Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +6 -0
- mlc-chat-config.json +79 -0
- model.wasm +3 -0
- ndarray-cache.json +1905 -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
README.md
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: jeff31415/TinyLlama-1.1B-1T-OpenOrca
|
3 |
+
---
|
4 |
+
|
5 |
+
[MLC](https://llm.mlc.ai/) version of [jeff31415/TinyLlama-1.1B-1T-OpenOrca](https://huggingface.co/jeff31415/TinyLlama-1.1B-1T-OpenOrca), using `q0f16` quantization.
|
6 |
+
|
mlc-chat-config.json
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "0.1.0",
|
3 |
+
"model_type": "llama",
|
4 |
+
"quantization": "q0f16",
|
5 |
+
"model_config": {
|
6 |
+
"hidden_size": 2048,
|
7 |
+
"intermediate_size": 5632,
|
8 |
+
"num_attention_heads": 32,
|
9 |
+
"num_hidden_layers": 22,
|
10 |
+
"rms_norm_eps": 1e-05,
|
11 |
+
"vocab_size": 32000,
|
12 |
+
"tie_word_embeddings": false,
|
13 |
+
"position_embedding_base": 10000,
|
14 |
+
"rope_scaling": null,
|
15 |
+
"context_window_size": 2048,
|
16 |
+
"prefill_chunk_size": 2048,
|
17 |
+
"num_key_value_heads": 4,
|
18 |
+
"head_dim": 64,
|
19 |
+
"tensor_parallel_shards": 1,
|
20 |
+
"max_batch_size": 80
|
21 |
+
},
|
22 |
+
"vocab_size": 32000,
|
23 |
+
"context_window_size": 2048,
|
24 |
+
"sliding_window_size": -1,
|
25 |
+
"prefill_chunk_size": 2048,
|
26 |
+
"attention_sink_size": -1,
|
27 |
+
"tensor_parallel_shards": 1,
|
28 |
+
"temperature": 1.0,
|
29 |
+
"presence_penalty": 0.0,
|
30 |
+
"frequency_penalty": 0.0,
|
31 |
+
"repetition_penalty": 1.0,
|
32 |
+
"top_p": 1.0,
|
33 |
+
"tokenizer_files": [
|
34 |
+
"tokenizer.model",
|
35 |
+
"tokenizer.json",
|
36 |
+
"tokenizer_config.json"
|
37 |
+
],
|
38 |
+
"tokenizer_info": {
|
39 |
+
"token_postproc_method": "byte_fallback",
|
40 |
+
"prepend_space_in_encode": true,
|
41 |
+
"strip_space_in_decode": true
|
42 |
+
},
|
43 |
+
"conv_template": {
|
44 |
+
"name": "gemma_instruction",
|
45 |
+
"system_template": "{system_message}",
|
46 |
+
"system_message": "",
|
47 |
+
"system_prefix_token_ids": [
|
48 |
+
2
|
49 |
+
],
|
50 |
+
"add_role_after_system_message": true,
|
51 |
+
"roles": {
|
52 |
+
"user": "<start_of_turn>user",
|
53 |
+
"assistant": "<start_of_turn>model"
|
54 |
+
},
|
55 |
+
"role_templates": {
|
56 |
+
"user": "{user_message}",
|
57 |
+
"assistant": "{assistant_message}",
|
58 |
+
"tool": "{tool_message}"
|
59 |
+
},
|
60 |
+
"messages": [],
|
61 |
+
"seps": [
|
62 |
+
"<end_of_turn>\n"
|
63 |
+
],
|
64 |
+
"role_content_sep": "\n",
|
65 |
+
"role_empty_sep": "\n",
|
66 |
+
"stop_str": [
|
67 |
+
"<end_of_turn>"
|
68 |
+
],
|
69 |
+
"stop_token_ids": [
|
70 |
+
1,
|
71 |
+
107
|
72 |
+
],
|
73 |
+
"function_string": "",
|
74 |
+
"use_function_calling": false
|
75 |
+
},
|
76 |
+
"pad_token_id": 0,
|
77 |
+
"bos_token_id": 1,
|
78 |
+
"eos_token_id": 2
|
79 |
+
}
|
model.wasm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5da85ddc382412ba563aa5f4cf9fb25d8fa82ccd426421a16c81cec4d2c4b4d1
|
3 |
+
size 4411826
|
ndarray-cache.json
ADDED
@@ -0,0 +1,1905 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"ParamSize": 135,
|
4 |
+
"ParamBytes": 2200096768.0,
|
5 |
+
"BitsPerParam": 16.0
|
6 |
+
},
|
7 |
+
"records": [
|
8 |
+
{
|
9 |
+
"dataPath": "params_shard_0.bin",
|
10 |
+
"format": "raw-shard",
|
11 |
+
"nbytes": 131072000,
|
12 |
+
"records": [
|
13 |
+
{
|
14 |
+
"name": "model.embed_tokens.weight",
|
15 |
+
"shape": [
|
16 |
+
32000,
|
17 |
+
2048
|
18 |
+
],
|
19 |
+
"dtype": "float16",
|
20 |
+
"format": "f32-to-bf16",
|
21 |
+
"nbytes": 131072000,
|
22 |
+
"byteOffset": 0
|
23 |
+
}
|
24 |
+
],
|
25 |
+
"md5sum": "eff73a0fd7c35d95ac5ee2b26e579d8b"
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"dataPath": "params_shard_1.bin",
|
29 |
+
"format": "raw-shard",
|
30 |
+
"nbytes": 46137344,
|
31 |
+
"records": [
|
32 |
+
{
|
33 |
+
"name": "model.layers.0.mlp.gate_up_proj.weight",
|
34 |
+
"shape": [
|
35 |
+
11264,
|
36 |
+
2048
