|
| 290 |
+
],
|
| 291 |
+
"md5sum": "1b5eb84972102f37bc3ed9d89be5f459"
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"dataPath": "params_shard_15.bin",
|
| 295 |
+
"format": "raw-shard",
|
| 296 |
+
"nbytes": 25690112,
|
| 297 |
+
"records": [
|
| 298 |
+
{
|
| 299 |
+
"name": "model.layers.13.self_attn.o_proj.weight",
|
| 300 |
+
"shape": [
|
| 301 |
+
3584,
|
| 302 |
+
3584
|
| 303 |
+
],
|
| 304 |
+
"dtype": "float16",
|
| 305 |
+
"format": "f32-to-bf16",
|
| 306 |
+
"nbytes": 25690112,
|
| 307 |
+
"byteOffset": 0
|
| 308 |
+
}
|
| 309 |
+
],
|
| 310 |
+
"md5sum": "64fca7d68e54b4ea5b5429ea8ca99c8f"
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"dataPath": "params_shard_16.bin",
|
| 314 |
+
"format": "raw-shard",
|
| 315 |
+
"nbytes": 135790592,
|
| 316 |
+
"records": [
|
| 317 |
+
{
|
| 318 |
+
"name": "model.layers.8.mlp.down_proj.weight",
|
| 319 |
+
"shape": [
|
| 320 |
+
3584,
|
| 321 |
+
18944
|
| 322 |
+
],
|
| 323 |
+
"dtype": "float16",
|
| 324 |
+
"format": "f32-to-bf16",
|
| 325 |
+
"nbytes": 135790592,
|
| 326 |
+
"byteOffset": 0
|
| 327 |
+
}
|
| 328 |
+
],
|
| 329 |
+
"md5sum": "60cda15a6f0386559aac0cd5e6d7ffe3"
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"dataPath": "params_shard_17.bin",
|
| 333 |
+
"format": "raw-shard",
|
| 334 |
+
"nbytes": 271581184,
|
| 335 |
+
"records": [
|
| 336 |
+
{
|
| 337 |
+
"name": "model.layers.8.mlp.gate_up_proj.weight",
|
| 338 |
+
"shape": [
|
| 339 |
+
37888,
|
| 340 |
+
3584
|
| 341 |
+
],
|
| 342 |
+
"dtype": "float16",
|
| 343 |
+
"format": "f32-to-bf16",
|
| 344 |
+
"nbytes": 271581184,
|
| 345 |
+
"byteOffset": 0
|
| 346 |
+
}
|
| 347 |
+
],
|
| 348 |
+
"md5sum": "8d77228e5da90942997d80366d11a132"
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"dataPath": "params_shard_18.bin",
|
| 352 |
+
"format": "raw-shard",
|
| 353 |
+
"nbytes": 135790592,
|
| 354 |
+
"records": [
|
| 355 |
+
{
|
| 356 |
+
"name": "model.layers.9.mlp.down_proj.weight",
|
| 357 |
+
"shape": [
|
| 358 |
+
3584,
|
| 359 |
+
18944
|
| 360 |
+
],
|
| 361 |
+
"dtype": "float16",
|
| 362 |
+
"format": "f32-to-bf16",
|
| 363 |
+
"nbytes": 135790592,
|
| 364 |
+
"byteOffset": 0
|
| 365 |
+
}
|
| 366 |
+
],
|
| 367 |
+
"md5sum": "85f76c5c8b9640c520931ae853e9db07"
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"dataPath": "params_shard_19.bin",
|
| 371 |
+
"format": "raw-shard",
|
| 372 |
+
"nbytes": 271581184,
|
| 373 |
+
"records": [
|
| 374 |
+
{
|
| 375 |
+
"name": "model.layers.9.mlp.gate_up_proj.weight",
|
| 376 |
+
"shape": [
|
| 377 |
+
37888,
|
| 378 |
+
3584
|
| 379 |
+
],
|
| 380 |
+
"dtype": "float16",
|
| 381 |
+
"format": "f32-to-bf16",
|
| 382 |
+
"nbytes": 271581184,
|
| 383 |
+
"byteOffset": 0
|
| 384 |
+
}
|
| 385 |
+
],
|
| 386 |
+
"md5sum": "b9a69f8d68700d2a89e239bbb5cc8212"
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"dataPath": "params_shard_20.bin",
|
| 390 |
+
"format": "raw-shard",
|
| 391 |
+
"nbytes": 33030144,
|
| 392 |
+
"records": [
|
| 393 |
+
{
|
| 394 |
+
"name": "model.layers.9.self_attn.c_attn.weight",
|
| 395 |
+
"shape": [
|
| 396 |
+
4608,
|
| 397 |
+
3584
|
| 398 |
+
],
|
| 399 |
+
"dtype": "float16",
|
| 400 |
+
"format": "f32-to-bf16",
|
| 401 |
+
"nbytes": 33030144,
|
| 402 |
+
"byteOffset": 0
|
| 403 |
+
}
|
| 404 |
+
],
|
| 405 |
+
"md5sum": "b7573789ef93abe0b2a03e9638104f18"
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"dataPath": "params_shard_21.bin",
|
| 409 |
+
"format": "raw-shard",
|
| 410 |
+
"nbytes": 25690112,
|
| 411 |
+
"records": [
|
| 412 |
+
{
|
| 413 |
+
"name": "model.layers.9.self_attn.o_proj.weight",
|
| 414 |
+
"shape": [
|
| 415 |
+
3584,
|
| 416 |
+
3584
|
| 417 |
+
],
|
| 418 |
+
"dtype": "float16",
|
| 419 |
+
"format": "f32-to-bf16",
|
| 420 |
+
"nbytes": 25690112,
|
| 421 |
+
"byteOffset": 0
|
| 422 |
+
}
|
| 423 |
+
],
|
| 424 |
+
"md5sum": "29ba6f525741d01884a2c2455066ac4a"
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"dataPath": "params_shard_22.bin",
|
| 428 |
+
"format": "raw-shard",
|
| 429 |
+
"nbytes": 1089994752,
|
| 430 |
+
"records": [
|
| 431 |
+
{
|
| 432 |
+
"name": "model.embed_tokens.weight",
|
| 433 |
+
"shape": [
|
| 434 |
+
152064,
|
| 435 |
+
3584
|
| 436 |
+
],
|
| 437 |
+
"dtype": "float16",
|
| 438 |
+
"format": "f32-to-bf16",
|
| 439 |
+
"nbytes": 1089994752,
|
| 440 |
+
"byteOffset": 0
|
| 441 |
+
}
|
| 442 |
+
],
|
| 443 |
+
"md5sum": "eab7f1580f3d7da612180468e04e74e3"
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"dataPath": "params_shard_23.bin",
|
| 447 |
+
"format": "raw-shard",
|
| 448 |
+
"nbytes": 135790592,
|
| 449 |
+
"records": [
|
| 450 |
+
{
|
| 451 |
+
"name": "model.layers.0.mlp.down_proj.weight",
|
| 452 |
+
"shape": [
|
| 453 |
+
3584,
|
| 454 |
+
18944
|
| 455 |
+
],
|
| 456 |
+
"dtype": "float16",
|
| 457 |
+
"format": "f32-to-bf16",
|
| 458 |
+
"nbytes": 135790592,
|
| 459 |
+
"byteOffset": 0
|
| 460 |
+
}
|
| 461 |
+
],
|
| 462 |
+
"md5sum": "8f255f7952726723f66cb23e9449ac27"
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"dataPath": "params_shard_24.bin",
|
| 466 |
+
"format": "raw-shard",
|
| 467 |
+
"nbytes": 271581184,
|
| 468 |
+
"records": [
|
| 469 |
+
{
|
| 470 |
+
"name": "model.layers.0.mlp.gate_up_proj.weight",
|
| 471 |
+
"shape": [
|
| 472 |
+
37888,
|
| 473 |
+
3584
|
| 474 |
+
],
|
| 475 |
+
"dtype": "float16",
|
| 476 |
+
"format": "f32-to-bf16",
|
| 477 |
+
"nbytes": 271581184,
|
| 478 |
+
"byteOffset": 0
|
| 479 |
+
}
|
| 480 |
+
],
|
| 481 |
+
"md5sum": "331bc7a2cd841d2622d6a2b658c91009"
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"dataPath": "params_shard_25.bin",
|
| 485 |
+
"format": "raw-shard",
|
| 486 |
+
"nbytes": 33030144,
|
| 487 |
+
"records": [
|
| 488 |
+
{
|
| 489 |
+
"name": "model.layers.0.self_attn.c_attn.weight",
|
| 490 |
+
"shape": [
|
| 491 |
+
4608,
|
| 492 |
+
3584
|
| 493 |
+
],
|
| 494 |
+
"dtype": "float16",
|
| 495 |
+
"format": "f32-to-bf16",
|
| 496 |
+
"nbytes": 33030144,
|
| 497 |
+
"byteOffset": 0
|
| 498 |
+
}
|
| 499 |
+
],
|
| 500 |
+
"md5sum": "2861e000bfe6d965d41f5e1092c50763"
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"dataPath": "params_shard_26.bin",
|
| 504 |
+
"format": "raw-shard",
|
| 505 |
+
"nbytes": 25690112,
|
| 506 |
+
"records": [
|
| 507 |
+
{
|
| 508 |
+
"name": "model.layers.0.self_attn.o_proj.weight",
|
| 509 |
+
"shape": [
|
| 510 |
+
3584,
|
| 511 |
+
3584
|
| 512 |
+
],
|
| 513 |
+
"dtype": "float16",
|
| 514 |
+
"format": "f32-to-bf16",
|
| 515 |
+
"nbytes": 25690112,
|
| 516 |
+
"byteOffset": 0
|
| 517 |
+
}
|
| 518 |
+
],
|
| 519 |
+
"md5sum": "25e256a5ccf25fa4a69528276ef3b6b0"
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"dataPath": "params_shard_27.bin",
|
| 523 |
+
"format": "raw-shard",
|
| 524 |
+
"nbytes": 135790592,
|
| 525 |
+
"records": [
|
| 526 |
+
{
|
| 527 |
+
"name": "model.layers.1.mlp.down_proj.weight",
|
| 528 |
+
"shape": [
|
| 529 |
+
3584,
|
| 530 |
+
18944
|
| 531 |
+
],
|
| 532 |
+
"dtype": "float16",
|
| 533 |
+
"format": "f32-to-bf16",
|
| 534 |
+
"nbytes": 135790592,
|
| 535 |
+
"byteOffset": 0
|
| 536 |
+
}
|
| 537 |
+
],
|
| 538 |
+
"md5sum": "96ebc7cd4f13156ecc012b8a474dbdb2"
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"dataPath": "params_shard_28.bin",
|
| 542 |
+
"format": "raw-shard",
|
| 543 |
+
"nbytes": 271581184,
|
| 544 |
+
"records": [
|
| 545 |
+
{
|
| 546 |
+
"name": "model.layers.1.mlp.gate_up_proj.weight",
|
| 547 |
+
"shape": [
|
| 548 |
+
37888,
|
| 549 |
+
3584
|
| 550 |
+
],
|
| 551 |
+
"dtype": "float16",
|
| 552 |
+
"format": "f32-to-bf16",
|
| 553 |
+
"nbytes": 271581184,
|
| 554 |
+
"byteOffset": 0
|
| 555 |
+
}
|
| 556 |
+
],
|
| 557 |
+
"md5sum": "93c05c68a9c69b52b8767fbce584d23a"
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"dataPath": "params_shard_29.bin",
|
| 561 |
+
"format": "raw-shard",
|
| 562 |
+
"nbytes": 33030144,
|
| 563 |
+
"records": [
|
| 564 |
+
{
|
| 565 |
+
"name": "model.layers.1.self_attn.c_attn.weight",
|
| 566 |
+
"shape": [
|
| 567 |
+
4608,
|
| 568 |
+
3584
|
| 569 |
+
],
|
| 570 |
+
"dtype": "float16",
|
| 571 |
+
"format": "f32-to-bf16",
|
| 572 |
+
"nbytes": 33030144,
|
| 573 |
+
"byteOffset": 0
|
| 574 |
+
}
|
| 575 |
+
],
|
| 576 |
+
"md5sum": "01d8a77a773d9cb312e9a52a799bd5d9"
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"dataPath": "params_shard_30.bin",
|
| 580 |
+
"format": "raw-shard",
|
| 581 |
+
"nbytes": 25690112,
|
| 582 |
+
"records": [
|
| 583 |
+
{
|
| 584 |
+
"name": "model.layers.1.self_attn.o_proj.weight",
|
| 585 |
+
"shape": [
|
| 586 |
+
3584,
|
| 587 |
+
3584
|
| 588 |
+
],
|
| 589 |
+
"dtype": "float16",
|
| 590 |
+
"format": "f32-to-bf16",
|
| 591 |
+
"nbytes": 25690112,
|
| 592 |
+
"byteOffset": 0
|
| 593 |
+
}
|
| 594 |
+
],
|
| 595 |
+
"md5sum": "fc7997354679466205be888fefae0248"
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"dataPath": "params_shard_31.bin",
|
| 599 |
+
"format": "raw-shard",
|
| 600 |
+
"nbytes": 135790592,
|
| 601 |
+
"records": [
|
| 602 |
+
{
|
| 603 |
+
"name": "model.layers.2.mlp.down_proj.weight",
|
| 604 |
+
"shape": [
|
| 605 |
+
3584,
|
| 606 |
+
18944
|
| 607 |
+
],
|
| 608 |
+
"dtype": "float16",
|
| 609 |
+
"format": "f32-to-bf16",
|
| 610 |
+
"nbytes": 135790592,
|
| 611 |
+
"byteOffset": 0
|
| 612 |
+
}
|
| 613 |
+
],
|
| 614 |
+
"md5sum": "6f77c8fe77e5f87583acc204ba9c03c5"
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"dataPath": "params_shard_32.bin",
|
| 618 |
+
"format": "raw-shard",
|
| 619 |
+
"nbytes": 271581184,
|
| 620 |
+
"records": [
|
| 621 |
+
{
|
| 622 |
+
"name": "model.layers.2.mlp.gate_up_proj.weight",
|
| 623 |
+
"shape": [
|
| 624 |
+
37888,
|
| 625 |
+
3584
|
| 626 |
+
],
|
| 627 |
+
"dtype": "float16",
|
| 628 |
+
"format": "f32-to-bf16",
|
| 629 |
+
"nbytes": 271581184,
|
| 630 |
+
"byteOffset": 0
|
| 631 |
+
}
|
| 632 |
+
],
|
| 633 |
+
"md5sum": "7f4d855ec114684c438d3ef22ba7b84f"
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"dataPath": "params_shard_33.bin",
|
| 637 |
+
"format": "raw-shard",
|
| 638 |
+
"nbytes": 33030144,
|
| 639 |
+
"records": [
|
| 640 |
+
{
|
| 641 |
+
"name": "model.layers.2.self_attn.c_attn.weight",
|
| 642 |
+
"shape": [
|
| 643 |
+
4608,
|
| 644 |
+
3584
|
| 645 |
+
],
|
| 646 |
+
"dtype": "float16",
|
| 647 |
+
"format": "f32-to-bf16",
|
| 648 |
+
"nbytes": 33030144,
|
| 649 |
+
"byteOffset": 0
|
| 650 |
+
}
|
| 651 |
+
],
|
| 652 |
+
"md5sum": "91f365dfff5ba01cdaaa8977626d041f"
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"dataPath": "params_shard_34.bin",
|
| 656 |
+
"format": "raw-shard",
|
| 657 |
+
"nbytes": 25690112,
|
| 658 |
+
"records": [
|
| 659 |
+
{
|
| 660 |
+
"name": "model.layers.2.self_attn.o_proj.weight",
|
| 661 |
+
"shape": [
|
| 662 |
+
3584,
|
| 663 |
+
3584
|
| 664 |
+
],
|
| 665 |
+
"dtype": "float16",
|
| 666 |
+
"format": "f32-to-bf16",
|
| 667 |
+
"nbytes": 25690112,
|
| 668 |
+
"byteOffset": 0
|
| 669 |
+
}
|
| 670 |
+
],
|
| 671 |
+
"md5sum": "5b8833e226def19b0cd97d7c3154f51c"