|
37 |
+
],
|
38 |
+
"dtype": "float16",
|
39 |
+
"format": "f32-to-bf16",
|
40 |
+
"nbytes": 46137344,
|
41 |
+
"byteOffset": 0
|
42 |
+
}
|
43 |
+
],
|
44 |
+
"md5sum": "1429fc4093dc297427a1d203e707a249"
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"dataPath": "params_shard_2.bin",
|
48 |
+
"format": "raw-shard",
|
49 |
+
"nbytes": 23068672,
|
50 |
+
"records": [
|
51 |
+
{
|
52 |
+
"name": "model.layers.0.mlp.down_proj.weight",
|
53 |
+
"shape": [
|
54 |
+
2048,
|
55 |
+
5632
|
56 |
+
],
|
57 |
+
"dtype": "float16",
|
58 |
+
"format": "f32-to-bf16",
|
59 |
+
"nbytes": 23068672,
|
60 |
+
"byteOffset": 0
|
61 |
+
}
|
62 |
+
],
|
63 |
+
"md5sum": "a344dc45356c7e4f600da19c1593c300"
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"dataPath": "params_shard_3.bin",
|
67 |
+
"format": "raw-shard",
|
68 |
+
"nbytes": 29368320,
|
69 |
+
"records": [
|
70 |
+
{
|
71 |
+
"name": "model.layers.0.self_attn.qkv_proj.weight",
|
72 |
+
"shape": [
|
73 |
+
2560,
|
74 |
+
2048
|
75 |
+
],
|
76 |
+
"dtype": "float16",
|
77 |
+
"format": "f32-to-bf16",
|
78 |
+
"nbytes": 10485760,
|
79 |
+
"byteOffset": 0
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"name": "model.layers.0.self_attn.o_proj.weight",
|
83 |
+
"shape": [
|
84 |
+
2048,
|
85 |
+
2048
|
86 |
+
],
|
87 |
+
"dtype": "float16",
|
88 |
+
"format": "f32-to-bf16",
|
89 |
+
"nbytes": 8388608,
|
90 |
+
"byteOffset": 10485760
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"name": "model.layers.0.input_layernorm.weight",
|
94 |
+
"shape": [
|
95 |
+
2048
|
96 |
+
],
|
97 |
+
"dtype": "float16",
|
98 |
+
"format": "f32-to-bf16",
|
99 |
+
"nbytes": 4096,
|
100 |
+
"byteOffset": 18874368
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"name": "model.layers.0.post_attention_layernorm.weight",
|
104 |
+
"shape": [
|
105 |
+
2048
|
106 |
+
],
|
107 |
+
"dtype": "float16",
|
108 |
+
"format": "f32-to-bf16",
|
109 |
+
"nbytes": 4096,
|
110 |
+
"byteOffset": 18878464
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"name": "model.layers.1.self_attn.qkv_proj.weight",
|
114 |
+
"shape": [
|
115 |
+
2560,
|
116 |
+
2048
|
117 |
+
],
|
118 |
+
"dtype": "float16",
|
119 |
+
"format": "f32-to-bf16",
|
120 |
+
"nbytes": 10485760,
|
121 |
+
"byteOffset": 18882560
|
122 |
+
}
|
123 |
+
],
|
124 |
+
"md5sum": "4cdb0f892aeb98c7437ce93ffc26f068"
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"dataPath": "params_shard_4.bin",
|
128 |
+
"format": "raw-shard",
|
129 |
+
"nbytes": 46137344,
|
130 |
+
"records": [
|
131 |
+
{
|
132 |
+
"name": "model.layers.1.mlp.gate_up_proj.weight",
|
133 |
+
"shape": [
|
134 |
+
11264,
|
135 |
+
2048
|
136 |
+
],
|
137 |
+
"dtype": "float16",
|
138 |
+
"format": "f32-to-bf16",
|
139 |
+
"nbytes": 46137344,
|
140 |
+
"byteOffset": 0
|
141 |
+
}
|
142 |
+
],
|
143 |
+
"md5sum": "6a8ce1a0b8b1f429b074de2595baa650"
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"dataPath": "params_shard_5.bin",
|
147 |
+
"format": "raw-shard",
|
148 |
+
"nbytes": 31465472,
|
149 |
+
"records": [
|
150 |
+
{
|
151 |
+
"name": "model.layers.1.self_attn.o_proj.weight",
|
152 |
+
"shape": [
|
153 |
+
2048,
|
154 |
+
2048
|
155 |
+
],
|
156 |
+
"dtype": "float16",
|
157 |
+
"format": "f32-to-bf16",
|
158 |
+
"nbytes": 8388608,
|
159 |
+
"byteOffset": 0
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"name": "model.layers.1.mlp.down_proj.weight",
|
163 |
+
"shape": [
|
164 |
+
2048,
|
165 |
+
5632
|
166 |
+
],
|
167 |
+
"dtype": "float16",
|
168 |
+
"format": "f32-to-bf16",
|
169 |
+
"nbytes": 23068672,
|
170 |
+
"byteOffset": 8388608
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"name": "model.layers.1.input_layernorm.weight",
|
174 |
+
"shape": [
|
175 |
+
2048
|
176 |
+
],
|
177 |
+
"dtype": "float16",
|
178 |
+
"format": "f32-to-bf16",
|
179 |
+
"nbytes": 4096,
|
180 |
+
"byteOffset": 31457280
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"name": "model.layers.1.post_attention_layernorm.weight",