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"dataPath": "params_shard_35.bin",
|
| 675 |
+
"format": "raw-shard",
|
| 676 |
+
"nbytes": 135790592,
|
| 677 |
+
"records": [
|
| 678 |
+
{
|
| 679 |
+
"name": "model.layers.3.mlp.down_proj.weight",
|
| 680 |
+
"shape": [
|
| 681 |
+
3584,
|
| 682 |
+
18944
|
| 683 |
+
],
|
| 684 |
+
"dtype": "float16",
|
| 685 |
+
"format": "f32-to-bf16",
|
| 686 |
+
"nbytes": 135790592,
|
| 687 |
+
"byteOffset": 0
|
| 688 |
+
}
|
| 689 |
+
],
|
| 690 |
+
"md5sum": "eb4c7d1fb5ff9387a71e2ae22c520b6f"
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"dataPath": "params_shard_36.bin",
|
| 694 |
+
"format": "raw-shard",
|
| 695 |
+
"nbytes": 271581184,
|
| 696 |
+
"records": [
|
| 697 |
+
{
|
| 698 |
+
"name": "model.layers.3.mlp.gate_up_proj.weight",
|
| 699 |
+
"shape": [
|
| 700 |
+
37888,
|
| 701 |
+
3584
|
| 702 |
+
],
|
| 703 |
+
"dtype": "float16",
|
| 704 |
+
"format": "f32-to-bf16",
|
| 705 |
+
"nbytes": 271581184,
|
| 706 |
+
"byteOffset": 0
|
| 707 |
+
}
|
| 708 |
+
],
|
| 709 |
+
"md5sum": "680be7e4577e5ccf7e265f7dff9a0eaa"
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"dataPath": "params_shard_37.bin",
|
| 713 |
+
"format": "raw-shard",
|
| 714 |
+
"nbytes": 33030144,
|
| 715 |
+
"records": [
|
| 716 |
+
{
|
| 717 |
+
"name": "model.layers.3.self_attn.c_attn.weight",
|
| 718 |
+
"shape": [
|
| 719 |
+
4608,
|
| 720 |
+
3584
|
| 721 |
+
],
|
| 722 |
+
"dtype": "float16",
|
| 723 |
+
"format": "f32-to-bf16",
|
| 724 |
+
"nbytes": 33030144,
|
| 725 |
+
"byteOffset": 0
|
| 726 |
+
}
|
| 727 |
+
],
|
| 728 |
+
"md5sum": "60119ba12e2ad9bdc042d90ccdb8ed87"
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"dataPath": "params_shard_38.bin",
|
| 732 |
+
"format": "raw-shard",
|
| 733 |
+
"nbytes": 25690112,
|
| 734 |
+
"records": [
|
| 735 |
+
{
|
| 736 |
+
"name": "model.layers.3.self_attn.o_proj.weight",
|
| 737 |
+
"shape": [
|
| 738 |
+
3584,
|
| 739 |
+
3584
|
| 740 |
+
],
|
| 741 |
+
"dtype": "float16",
|
| 742 |
+
"format": "f32-to-bf16",
|
| 743 |
+
"nbytes": 25690112,
|
| 744 |
+
"byteOffset": 0
|
| 745 |
+
}
|
| 746 |
+
],
|
| 747 |
+
"md5sum": "88053879f96079cfa67cae9ba14d8107"
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"dataPath": "params_shard_39.bin",
|
| 751 |
+
"format": "raw-shard",
|
| 752 |
+
"nbytes": 135790592,
|
| 753 |
+
"records": [
|
| 754 |
+
{
|
| 755 |
+
"name": "model.layers.4.mlp.down_proj.weight",
|
| 756 |
+
"shape": [
|
| 757 |
+
3584,
|
| 758 |
+
18944
|
| 759 |
+
],
|
| 760 |
+
"dtype": "float16",
|
| 761 |
+
"format": "f32-to-bf16",
|
| 762 |
+
"nbytes": 135790592,
|
| 763 |
+
"byteOffset": 0
|
| 764 |
+
}
|
| 765 |
+
],
|
| 766 |
+
"md5sum": "7b730af45f53ba36b342f25dbb0c4583"
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"dataPath": "params_shard_40.bin",
|
| 770 |
+
"format": "raw-shard",
|
| 771 |
+
"nbytes": 271581184,
|
| 772 |
+
"records": [
|
| 773 |
+
{
|
| 774 |
+
"name": "model.layers.4.mlp.gate_up_proj.weight",
|
| 775 |
+
"shape": [
|
| 776 |
+
37888,
|
| 777 |
+
3584
|
| 778 |
+
],
|
| 779 |
+
"dtype": "float16",
|
| 780 |
+
"format": "f32-to-bf16",
|
| 781 |
+
"nbytes": 271581184,
|
| 782 |
+
"byteOffset": 0
|
| 783 |
+
}
|
| 784 |
+
],
|
| 785 |
+
"md5sum": "daf9b8be99b3df2601187126b5190a53"
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"dataPath": "params_shard_41.bin",
|
| 789 |
+
"format": "raw-shard",
|
| 790 |
+
"nbytes": 33030144,
|
| 791 |
+
"records": [
|
| 792 |
+
{
|
| 793 |
+
"name": "model.layers.4.self_attn.c_attn.weight",
|
| 794 |
+
"shape": [
|
| 795 |
+
4608,
|
| 796 |
+
3584
|
| 797 |
+
],
|
| 798 |
+
"dtype": "float16",
|
| 799 |
+
"format": "f32-to-bf16",
|
| 800 |
+
"nbytes": 33030144,
|
| 801 |
+
"byteOffset": 0
|
| 802 |
+
}
|
| 803 |
+
],
|
| 804 |
+
"md5sum": "1c574220ef3be8a9d9123bacdaa42f00"
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"dataPath": "params_shard_42.bin",
|
| 808 |
+
"format": "raw-shard",
|
| 809 |
+
"nbytes": 25690112,
|
| 810 |
+
"records": [
|
| 811 |
+
{
|
| 812 |
+
"name": "model.layers.4.self_attn.o_proj.weight",
|
| 813 |
+
"shape": [
|
| 814 |
+
3584,
|
| 815 |
+
3584
|
| 816 |
+
],
|
| 817 |
+
"dtype": "float16",
|
| 818 |
+
"format": "f32-to-bf16",
|
| 819 |
+
"nbytes": 25690112,
|
| 820 |
+
"byteOffset": 0
|
| 821 |
+
}
|
| 822 |
+
],
|
| 823 |
+
"md5sum": "8489341558d48ea7184b2040952534f4"
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"dataPath": "params_shard_43.bin",
|
| 827 |
+
"format": "raw-shard",
|
| 828 |
+
"nbytes": 135790592,
|
| 829 |
+
"records": [
|
| 830 |
+
{
|
| 831 |
+
"name": "model.layers.5.mlp.down_proj.weight",
|
| 832 |
+
"shape": [
|
| 833 |
+
3584,
|
| 834 |
+
18944
|
| 835 |
+
],
|
| 836 |
+
"dtype": "float16",
|
| 837 |
+
"format": "f32-to-bf16",
|
| 838 |
+
"nbytes": 135790592,
|
| 839 |
+
"byteOffset": 0
|
| 840 |
+
}
|
| 841 |
+
],
|
| 842 |
+
"md5sum": "708b0427f5cdd2360430239c7b1b918e"
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"dataPath": "params_shard_44.bin",
|
| 846 |
+
"format": "raw-shard",
|
| 847 |
+
"nbytes": 271581184,
|
| 848 |
+
"records": [
|
| 849 |
+
{
|
| 850 |
+
"name": "model.layers.5.mlp.gate_up_proj.weight",
|
| 851 |
+
"shape": [
|
| 852 |
+
37888,
|
| 853 |
+
3584
|
| 854 |
+
],
|
| 855 |
+
"dtype": "float16",
|
| 856 |
+
"format": "f32-to-bf16",
|
| 857 |
+
"nbytes": 271581184,
|
| 858 |
+
"byteOffset": 0
|
| 859 |
+
}
|
| 860 |
+
],
|
| 861 |
+
"md5sum": "84afa5e9b366b694df927267e8464a17"
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"dataPath": "params_shard_45.bin",
|
| 865 |
+
"format": "raw-shard",
|
| 866 |
+
"nbytes": 33030144,
|
| 867 |
+
"records": [
|
| 868 |
+
{
|
| 869 |
+
"name": "model.layers.5.self_attn.c_attn.weight",
|
| 870 |
+
"shape": [
|
| 871 |
+
4608,
|
| 872 |
+
3584
|
| 873 |
+
],
|
| 874 |
+
"dtype": "float16",
|
| 875 |
+
"format": "f32-to-bf16",
|
| 876 |
+
"nbytes": 33030144,
|
| 877 |
+
"byteOffset": 0
|
| 878 |
+
}
|
| 879 |
+
],
|
| 880 |
+
"md5sum": "f3d3e51953f6d51ece79485f92678d95"
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"dataPath": "params_shard_46.bin",
|
| 884 |
+
"format": "raw-shard",
|
| 885 |
+
"nbytes": 25690112,
|
| 886 |
+
"records": [
|
| 887 |
+
{
|
| 888 |
+
"name": "model.layers.5.self_attn.o_proj.weight",
|
| 889 |
+
"shape": [
|
| 890 |
+
3584,
|
| 891 |
+
3584
|
| 892 |
+
],
|
| 893 |
+
"dtype": "float16",
|
| 894 |
+
"format": "f32-to-bf16",
|
| 895 |
+
"nbytes": 25690112,
|
| 896 |
+
"byteOffset": 0
|
| 897 |
+
}
|
| 898 |
+
],
|
| 899 |
+
"md5sum": "0eaff87011829467b39aa230b50e8367"
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"dataPath": "params_shard_47.bin",
|
| 903 |
+
"format": "raw-shard",
|
| 904 |
+
"nbytes": 135790592,
|
| 905 |
+
"records": [
|
| 906 |
+
{
|
| 907 |
+
"name": "model.layers.6.mlp.down_proj.weight",
|
| 908 |
+
"shape": [
|
| 909 |
+
3584,
|
| 910 |
+
18944
|
| 911 |
+
],
|
| 912 |
+
"dtype": "float16",
|
| 913 |
+
"format": "f32-to-bf16",
|
| 914 |
+
"nbytes": 135790592,
|
| 915 |
+
"byteOffset": 0
|
| 916 |
+
}
|
| 917 |
+
],
|
| 918 |
+
"md5sum": "0cd87cb0de2bae8b12b182cd570a1676"
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"dataPath": "params_shard_48.bin",
|
| 922 |
+
"format": "raw-shard",
|
| 923 |
+
"nbytes": 271581184,
|
| 924 |
+
"records": [
|
| 925 |
+
{
|
| 926 |
+
"name": "model.layers.6.mlp.gate_up_proj.weight",
|
| 927 |
+
"shape": [
|
| 928 |
+
37888,
|
| 929 |
+
3584
|
| 930 |
+
],
|
| 931 |
+
"dtype": "float16",
|
| 932 |
+
"format": "f32-to-bf16",
|
| 933 |
+
"nbytes": 271581184,
|
| 934 |
+
"byteOffset": 0
|
| 935 |
+
}
|
| 936 |
+
],
|
| 937 |
+
"md5sum": "1282b720e05c09c678f0535db2b5b78f"
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"dataPath": "params_shard_49.bin",
|
| 941 |
+
"format": "raw-shard",
|
| 942 |
+
"nbytes": 33030144,
|
| 943 |
+
"records": [
|
| 944 |
+
{
|
| 945 |
+
"name": "model.layers.6.self_attn.c_attn.weight",
|
| 946 |
+
"shape": [
|
| 947 |
+
4608,
|
| 948 |
+
3584
|
| 949 |
+
],
|
| 950 |
+
"dtype": "float16",
|
| 951 |
+
"format": "f32-to-bf16",
|
| 952 |
+
"nbytes": 33030144,
|
| 953 |
+
"byteOffset": 0
|
| 954 |
+
}
|
| 955 |
+
],
|
| 956 |
+
"md5sum": "e2b71d9839700958718663722a8c1cea"
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"dataPath": "params_shard_50.bin",
|
| 960 |
+
"format": "raw-shard",
|
| 961 |
+
"nbytes": 25690112,
|
| 962 |
+
"records": [
|
| 963 |
+
{
|
| 964 |
+
"name": "model.layers.6.self_attn.o_proj.weight",
|
| 965 |
+
"shape": [
|
| 966 |
+
3584,
|
| 967 |
+
3584
|
| 968 |
+
],
|
| 969 |
+
"dtype": "float16",
|
| 970 |
+
"format": "f32-to-bf16",
|
| 971 |
+
"nbytes": 25690112,
|
| 972 |
+
"byteOffset": 0
|
| 973 |
+
}
|
| 974 |
+
],
|
| 975 |
+
"md5sum": "004bdcd6cd20a34c501db9399db1b59f"
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"dataPath": "params_shard_51.bin",
|
| 979 |
+
"format": "raw-shard",
|
| 980 |
+
"nbytes": 135790592,
|
| 981 |
+
"records": [
|
| 982 |
+
{
|
| 983 |
+
"name": "model.layers.7.mlp.down_proj.weight",
|
| 984 |
+
"shape": [
|
| 985 |
+
3584,
|
| 986 |
+
18944
|
| 987 |
+
],
|
| 988 |
+
"dtype": "float16",
|
| 989 |
+
"format": "f32-to-bf16",
|
| 990 |
+
"nbytes": 135790592,
|
| 991 |
+
"byteOffset": 0
|
| 992 |
+
}
|
| 993 |
+
],
|
| 994 |
+
"md5sum": "3acae7d1c65b7c673c76a8419aa5a37a"
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"dataPath": "params_shard_52.bin",
|
| 998 |
+
"format": "raw-shard",
|
| 999 |
+
"nbytes": 271581184,
|
| 1000 |
+
"records": [
|
| 1001 |
+
{
|
| 1002 |
+
"name": "model.layers.7.mlp.gate_up_proj.weight",
|
| 1003 |
+
"shape": [
|
| 1004 |
+
37888,
|
| 1005 |
+
3584
|
| 1006 |
+
],
|
| 1007 |
+
"dtype": "float16",
|
| 1008 |
+
"format": "f32-to-bf16",
|
| 1009 |
+
"nbytes": 271581184,
|
| 1010 |
+
"byteOffset": 0
|
| 1011 |
+
}
|
| 1012 |
+
],
|
| 1013 |
+
"md5sum": "c93d3489b9e01c1813b281a58b4b50d3"
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"dataPath": "params_shard_53.bin",
|
| 1017 |
+
"format": "raw-shard",
|
| 1018 |
+
"nbytes": 33030144,
|
| 1019 |
+
"records": [
|
| 1020 |
+
{
|
| 1021 |
+
"name": "model.layers.7.self_attn.c_attn.weight",
|
| 1022 |
+
"shape": [
|
| 1023 |
+
4608,
|
| 1024 |
+
3584
|
| 1025 |
+
],
|
| 1026 |
+
"dtype": "float16",
|
| 1027 |
+
"format": "f32-to-bf16",
|
| 1028 |
+
"nbytes": 33030144,
|
| 1029 |
+
"byteOffset": 0
|
| 1030 |
+
}
|
| 1031 |
+
],
|
| 1032 |
+
"md5sum": "e1952f2e90d397c6326a4ebfe4d87fe5"
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"dataPath": "params_shard_54.bin",
|
| 1036 |
+
"format": "raw-shard",
|
| 1037 |
+
"nbytes": 25690112,
|
| 1038 |
+
"records": [
|
| 1039 |
+
{
|
| 1040 |
+
"name": "model.layers.7.self_attn.o_proj.weight",
|
| 1041 |
+
"shape": [
|
| 1042 |
+
3584,
|
| 1043 |
+
3584
|
| 1044 |
+
],
|
| 1045 |
+
"dtype": "float16",
|
| 1046 |
+
"format": "f32-to-bf16",
|
| 1047 |
+
"nbytes": 25690112,
|
| 1048 |
+
"byteOffset": 0
|
| 1049 |
+
}
|
| 1050 |
+
],
|
| 1051 |
+
"md5sum": "239fc89d4a4f51ea8a1e0272fd1c0da3"