|
184 |
+
"shape": [
|
185 |
+
2048
|
186 |
+
],
|
187 |
+
"dtype": "float16",
|
188 |
+
"format": "f32-to-bf16",
|
189 |
+
"nbytes": 4096,
|
190 |
+
"byteOffset": 31461376
|
191 |
+
}
|
192 |
+
],
|
193 |
+
"md5sum": "bb69861eb1057665fe422716af9732cf"
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"dataPath": "params_shard_6.bin",
|
197 |
+
"format": "raw-shard",
|
198 |
+
"nbytes": 46137344,
|
199 |
+
"records": [
|
200 |
+
{
|
201 |
+
"name": "model.layers.2.mlp.gate_up_proj.weight",
|
202 |
+
"shape": [
|
203 |
+
11264,
|
204 |
+
2048
|
205 |
+
],
|
206 |
+
"dtype": "float16",
|
207 |
+
"format": "f32-to-bf16",
|
208 |
+
"nbytes": 46137344,
|
209 |
+
"byteOffset": 0
|
210 |
+
}
|
211 |
+
],
|
212 |
+
"md5sum": "23f4d96019adbd875c8c59dec0d2c4ec"
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"dataPath": "params_shard_7.bin",
|
216 |
+
"format": "raw-shard",
|
217 |
+
"nbytes": 23068672,
|
218 |
+
"records": [
|
219 |
+
{
|
220 |
+
"name": "model.layers.2.mlp.down_proj.weight",
|
221 |
+
"shape": [
|
222 |
+
2048,
|
223 |
+
5632
|
224 |
+
],
|
225 |
+
"dtype": "float16",
|
226 |
+
"format": "f32-to-bf16",
|
227 |
+
"nbytes": 23068672,
|
228 |
+
"byteOffset": 0
|
229 |
+
}
|
230 |
+
],
|
231 |
+
"md5sum": "76c7bb449215a4c142bf34377cb9ce06"
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"dataPath": "params_shard_8.bin",
|
235 |
+
"format": "raw-shard",
|
236 |
+
"nbytes": 29368320,
|
237 |
+
"records": [
|
238 |
+
{
|
239 |
+
"name": "model.layers.2.self_attn.qkv_proj.weight",
|
240 |
+
"shape": [
|
241 |
+
2560,
|
242 |
+
2048
|
243 |
+
],
|
244 |
+
"dtype": "float16",
|
245 |
+
"format": "f32-to-bf16",
|
246 |
+
"nbytes": 10485760,
|
247 |
+
"byteOffset": 0
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"name": "model.layers.2.self_attn.o_proj.weight",
|
251 |
+
"shape": [
|
252 |
+
2048,
|
253 |
+
2048
|
254 |
+
],
|
255 |
+
"dtype": "float16",
|
256 |
+
"format": "f32-to-bf16",
|
257 |
+
"nbytes": 8388608,
|
258 |
+
"byteOffset": 10485760
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"name": "model.layers.2.input_layernorm.weight",
|
262 |
+
"shape": [
|
263 |
+
2048
|
264 |
+
],
|
265 |
+
"dtype": "float16",
|
266 |
+
"format": "f32-to-bf16",
|
267 |
+
"nbytes": 4096,
|
268 |
+
"byteOffset": 18874368
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"name": "model.layers.2.post_attention_layernorm.weight",
|
272 |
+
"shape": [
|
273 |
+
2048
|
274 |
+
],
|
275 |
+
"dtype": "float16",
|
276 |
+
"format": "f32-to-bf16",
|
277 |
+
"nbytes": 4096,
|
278 |
+
"byteOffset": 18878464
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"name": "model.layers.3.self_attn.qkv_proj.weight",
|
282 |
+
"shape": [
|
283 |
+
2560,
|
284 |
+
2048
|
285 |
+
],
|
286 |
+
"dtype": "float16",
|
287 |
+
"format": "f32-to-bf16",
|
288 |
+
"nbytes": 10485760,
|
289 |
+
"byteOffset": 18882560
|
290 |
+
}
|
291 |
+
],
|
292 |
+
"md5sum": "0146969afe6b3f5c8b1c723da284f2e3"
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"dataPath": "params_shard_9.bin",
|
296 |
+
"format": "raw-shard",
|
297 |
+
"nbytes": 46137344,
|
298 |
+
"records": [
|
299 |
+
{
|
300 |
+
"name": "model.layers.3.mlp.gate_up_proj.weight",
|
301 |
+
"shape": [
|
302 |
+
11264,
|
303 |
+
2048
|
304 |
+
],
|
305 |
+
"dtype": "float16",
|
306 |
+
"format": "f32-to-bf16",
|
307 |
+
"nbytes": 46137344,
|
308 |
+
"byteOffset": 0
|
309 |
+
}
|
310 |
+
],
|
311 |
+
"md5sum": "bad7f4dce5e722bd6abe9fac1d90eff4"
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"dataPath": "params_shard_10.bin",
|
315 |
+
"format": "raw-shard",
|
316 |
+
"nbytes": 31465472,
|
317 |
+
"records": [
|
318 |
+
{
|
319 |
+
"name": "model.layers.3.self_attn.o_proj.weight",
|
320 |
+
"shape": [
|
321 |
+
2048,
|
322 |
+
2048
|
323 |
+
],
|
324 |
+
"dtype": "float16",
|
325 |
+
"format": "f32-to-bf16",
|
326 |
+
"nbytes": 8388608,
|
327 |
+
"byteOffset": 0
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"name": "model.layers.3.mlp.down_proj.weight",