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"dataPath": "params_shard_55.bin",
|
| 1055 |
+
"format": "raw-shard",
|
| 1056 |
+
"nbytes": 33030144,
|
| 1057 |
+
"records": [
|
| 1058 |
+
{
|
| 1059 |
+
"name": "model.layers.8.self_attn.c_attn.weight",
|
| 1060 |
+
"shape": [
|
| 1061 |
+
4608,
|
| 1062 |
+
3584
|
| 1063 |
+
],
|
| 1064 |
+
"dtype": "float16",
|
| 1065 |
+
"format": "f32-to-bf16",
|
| 1066 |
+
"nbytes": 33030144,
|
| 1067 |
+
"byteOffset": 0
|
| 1068 |
+
}
|
| 1069 |
+
],
|
| 1070 |
+
"md5sum": "ac8a22fffc1b2b51697e7f38647dcda0"
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"dataPath": "params_shard_56.bin",
|
| 1074 |
+
"format": "raw-shard",
|
| 1075 |
+
"nbytes": 25690112,
|
| 1076 |
+
"records": [
|
| 1077 |
+
{
|
| 1078 |
+
"name": "model.layers.8.self_attn.o_proj.weight",
|
| 1079 |
+
"shape": [
|
| 1080 |
+
3584,
|
| 1081 |
+
3584
|
| 1082 |
+
],
|
| 1083 |
+
"dtype": "float16",
|
| 1084 |
+
"format": "f32-to-bf16",
|
| 1085 |
+
"nbytes": 25690112,
|
| 1086 |
+
"byteOffset": 0
|
| 1087 |
+
}
|
| 1088 |
+
],
|
| 1089 |
+
"md5sum": "c34e852cc01780eb2c8c92053433effa"
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"dataPath": "params_shard_57.bin",
|
| 1093 |
+
"format": "raw-shard",
|
| 1094 |
+
"nbytes": 33367040,
|
| 1095 |
+
"records": [
|
| 1096 |
+
{
|
| 1097 |
+
"name": "model.layers.10.input_layernorm.weight",
|
| 1098 |
+
"shape": [
|
| 1099 |
+
3584
|
| 1100 |
+
],
|
| 1101 |
+
"dtype": "float16",
|
| 1102 |
+
"format": "f32-to-bf16",
|
| 1103 |
+
"nbytes": 7168,
|
| 1104 |
+
"byteOffset": 0
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"name": "model.layers.10.post_attention_layernorm.weight",
|
| 1108 |
+
"shape": [
|
| 1109 |
+
3584
|
| 1110 |
+
],
|
| 1111 |
+
"dtype": "float16",
|
| 1112 |
+
"format": "f32-to-bf16",
|
| 1113 |
+
"nbytes": 7168,
|
| 1114 |
+
"byteOffset": 7168
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"name": "model.layers.10.self_attn.c_attn.bias",
|
| 1118 |
+
"shape": [
|
| 1119 |
+
4608
|
| 1120 |
+
],
|
| 1121 |
+
"dtype": "float16",
|
| 1122 |
+
"format": "f32-to-bf16",
|
| 1123 |
+
"nbytes": 9216,
|
| 1124 |
+
"byteOffset": 14336
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"name": "model.layers.10.self_attn.c_attn.weight",
|
| 1128 |
+
"shape": [
|
| 1129 |
+
4608,
|
| 1130 |
+
3584
|
| 1131 |
+
],
|
| 1132 |
+
"dtype": "float16",
|
| 1133 |
+
"format": "f32-to-bf16",
|
| 1134 |
+
"nbytes": 33030144,
|
| 1135 |
+
"byteOffset": 23552
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"name": "model.layers.11.input_layernorm.weight",
|
| 1139 |
+
"shape": [
|
| 1140 |
+
3584
|
| 1141 |
+
],
|
| 1142 |
+
"dtype": "float16",
|
| 1143 |
+
"format": "f32-to-bf16",
|
| 1144 |
+
"nbytes": 7168,
|
| 1145 |
+
"byteOffset": 33053696
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"name": "model.layers.11.post_attention_layernorm.weight",
|
| 1149 |
+
"shape": [
|
| 1150 |
+
3584
|
| 1151 |
+
],
|
| 1152 |
+
"dtype": "float16",
|
| 1153 |
+
"format": "f32-to-bf16",
|
| 1154 |
+
"nbytes": 7168,
|
| 1155 |
+
"byteOffset": 33060864
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"name": "model.layers.11.self_attn.c_attn.bias",
|
| 1159 |
+
"shape": [
|
| 1160 |
+
4608
|
| 1161 |
+
],
|
| 1162 |
+
"dtype": "float16",
|
| 1163 |
+
"format": "f32-to-bf16",
|
| 1164 |
+
"nbytes": 9216,
|
| 1165 |
+
"byteOffset": 33068032
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"name": "model.layers.12.input_layernorm.weight",
|
| 1169 |
+
"shape": [
|
| 1170 |
+
3584
|
| 1171 |
+
],
|
| 1172 |
+
"dtype": "float16",
|
| 1173 |
+
"format": "f32-to-bf16",
|
| 1174 |
+
"nbytes": 7168,
|
| 1175 |
+
"byteOffset": 33077248
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"name": "model.layers.12.post_attention_layernorm.weight",
|
| 1179 |
+
"shape": [
|
| 1180 |
+
3584
|
| 1181 |
+
],
|
| 1182 |
+
"dtype": "float16",
|
| 1183 |
+
"format": "f32-to-bf16",
|
| 1184 |
+
"nbytes": 7168,
|
| 1185 |
+
"byteOffset": 33084416
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"name": "model.layers.12.self_attn.c_attn.bias",
|
| 1189 |
+
"shape": [
|
| 1190 |
+
4608
|
| 1191 |
+
],
|
| 1192 |
+
"dtype": "float16",
|
| 1193 |
+
"format": "f32-to-bf16",
|
| 1194 |
+
"nbytes": 9216,
|
| 1195 |
+
"byteOffset": 33091584
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"name": "model.layers.13.input_layernorm.weight",
|
| 1199 |
+
"shape": [
|
| 1200 |
+
3584
|
| 1201 |
+
],
|
| 1202 |
+
"dtype": "float16",
|
| 1203 |
+
"format": "f32-to-bf16",
|
| 1204 |
+
"nbytes": 7168,
|
| 1205 |
+
"byteOffset": 33100800
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"name": "model.layers.13.post_attention_layernorm.weight",
|
| 1209 |
+
"shape": [
|
| 1210 |
+
3584
|
| 1211 |
+
],
|
| 1212 |
+
"dtype": "float16",
|
| 1213 |
+
"format": "f32-to-bf16",
|
| 1214 |
+
"nbytes": 7168,
|
| 1215 |
+
"byteOffset": 33107968
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"name": "model.layers.13.self_attn.c_attn.bias",
|
| 1219 |
+
"shape": [
|
| 1220 |
+
4608
|
| 1221 |
+
],
|
| 1222 |
+
"dtype": "float16",
|
| 1223 |
+
"format": "f32-to-bf16",
|
| 1224 |
+
"nbytes": 9216,
|
| 1225 |
+
"byteOffset": 33115136
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"name": "model.layers.8.input_layernorm.weight",
|
| 1229 |
+
"shape": [
|
| 1230 |
+
3584
|
| 1231 |
+
],
|
| 1232 |
+
"dtype": "float16",
|
| 1233 |
+
"format": "f32-to-bf16",
|
| 1234 |
+
"nbytes": 7168,
|
| 1235 |
+
"byteOffset": 33124352
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"name": "model.layers.8.post_attention_layernorm.weight",
|
| 1239 |
+
"shape": [
|
| 1240 |
+
3584
|
| 1241 |
+
],
|
| 1242 |
+
"dtype": "float16",
|
| 1243 |
+
"format": "f32-to-bf16",
|
| 1244 |
+
"nbytes": 7168,
|
| 1245 |
+
"byteOffset": 33131520
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"name": "model.layers.9.input_layernorm.weight",
|
| 1249 |
+
"shape": [
|
| 1250 |
+
3584
|
| 1251 |
+
],
|
| 1252 |
+
"dtype": "float16",
|
| 1253 |
+
"format": "f32-to-bf16",
|
| 1254 |
+
"nbytes": 7168,
|
| 1255 |
+
"byteOffset": 33138688
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"name": "model.layers.9.post_attention_layernorm.weight",
|
| 1259 |
+
"shape": [
|
| 1260 |
+
3584
|
| 1261 |
+
],
|
| 1262 |
+
"dtype": "float16",
|
| 1263 |
+
"format": "f32-to-bf16",
|
| 1264 |
+
"nbytes": 7168,
|
| 1265 |
+
"byteOffset": 33145856
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"name": "model.layers.9.self_attn.c_attn.bias",
|
| 1269 |
+
"shape": [
|
| 1270 |
+
4608
|
| 1271 |
+
],
|
| 1272 |
+
"dtype": "float16",
|
| 1273 |
+
"format": "f32-to-bf16",
|
| 1274 |
+
"nbytes": 9216,
|
| 1275 |
+
"byteOffset": 33153024
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"name": "model.norm.weight",
|
| 1279 |
+
"shape": [
|
| 1280 |
+
3584
|
| 1281 |
+
],
|
| 1282 |
+
"dtype": "float16",
|
| 1283 |
+
"format": "f32-to-bf16",
|
| 1284 |
+
"nbytes": 7168,
|
| 1285 |
+
"byteOffset": 33162240
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"name": "model.layers.0.input_layernorm.weight",
|
| 1289 |
+
"shape": [
|
| 1290 |
+
3584
|
| 1291 |
+
],
|
| 1292 |
+
"dtype": "float16",
|
| 1293 |
+
"format": "f32-to-bf16",
|
| 1294 |
+
"nbytes": 7168,
|
| 1295 |
+
"byteOffset": 33169408
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"name": "model.layers.0.post_attention_layernorm.weight",
|
| 1299 |
+
"shape": [
|
| 1300 |
+
3584
|
| 1301 |
+
],
|
| 1302 |
+
"dtype": "float16",
|
| 1303 |
+
"format": "f32-to-bf16",
|
| 1304 |
+
"nbytes": 7168,
|
| 1305 |
+
"byteOffset": 33176576
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"name": "model.layers.0.self_attn.c_attn.bias",
|
| 1309 |
+
"shape": [
|
| 1310 |
+
4608
|
| 1311 |
+
],
|
| 1312 |
+
"dtype": "float16",
|
| 1313 |
+
"format": "f32-to-bf16",
|
| 1314 |
+
"nbytes": 9216,
|
| 1315 |
+
"byteOffset": 33183744
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"name": "model.layers.1.input_layernorm.weight",
|
| 1319 |
+
"shape": [
|
| 1320 |
+
3584
|
| 1321 |
+
],
|
| 1322 |
+
"dtype": "float16",
|
| 1323 |
+
"format": "f32-to-bf16",
|
| 1324 |
+
"nbytes": 7168,
|
| 1325 |
+
"byteOffset": 33192960
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"name": "model.layers.1.post_attention_layernorm.weight",
|
| 1329 |
+
"shape": [
|
| 1330 |
+
3584
|
| 1331 |
+
],
|
| 1332 |
+
"dtype": "float16",
|
| 1333 |
+
"format": "f32-to-bf16",
|
| 1334 |
+
"nbytes": 7168,
|
| 1335 |
+
"byteOffset": 33200128
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"name": "model.layers.1.self_attn.c_attn.bias",
|
| 1339 |
+
"shape": [
|
| 1340 |
+
4608
|
| 1341 |
+
],
|
| 1342 |
+
"dtype": "float16",
|
| 1343 |
+
"format": "f32-to-bf16",
|
| 1344 |
+
"nbytes": 9216,
|
| 1345 |
+
"byteOffset": 33207296
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"name": "model.layers.2.input_layernorm.weight",
|
| 1349 |
+
"shape": [
|
| 1350 |
+
3584
|
| 1351 |
+
],
|
| 1352 |
+
"dtype": "float16",
|
| 1353 |
+
"format": "f32-to-bf16",
|
| 1354 |
+
"nbytes": 7168,
|
| 1355 |
+
"byteOffset": 33216512
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"name": "model.layers.2.post_attention_layernorm.weight",
|
| 1359 |
+
"shape": [
|
| 1360 |
+
3584
|
| 1361 |
+
],
|
| 1362 |
+
"dtype": "float16",
|
| 1363 |
+
"format": "f32-to-bf16",
|
| 1364 |
+
"nbytes": 7168,
|
| 1365 |
+
"byteOffset": 33223680
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"name": "model.layers.2.self_attn.c_attn.bias",
|
| 1369 |
+
"shape": [
|
| 1370 |
+
4608
|
| 1371 |
+
],
|
| 1372 |
+
"dtype": "float16",
|
| 1373 |
+
"format": "f32-to-bf16",
|
| 1374 |
+
"nbytes": 9216,
|
| 1375 |
+
"byteOffset": 33230848
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"name": "model.layers.3.input_layernorm.weight",
|
| 1379 |
+
"shape": [
|
| 1380 |
+
3584
|
| 1381 |
+
],
|
| 1382 |
+
"dtype": "float16",
|
| 1383 |
+
"format": "f32-to-bf16",
|
| 1384 |
+
"nbytes": 7168,
|
| 1385 |
+
"byteOffset": 33240064
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"name": "model.layers.3.post_attention_layernorm.weight",
|
| 1389 |
+
"shape": [
|
| 1390 |
+
3584
|
| 1391 |
+
],
|
| 1392 |
+
"dtype": "float16",
|
| 1393 |
+
"format": "f32-to-bf16",
|
| 1394 |
+
"nbytes": 7168,
|
| 1395 |
+
"byteOffset": 33247232
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"name": "model.layers.3.self_attn.c_attn.bias",
|
| 1399 |
+
"shape": [
|
| 1400 |
+
4608
|
| 1401 |
+
],
|
| 1402 |
+
"dtype": "float16",
|
| 1403 |
+
"format": "f32-to-bf16",
|
| 1404 |
+
"nbytes": 9216,
|
| 1405 |
+
"byteOffset": 33254400
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"name": "model.layers.4.input_layernorm.weight",
|
| 1409 |
+
"shape": [
|
| 1410 |
+
3584
|
| 1411 |
+
],
|
| 1412 |
+
"dtype": "float16",
|
| 1413 |
+
"format": "f32-to-bf16",
|
| 1414 |
+
"nbytes": 7168,
|
| 1415 |
+
"byteOffset": 33263616
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"name": "model.layers.4.post_attention_layernorm.weight",
|
| 1419 |
+
"shape": [
|