|
331 |
+
"shape": [
|
332 |
+
2048,
|
333 |
+
5632
|
334 |
+
],
|
335 |
+
"dtype": "float16",
|
336 |
+
"format": "f32-to-bf16",
|
337 |
+
"nbytes": 23068672,
|
338 |
+
"byteOffset": 8388608
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"name": "model.layers.3.input_layernorm.weight",
|
342 |
+
"shape": [
|
343 |
+
2048
|
344 |
+
],
|
345 |
+
"dtype": "float16",
|
346 |
+
"format": "f32-to-bf16",
|
347 |
+
"nbytes": 4096,
|
348 |
+
"byteOffset": 31457280
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"name": "model.layers.3.post_attention_layernorm.weight",
|
352 |
+
"shape": [
|
353 |
+
2048
|
354 |
+
],
|
355 |
+
"dtype": "float16",
|
356 |
+
"format": "f32-to-bf16",
|
357 |
+
"nbytes": 4096,
|
358 |
+
"byteOffset": 31461376
|
359 |
+
}
|
360 |
+
],
|
361 |
+
"md5sum": "248d134f8a98490d7b4bb7049ff6fadf"
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"dataPath": "params_shard_11.bin",
|
365 |
+
"format": "raw-shard",
|
366 |
+
"nbytes": 46137344,
|
367 |
+
"records": [
|
368 |
+
{
|
369 |
+
"name": "model.layers.4.mlp.gate_up_proj.weight",
|
370 |
+
"shape": [
|
371 |
+
11264,
|
372 |
+
2048
|
373 |
+
],
|
374 |
+
"dtype": "float16",
|
375 |
+
"format": "f32-to-bf16",
|
376 |
+
"nbytes": 46137344,
|
377 |
+
"byteOffset": 0
|
378 |
+
}
|
379 |
+
],
|
380 |
+
"md5sum": "f9ebe9f2714624fbbf8250efc1b0c844"
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"dataPath": "params_shard_12.bin",
|
384 |
+
"format": "raw-shard",
|
385 |
+
"nbytes": 23068672,
|
386 |
+
"records": [
|
387 |
+
{
|
388 |
+
"name": "model.layers.4.mlp.down_proj.weight",
|
389 |
+
"shape": [
|
390 |
+
2048,
|
391 |
+
5632
|
392 |
+
],
|
393 |
+
"dtype": "float16",
|
394 |
+
"format": "f32-to-bf16",
|
395 |
+
"nbytes": 23068672,
|
396 |
+
"byteOffset": 0
|
397 |
+
}
|
398 |
+
],
|
399 |
+
"md5sum": "6ac19ac227656ed2a9c0c0c4207a6e0c"
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"dataPath": "params_shard_13.bin",
|
403 |
+
"format": "raw-shard",
|
404 |
+
"nbytes": 29368320,
|
405 |
+
"records": [
|
406 |
+
{
|
407 |
+
"name": "model.layers.4.self_attn.qkv_proj.weight",
|
408 |
+
"shape": [
|
409 |
+
2560,
|
410 |
+
2048
|
411 |
+
],
|
412 |
+
"dtype": "float16",
|
413 |
+
"format": "f32-to-bf16",
|
414 |
+
"nbytes": 10485760,
|
415 |
+
"byteOffset": 0
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"name": "model.layers.4.self_attn.o_proj.weight",
|
419 |
+
"shape": [
|
420 |
+
2048,
|
421 |
+
2048
|
422 |
+
],
|
423 |
+
"dtype": "float16",
|
424 |
+
"format": "f32-to-bf16",
|
425 |
+
"nbytes": 8388608,
|
426 |
+
"byteOffset": 10485760
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"name": "model.layers.4.input_layernorm.weight",
|
430 |
+
"shape": [
|
431 |
+
2048
|
432 |
+
],
|
433 |
+
"dtype": "float16",
|
434 |
+
"format": "f32-to-bf16",
|
435 |
+
"nbytes": 4096,
|
436 |
+
"byteOffset": 18874368
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"name": "model.layers.4.post_attention_layernorm.weight",
|
440 |
+
"shape": [
|
441 |
+
2048
|
442 |
+
],
|
443 |
+
"dtype": "float16",
|
444 |
+
"format": "f32-to-bf16",
|
445 |
+
"nbytes": 4096,
|
446 |
+
"byteOffset": 18878464
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"name": "model.layers.5.self_attn.qkv_proj.weight",
|
450 |
+
"shape": [
|
451 |
+
2560,
|
452 |
+
2048
|
453 |
+
],
|
454 |
+
"dtype": "float16",
|
455 |
+
"format": "f32-to-bf16",
|
456 |
+
"nbytes": 10485760,
|
457 |
+
"byteOffset": 18882560
|
458 |
+
}
|
459 |
+
],
|
460 |
+
"md5sum": "dab1a17c6787ca0f2c97e7c4242e8fd6"
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"dataPath": "params_shard_14.bin",
|
464 |
+
"format": "raw-shard",
|
465 |
+
"nbytes": 46137344,
|
466 |
+
"records": [
|
467 |
+
{
|
468 |
+
"name": "model.layers.5.mlp.gate_up_proj.weight",
|
469 |
+
"shape": [
|
470 |
+
11264,
|
471 |
+
2048
|
472 |
+
],
|
473 |
+
"dtype": "float16",
|
474 |
+
"format": "f32-to-bf16",
|
475 |
+
"nbytes": 46137344,
|
476 |
+
"byteOffset": 0
|
477 |
+
}
|
478 |
+
],
|
479 |
+
"md5sum": "faf5f505315df5591917b35220d5c4de"
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"dataPath": "params_shard_15.bin",
|
483 |
+
"format": "raw-shard",
|
484 |
+
"nbytes": 31465472,
|
485 |
+
"records": [
|
486 |
+
{
|
487 |
+
"name": "model.layers.5.self_attn.o_proj.weight",
|
488 |
+
"shape": [
|
489 |
+
2048,
|
490 |
+
2048
|
491 |
+
],
|
492 |
+
"dtype": "float16",
|
493 |
+
"format": "f32-to-bf16",
|
494 |
+
"nbytes": 8388608,
|
495 |
+
"byteOffset": 0
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"name": "model.layers.5.mlp.down_proj.weight",
|
499 |
+
"shape": [
|
500 |
+
2048,
|
501 |
+
5632
|
502 |
+
],
|
503 |
+
"dtype": "float16",
|
504 |
+
"format": "f32-to-bf16",
|
505 |
+
"nbytes": 23068672,
|
506 |
+
"byteOffset": 8388608
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"name": "model.layers.5.input_layernorm.weight",
|
510 |
+
"shape": [
|
511 |
+
2048
|
512 |
+
],
|
513 |
+
"dtype": "float16",
|
514 |
+
"format": "f32-to-bf16",
|
515 |
+
"nbytes": 4096,
|
516 |
+
"byteOffset": 31457280
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"name": "model.layers.5.post_attention_layernorm.weight",
|
520 |
+
"shape": [
|
521 |
+
2048
|
522 |
+
],
|
523 |
+
"dtype": "float16",
|
524 |
+
"format": "f32-to-bf16",
|
525 |
+
"nbytes": 4096,
|
526 |
+
"byteOffset": 31461376
|
527 |
+
}
|
528 |
+
],
|
529 |
+
"md5sum": "c2f11225f3c5733a1a4d184c1edf3c48"
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"dataPath": "params_shard_16.bin",
|
533 |
+
"format": "raw-shard",
|
534 |
+
"nbytes": 46137344,
|
535 |
+
"records": [
|
536 |
+
{
|
537 |
+
"name": "model.layers.6.mlp.gate_up_proj.weight",
|
538 |
+
"shape": [
|
539 |
+
11264,
|
540 |
+
2048
|
541 |
+
],
|
542 |
+
"dtype": "float16",
|
543 |
+
"format": "f32-to-bf16",
|
544 |
+
"nbytes": 46137344,
|
545 |
+
"byteOffset": 0
|
546 |
+
}
|
547 |
+
],
|
548 |
+
"md5sum": "063dd74c0700b250c9ed1dc1893374d9"
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"dataPath": "params_shard_17.bin",
|
552 |
+
"format": "raw-shard",
|
553 |
+
"nbytes": 23068672,
|
554 |
+
"records": [
|
555 |
+
{
|
556 |
+
"name": "model.layers.6.mlp.down_proj.weight",
|
557 |
+
"shape": [
|
558 |
+
2048,
|
559 |
+
5632
|
560 |
+
],
|
561 |
+
"dtype": "float16",
|
562 |
+
"format": "f32-to-bf16",
|
563 |
+
"nbytes": 23068672,
|
564 |
+
"byteOffset": 0
|
565 |
+
}
|
566 |
+
],
|
567 |
+
"md5sum": "9213875dbdfcf3beafdacd7ede601517"
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"dataPath": "params_shard_18.bin",
|
571 |
+
"format": "raw-shard",
|
572 |
+
"nbytes": 29368320,
|
573 |
+
"records": [
|
574 |
+
{
|
575 |
+
"name": "model.layers.6.self_attn.qkv_proj.weight",
|
576 |
+
"shape": [
|
577 |
+
2560,
|
578 |
+
2048
|
579 |
+
],
|
580 |
+
"dtype": "float16",
|
581 |
+
"format": "f32-to-bf16",
|
582 |
+
"nbytes": 10485760,
|
583 |
+
"byteOffset": 0
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"name": "model.layers.6.self_attn.o_proj.weight",
|
587 |
+
"shape": [
|
588 |
+
2048,
|
589 |
+
2048
|
590 |
+
],
|
591 |
+
"dtype": "float16",
|
592 |
+
"format": "f32-to-bf16",
|
593 |
+
"nbytes": 8388608,
|
594 |
+
"byteOffset": 10485760
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"name": "model.layers.6.input_layernorm.weight",
|
598 |
+
"shape": [
|
599 |
+
2048
|
600 |
+
],
|
601 |
+
"dtype": "float16",
|
602 |
+
"format": "f32-to-bf16",
|
603 |
+
"nbytes": 4096,
|
604 |
+
"byteOffset": 18874368
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"name": "model.layers.6.post_attention_layernorm.weight",
|
608 |
+
"shape": [
|
609 |
+
2048
|
610 |
+
],
|
611 |
+
"dtype": "float16",
|
612 |
+
"format": "f32-to-bf16",
|
613 |
+
"nbytes": 4096,
|
614 |
+
"byteOffset": 18878464
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"name": "model.layers.7.self_attn.qkv_proj.weight",
|
618 |
+
"shape": [
|
619 |
+
2560,
|
620 |
+
2048