| 1420 |
+
3584
|
| 1421 |
+
],
|
| 1422 |
+
"dtype": "float16",
|
| 1423 |
+
"format": "f32-to-bf16",
|
| 1424 |
+
"nbytes": 7168,
|
| 1425 |
+
"byteOffset": 33270784
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"name": "model.layers.4.self_attn.c_attn.bias",
|
| 1429 |
+
"shape": [
|
| 1430 |
+
4608
|
| 1431 |
+
],
|
| 1432 |
+
"dtype": "float16",
|
| 1433 |
+
"format": "f32-to-bf16",
|
| 1434 |
+
"nbytes": 9216,
|
| 1435 |
+
"byteOffset": 33277952
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"name": "model.layers.5.input_layernorm.weight",
|
| 1439 |
+
"shape": [
|
| 1440 |
+
3584
|
| 1441 |
+
],
|
| 1442 |
+
"dtype": "float16",
|
| 1443 |
+
"format": "f32-to-bf16",
|
| 1444 |
+
"nbytes": 7168,
|
| 1445 |
+
"byteOffset": 33287168
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"name": "model.layers.5.post_attention_layernorm.weight",
|
| 1449 |
+
"shape": [
|
| 1450 |
+
3584
|
| 1451 |
+
],
|
| 1452 |
+
"dtype": "float16",
|
| 1453 |
+
"format": "f32-to-bf16",
|
| 1454 |
+
"nbytes": 7168,
|
| 1455 |
+
"byteOffset": 33294336
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"name": "model.layers.5.self_attn.c_attn.bias",
|
| 1459 |
+
"shape": [
|
| 1460 |
+
4608
|
| 1461 |
+
],
|
| 1462 |
+
"dtype": "float16",
|
| 1463 |
+
"format": "f32-to-bf16",
|
| 1464 |
+
"nbytes": 9216,
|
| 1465 |
+
"byteOffset": 33301504
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"name": "model.layers.6.input_layernorm.weight",
|
| 1469 |
+
"shape": [
|
| 1470 |
+
3584
|
| 1471 |
+
],
|
| 1472 |
+
"dtype": "float16",
|
| 1473 |
+
"format": "f32-to-bf16",
|
| 1474 |
+
"nbytes": 7168,
|
| 1475 |
+
"byteOffset": 33310720
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"name": "model.layers.6.post_attention_layernorm.weight",
|
| 1479 |
+
"shape": [
|
| 1480 |
+
3584
|
| 1481 |
+
],
|
| 1482 |
+
"dtype": "float16",
|
| 1483 |
+
"format": "f32-to-bf16",
|
| 1484 |
+
"nbytes": 7168,
|
| 1485 |
+
"byteOffset": 33317888
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"name": "model.layers.6.self_attn.c_attn.bias",
|
| 1489 |
+
"shape": [
|
| 1490 |
+
4608
|
| 1491 |
+
],
|
| 1492 |
+
"dtype": "float16",
|
| 1493 |
+
"format": "f32-to-bf16",
|
| 1494 |
+
"nbytes": 9216,
|
| 1495 |
+
"byteOffset": 33325056
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"name": "model.layers.7.input_layernorm.weight",
|
| 1499 |
+
"shape": [
|
| 1500 |
+
3584
|
| 1501 |
+
],
|
| 1502 |
+
"dtype": "float16",
|
| 1503 |
+
"format": "f32-to-bf16",
|
| 1504 |
+
"nbytes": 7168,
|
| 1505 |
+
"byteOffset": 33334272
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"name": "model.layers.7.post_attention_layernorm.weight",
|
| 1509 |
+
"shape": [
|
| 1510 |
+
3584
|
| 1511 |
+
],
|
| 1512 |
+
"dtype": "float16",
|
| 1513 |
+
"format": "f32-to-bf16",
|
| 1514 |
+
"nbytes": 7168,
|
| 1515 |
+
"byteOffset": 33341440
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"name": "model.layers.7.self_attn.c_attn.bias",
|
| 1519 |
+
"shape": [
|
| 1520 |
+
4608
|
| 1521 |
+
],
|
| 1522 |
+
"dtype": "float16",
|
| 1523 |
+
"format": "f32-to-bf16",
|
| 1524 |
+
"nbytes": 9216,
|
| 1525 |
+
"byteOffset": 33348608
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"name": "model.layers.8.self_attn.c_attn.bias",
|
| 1529 |
+
"shape": [
|
| 1530 |
+
4608
|
| 1531 |
+
],
|
| 1532 |
+
"dtype": "float16",
|
| 1533 |
+
"format": "f32-to-bf16",
|
| 1534 |
+
"nbytes": 9216,
|
| 1535 |
+
"byteOffset": 33357824
|
| 1536 |
+
}
|
| 1537 |
+
],
|
| 1538 |
+
"md5sum": "e4c982148947f2c82d6965ad54885725"
|
| 1539 |
+
}
|
| 1540 |
+
]
|
| 1541 |
+
}
|
params_shard_0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1198e20be2499c6ed64a734fced221dc4347579006029dac4ec3d62dd6f5f269
|
| 3 |
+
size 1089994752
|
params_shard_1.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88432fdaf786d9007288426f934b34f83cb1f25ba93f1a84fcd48bb889dc3a57
|
| 3 |
+
size 135790592
|
params_shard_10.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f3084d7dfac6b02afffb033ebee5bd24b8ed688686889bf8cdcf2f0c9862362
|
| 3 |
+
size 33030144
|
params_shard_11.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c45a5a4be7c9f48cbc618478984206a2e9bef00c597a30bb91667ad4edf04081
|
| 3 |
+
size 25690112
|
params_shard_12.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d69ec2fc84a19c21eb4c4391b50e384d5f562220ba53c3ac8e907ceede5fe925
|
| 3 |
+
size 135790592
|
params_shard_13.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f80507638024d01b4ab041ad2ee8fce846db059ac19063572e5659f1e5a6f72d
|
| 3 |
+
size 271581184
|
params_shard_14.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b98c00fd7cbe37e607e147464d440747898f6533cd5d1c20ffd4992b26cd21d8
|
| 3 |
+
size 33030144
|
params_shard_15.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90fdbf0797790c7398841fe0fac334963c058bb7a57f93ecfbcc6dbed9163675
|
| 3 |
+
size 25690112
|
params_shard_16.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4728eed14af21a9b55e05b6eeabb59c4d4b329b57688bc7c22aec66c958b0cca
|
| 3 |
+
size 135790592
|
params_shard_17.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ed054adb9a04302bb5581fe4770b5eedc6c1d3a6317344c276d5f0685a270fa
|
| 3 |
+
size 271581184
|
params_shard_18.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42aaa82f06ebe5f7425bd144e56a5dd8ea8ce94f6233d2586ab5039a6fa5a1c5
|
| 3 |
+
size 135790592
|
params_shard_19.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6850bb49c2a52e50fcf0893c79b66ff296dec10014f2aa3a5372fcf685b9bcdd