|
621 |
+
],
|
622 |
+
"dtype": "float16",
|
623 |
+
"format": "f32-to-bf16",
|
624 |
+
"nbytes": 10485760,
|
625 |
+
"byteOffset": 18882560
|
626 |
+
}
|
627 |
+
],
|
628 |
+
"md5sum": "922c6ebcebf9aa82429d7d8cc10996a3"
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"dataPath": "params_shard_19.bin",
|
632 |
+
"format": "raw-shard",
|
633 |
+
"nbytes": 46137344,
|
634 |
+
"records": [
|
635 |
+
{
|
636 |
+
"name": "model.layers.7.mlp.gate_up_proj.weight",
|
637 |
+
"shape": [
|
638 |
+
11264,
|
639 |
+
2048
|
640 |
+
],
|
641 |
+
"dtype": "float16",
|
642 |
+
"format": "f32-to-bf16",
|
643 |
+
"nbytes": 46137344,
|
644 |
+
"byteOffset": 0
|
645 |
+
}
|
646 |
+
],
|
647 |
+
"md5sum": "aecdd343857e3aa80bb8c94902c143c6"
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"dataPath": "params_shard_20.bin",
|
651 |
+
"format": "raw-shard",
|
652 |
+
"nbytes": 31465472,
|
653 |
+
"records": [
|
654 |
+
{
|
655 |
+
"name": "model.layers.7.self_attn.o_proj.weight",
|
656 |
+
"shape": [
|
657 |
+
2048,
|
658 |
+
2048
|
659 |
+
],
|
660 |
+
"dtype": "float16",
|
661 |
+
"format": "f32-to-bf16",
|
662 |
+
"nbytes": 8388608,
|
663 |
+
"byteOffset": 0
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"name": "model.layers.7.mlp.down_proj.weight",
|
667 |
+
"shape": [
|
668 |
+
2048,
|
669 |
+
5632
|
670 |
+
],
|
671 |
+
"dtype": "float16",
|
672 |
+
"format": "f32-to-bf16",
|
673 |
+
"nbytes": 23068672,
|
674 |
+
"byteOffset": 8388608
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"name": "model.layers.7.input_layernorm.weight",
|
678 |
+
"shape": [
|
679 |
+
2048
|
680 |
+
],
|
681 |
+
"dtype": "float16",
|
682 |
+
"format": "f32-to-bf16",
|
683 |
+
"nbytes": 4096,
|
684 |
+
"byteOffset": 31457280
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"name": "model.layers.7.post_attention_layernorm.weight",
|
688 |
+
"shape": [
|
689 |
+
2048
|
690 |
+
],
|
691 |
+
"dtype": "float16",
|
692 |
+
"format": "f32-to-bf16",
|
693 |
+
"nbytes": 4096,
|
694 |
+
"byteOffset": 31461376
|
695 |
+
}
|
696 |
+
],
|
697 |
+
"md5sum": "aac6be0171e02618aae40545fc5faf8e"
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"dataPath": "params_shard_21.bin",
|
701 |
+
"format": "raw-shard",
|
702 |
+
"nbytes": 46137344,
|
703 |
+
"records": [
|
704 |
+
{
|
705 |
+
"name": "model.layers.8.mlp.gate_up_proj.weight",
|
706 |
+
"shape": [
|
707 |
+
11264,
|
708 |
+
2048
|
709 |
+
],
|
710 |
+
"dtype": "float16",
|
711 |
+
"format": "f32-to-bf16",
|
712 |
+
"nbytes": 46137344,
|
713 |
+
"byteOffset": 0
|
714 |
+
}
|
715 |
+
],
|
716 |
+
"md5sum": "378996eebce2626f3e75e8cc1fb75cc8"
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"dataPath": "params_shard_22.bin",
|
720 |
+
"format": "raw-shard",
|
721 |
+
"nbytes": 23068672,
|
722 |
+
"records": [
|
723 |
+
{
|
724 |
+
"name": "model.layers.8.mlp.down_proj.weight",
|
725 |
+
"shape": [
|
726 |
+
2048,
|
727 |
+
5632
|
728 |
+
],
|
729 |
+
"dtype": "float16",
|
730 |
+
"format": "f32-to-bf16",
|
731 |
+
"nbytes": 23068672,
|
732 |
+
"byteOffset": 0
|
733 |
+
}
|
734 |
+
],
|
735 |
+
"md5sum": "8bcf35bd8fc1aca4e79f13c7eeef12de"
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"dataPath": "params_shard_23.bin",
|
739 |
+
"format": "raw-shard",
|
740 |
+
"nbytes": 29368320,
|
741 |
+
"records": [
|
742 |
+
{
|
743 |
+
"name": "model.layers.8.self_attn.qkv_proj.weight",
|
744 |
+
"shape": [
|
745 |
+
2560,
|
746 |
+
2048
|
747 |
+
],
|
748 |
+
"dtype": "float16",
|
749 |
+
"format": "f32-to-bf16",
|
750 |
+
"nbytes": 10485760,
|
751 |
+
"byteOffset": 0
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"name": "model.layers.8.self_attn.o_proj.weight",
|
755 |
+
"shape": [
|
756 |
+
2048,
|
757 |
+
2048
|
758 |
+
],
|
759 |
+
"dtype": "float16",
|
760 |
+
"format": "f32-to-bf16",
|
761 |
+
"nbytes": 8388608,
|
762 |
+
"byteOffset": 10485760
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"name": "model.layers.8.input_layernorm.weight",
|
766 |
+
"shape": [
|
767 |
+
2048
|
768 |
+
],
|
769 |
+
"dtype": "float16",
|
770 |
+
"format": "f32-to-bf16",
|
771 |
+
"nbytes": 4096,
|
772 |
+
"byteOffset": 18874368
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"name": "model.layers.8.post_attention_layernorm.weight",
|
776 |
+
"shape": [
|
777 |
+
2048
|
778 |
+
],
|
779 |
+
"dtype": "float16",
|
780 |
+
"format": "f32-to-bf16",
|
781 |
+
"nbytes": 4096,
|
782 |
+
"byteOffset": 18878464
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"name": "model.layers.9.self_attn.qkv_proj.weight",
|
786 |
+
"shape": [
|
787 |
+
2560,
|
788 |
+
2048
|
789 |
+
],
|
790 |
+
"dtype": "float16",
|
791 |
+
"format": "f32-to-bf16",
|
792 |
+
"nbytes": 10485760,
|
793 |
+
"byteOffset": 18882560
|
794 |
+
}
|
795 |
+
],
|
796 |
+
"md5sum": "59703751a89011572ba8b8cad1a4aba8"
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"dataPath": "params_shard_24.bin",
|
800 |
+
"format": "raw-shard",
|
801 |
+
"nbytes": 46137344,
|
802 |
+
"records": [
|
803 |
+
{
|
804 |
+
"name": "model.layers.9.mlp.gate_up_proj.weight",
|
805 |
+
"shape": [
|
806 |
+
11264,
|
807 |
+
2048
|
808 |
+
],
|
809 |
+
"dtype": "float16",
|
810 |
+
"format": "f32-to-bf16",
|
811 |
+
"nbytes": 46137344,
|
812 |
+
"byteOffset": 0
|
813 |
+
}
|
814 |
+
],
|
815 |
+
"md5sum": "404ee845876d55ec540779bb5b6c34e3"
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"dataPath": "params_shard_25.bin",
|
819 |
+
"format": "raw-shard",
|
820 |
+
"nbytes": 31465472,
|
821 |
+
"records": [
|
822 |
+
{
|
823 |
+
"name": "model.layers.9.self_attn.o_proj.weight",
|
824 |
+
"shape": [
|
825 |
+
2048,
|
826 |
+
2048
|
827 |
+
],
|
828 |
+
"dtype": "float16",
|
829 |
+
"format": "f32-to-bf16",
|
830 |
+
"nbytes": 8388608,
|
831 |
+
"byteOffset": 0
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"name": "model.layers.9.mlp.down_proj.weight",
|
835 |
+
"shape": [
|
836 |
+
2048,
|
837 |
+
5632
|
838 |
+
],
|
839 |
+
"dtype": "float16",
|
840 |
+
"format": "f32-to-bf16",
|
841 |
+
"nbytes": 23068672,
|
842 |
+
"byteOffset": 8388608
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"name": "model.layers.9.input_layernorm.weight",
|
846 |
+
"shape": [
|
847 |
+
2048
|
848 |
+
],
|
849 |
+
"dtype": "float16",
|
850 |
+
"format": "f32-to-bf16",
|
851 |
+
"nbytes": 4096,
|
852 |
+
"byteOffset": 31457280
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"name": "model.layers.9.post_attention_layernorm.weight",
|
856 |
+
"shape": [
|
857 |
+
2048
|
858 |
+
],
|
859 |
+
"dtype": "float16",
|
860 |
+
"format": "f32-to-bf16",
|
861 |
+
"nbytes": 4096,
|
862 |
+
"byteOffset": 31461376
|
863 |
+
}
|
864 |
+
],
|
865 |
+
"md5sum": "052fbbd438265bb5a93a5084015bc992"
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"dataPath": "params_shard_26.bin",
|
869 |
+
"format": "raw-shard",
|
870 |
+
"nbytes": 46137344,
|
871 |
+
"records": [
|
872 |
+
{
|
873 |
+
"name": "model.layers.10.mlp.gate_up_proj.weight",
|
874 |
+
"shape": [
|
875 |
+
11264,
|
876 |
+
2048
|
877 |
+
],
|
878 |
+
"dtype": "float16",
|
879 |
+
"format": "f32-to-bf16",
|
880 |
+
"nbytes": 46137344,
|
881 |
+
"byteOffset": 0
|
882 |
+
}
|
883 |
+
],
|
884 |
+
"md5sum": "f023907997c3ed547ae03bdcdefcd1b5"
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"dataPath": "params_shard_27.bin",
|
888 |
+
"format": "raw-shard",
|
889 |
+
"nbytes": 23068672,
|
890 |
+
"records": [
|
891 |
+
{
|
892 |
+
"name": "model.layers.10.mlp.down_proj.weight",
|
893 |
+
"shape": [
|
894 |
+
2048,
|
895 |
+
5632
|
896 |
+
],
|
897 |
+
"dtype": "float16",
|
898 |
+
"format": "f32-to-bf16",
|
899 |
+
"nbytes": 23068672,
|
900 |
+
"byteOffset": 0
|
901 |
+
}
|
902 |
+
],
|
903 |
+
"md5sum": "90f22652a80539b61d36867074f3204a"
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"dataPath": "params_shard_28.bin",
|
907 |
+
"format": "raw-shard",
|
908 |
+
"nbytes": 29368320,
|
909 |
+
"records": [
|
910 |
+
{
|
911 |
+