|
| 3 |
+
size 271581184
|
params_shard_2.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c4dfda19bba9ab669f80eeec226ad839b1c0cc49f412821e044b8f72933cd6c
|
| 3 |
+
size 271581184
|
params_shard_20.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e599eafdbf22fc963964230ee7589453dae8217ac4e22cfc5b1a42b8d150d0eb
|
| 3 |
+
size 33030144
|
params_shard_21.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff1cdc54b98ea2518a11b16cf124f04606fbfe968bf880932540d75f1f7ed7d9
|
| 3 |
+
size 25690112
|
params_shard_22.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5da4bc9939d162fbcb4384ddf36900d36e59afc5987ef99d7686c6aa05e6a18b
|
| 3 |
+
size 1089994752
|
params_shard_23.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb84bdbfda38051d30154b7c006fa76d7f2b2b655dddcd3517f3a81689dafd55
|
| 3 |
+
size 135790592
|
params_shard_24.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dad9163c965ff11847acc2c242cbdc01d018cf5d1b9844b7d9ce8504403e28f4
|
| 3 |
+
size 271581184
|
params_shard_25.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f8b373a4be5b7e10d384d283986cb372389bb177fe72c2b5ecd7d2cd8d7490d
|
| 3 |
+
size 33030144
|
params_shard_26.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1deb1406b8f996931590eb6c2228cc5949583f795e6e92cd2eaf4798d3f463df
|
| 3 |
+
size 25690112
|
params_shard_27.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82f9d2a8dd1b5bde7ba2d80069f2aa50610ea2a225ff0ea77238be182ba291f2
|
| 3 |
+
size 135790592
|
params_shard_28.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbc4017732a46ac316e39d6e50c954c84be850ff2b9e15bdb5db5c76dfb056f6
|
| 3 |
+
size 271581184
|
params_shard_29.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db1859ad964ca9be465180c264c0535b30c1c6d2782c786f0088aba01c9a94e8
|
| 3 |
+
size 33030144
|
params_shard_3.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01e993883aaa54987035ba5418e2451180e2b4436ff0ad07bc7de73397c9774a
|
| 3 |
+
size 25690112
|
params_shard_30.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:250cd7828cfe1ace3115945a984a8b886c7fcb57ca5ad7d9cd703b732a5b9249
|
| 3 |
+
size 25690112
|
params_shard_31.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:920d2b5ea81ee732a78b70c251d6eb065ab1ed2b6764b3da819e5a3ca9fdab2e
|
| 3 |
+
size 135790592
|
params_shard_32.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b3fdab3c10d0ecc3be713d57074488b3a2c900e3176077136bffedf0d468677
|
| 3 |
+
size 271581184
|
params_shard_33.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b387cfc69a9fce6929514d98b00d47ffd5c5d973c7490f9384b962601d02dd5b
|
| 3 |
+
size 33030144
|
params_shard_34.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:482391a5504aabc62d1b235af60ea76bd5d170e25941d75125427f264e697a85
|
| 3 |
+
size 25690112
|
params_shard_35.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a59c730ae92039757af2129ac569c1bb2058db03f1688bb07d3d1d34d83dbc7d
|
| 3 |
+
size 135790592
|
params_shard_36.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2876df90bfcc92c63afccbcecdf156565b720668bafaacb26accb8fda66bd606
|
| 3 |
+
size 271581184
|
params_shard_37.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8486b4067ad97df70e37583cb951e32bda90ec93cfba6dbfbb7d73c3eb76d93c
|
| 3 |
+
size 33030144
|
params_shard_38.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dac6680a80f5f0da60ee12d9390f0dd6bd9fff9b218a2619f8736941008ce81e
|
| 3 |
+
size 25690112
|
params_shard_39.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2a5db88d3585050712012425518813049471695e42bb97217d751ce2c7bcbaf
|
| 3 |
+
size 135790592
|
params_shard_4.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a185cf606e0f64049ec12bd1c0a99efe847421bdb8355fdbb27633dd6a54d4b4
|
| 3 |
+
size 135790592
|
params_shard_40.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:634248c241aa3cd36d6fd6da0884cb682ecf62fcacca237f759b7c62f2a79224
|
| 3 |
+
size 271581184
|
params_shard_41.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40c1479fdd13cd8b8f20a1180a5eba6699a3ecd391a2b27ed75fc272d54756f1
|
| 3 |
+
size 33030144
|
params_shard_42.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01cc1836d0a8f227ec70f1db769f8bbfc3ad5bc8c3f5f23953b9e89c3e804129
|
| 3 |
+
size 25690112
|
params_shard_43.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e10d4c57c6b534f832c1fe08fdbfaf7574f8d04abe7f059842a76909d539cdf
|
| 3 |
+
size 135790592
|
params_shard_44.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d928c36e9f5a130c691a920d63ef0eec6a079fdba09adc40f9ac54906c36a484
|
| 3 |
+
size 271581184
|
params_shard_45.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5c577f039e48455ad095892e06a2e0f9f2470d459ec43daa1da7a6ae29499e2
|
| 3 |
+
size 33030144
|
params_shard_46.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44280a3de6c5016d88ca369a3a63b99e64367a442847ccb9439d614d49a8a134
|
| 3 |
+
size 25690112
|
params_shard_47.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83f9e5db1a2c2c942e159b50918e3f97b1d1b763ef140ea89b69df62d6f8fff8
|
| 3 |
+
size 135790592
|
params_shard_48.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9eb39dd77d21a0ba7443c643e5d890b13a1a934520ba784c0cf2ab449c3c0a15
|
| 3 |
+
size 271581184
|
params_shard_49.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:921dc35f8d866fd74e5c77ce17ec542ae749fd9aa0c3c46ed53afc382540e573
|
| 3 |
+
size 33030144
|
params_shard_5.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2465efde645cc7b8f94901b5acb762ed74ae4284a3489fe53263aa87320d4f34
|
| 3 |
+
size 271581184
|