"name": "model.layers.10.self_attn.qkv_proj.weight",
|
912 |
+
"shape": [
|
913 |
+
2560,
|
914 |
+
2048
|
915 |
+
],
|
916 |
+
"dtype": "float16",
|
917 |
+
"format": "f32-to-bf16",
|
918 |
+
"nbytes": 10485760,
|
919 |
+
"byteOffset": 0
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"name": "model.layers.10.self_attn.o_proj.weight",
|
923 |
+
"shape": [
|
924 |
+
2048,
|
925 |
+
2048
|
926 |
+
],
|
927 |
+
"dtype": "float16",
|
928 |
+
"format": "f32-to-bf16",
|
929 |
+
"nbytes": 8388608,
|
930 |
+
"byteOffset": 10485760
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"name": "model.layers.10.input_layernorm.weight",
|
934 |
+
"shape": [
|
935 |
+
2048
|
936 |
+
],
|
937 |
+
"dtype": "float16",
|
938 |
+
"format": "f32-to-bf16",
|
939 |
+
"nbytes": 4096,
|
940 |
+
"byteOffset": 18874368
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"name": "model.layers.10.post_attention_layernorm.weight",
|
944 |
+
"shape": [
|
945 |
+
2048
|
946 |
+
],
|
947 |
+
"dtype": "float16",
|
948 |
+
"format": "f32-to-bf16",
|
949 |
+
"nbytes": 4096,
|
950 |
+
"byteOffset": 18878464
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"name": "model.layers.11.self_attn.qkv_proj.weight",
|
954 |
+
"shape": [
|
955 |
+
2560,
|
956 |
+
2048
|
957 |
+
],
|
958 |
+
"dtype": "float16",
|
959 |
+
"format": "f32-to-bf16",
|
960 |
+
"nbytes": 10485760,
|
961 |
+
"byteOffset": 18882560
|
962 |
+
}
|
963 |
+
],
|
964 |
+
"md5sum": "97016e4d3dbbdf58594a6c4f0068b87d"
|
965 |
+
},
|
966 |
+
{
|
967 |
+
"dataPath": "params_shard_29.bin",
|
968 |
+
"format": "raw-shard",
|
969 |
+
"nbytes": 46137344,
|
970 |
+
"records": [
|
971 |
+
{
|
972 |
+
"name": "model.layers.11.mlp.gate_up_proj.weight",
|
973 |
+
"shape": [
|
974 |
+
11264,
|
975 |
+
2048
|
976 |
+
],
|
977 |
+
"dtype": "float16",
|
978 |
+
"format": "f32-to-bf16",
|
979 |
+
"nbytes": 46137344,
|
980 |
+
"byteOffset": 0
|
981 |
+
}
|
982 |
+
],
|
983 |
+
"md5sum": "04a4e35f6c0ec7c2e6ae3e00796a5340"
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"dataPath": "params_shard_30.bin",
|
987 |
+
"format": "raw-shard",
|
988 |
+
"nbytes": 31465472,
|
989 |
+
"records": [
|
990 |
+
{
|
991 |
+
"name": "model.layers.11.self_attn.o_proj.weight",
|
992 |
+
"shape": [
|
993 |
+
2048,
|
994 |
+
2048
|
995 |
+
],
|
996 |
+
"dtype": "float16",
|
997 |
+
"format": "f32-to-bf16",
|
998 |
+
"nbytes": 8388608,
|
999 |
+
"byteOffset": 0
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"name": "model.layers.11.mlp.down_proj.weight",
|
1003 |
+
"shape": [
|
1004 |
+
2048,
|
1005 |
+
5632
|
1006 |
+
],
|
1007 |
+
"dtype": "float16",
|
1008 |
+
"format": "f32-to-bf16",
|
1009 |
+
"nbytes": 23068672,
|
1010 |
+
"byteOffset": 8388608
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"name": "model.layers.11.input_layernorm.weight",
|
1014 |
+
"shape": [
|
1015 |
+
2048
|
1016 |
+
],
|
1017 |
+
"dtype": "float16",
|
1018 |
+
"format": "f32-to-bf16",
|
1019 |
+
"nbytes": 4096,
|
1020 |
+
"byteOffset": 31457280
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"name": "model.layers.11.post_attention_layernorm.weight",
|
1024 |
+
"shape": [
|
1025 |
+
2048
|
1026 |
+
],
|
1027 |
+
"dtype": "float16",
|
1028 |
+
"format": "f32-to-bf16",
|
1029 |
+
"nbytes": 4096,
|
1030 |
+
"byteOffset": 31461376
|
1031 |
+
}
|
1032 |
+
],
|
1033 |
+
"md5sum": "bd378eec1efe504b556676ba55a10fca"
|
1034 |
+
},
|
1035 |
+
{
|
1036 |
+
"dataPath": "params_shard_31.bin",
|
1037 |
+
"format": "raw-shard",
|
1038 |
+
"nbytes": 46137344,
|
1039 |
+
"records": [
|
1040 |
+
{
|
1041 |
+
"name": "model.layers.12.mlp.gate_up_proj.weight",
|
1042 |
+
"shape": [
|
1043 |
+
11264,
|
1044 |
+
2048
|
1045 |
+
],
|
1046 |
+
"dtype": "float16",
|
1047 |
+
"format": "f32-to-bf16",
|
1048 |
+
"nbytes": 46137344,
|
1049 |
+
"byteOffset": 0
|
1050 |
+
}
|
1051 |
+
],
|
1052 |
+
"md5sum": "60b30fd02636aea5794d7335824b22fb"
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"dataPath": "params_shard_32.bin",
|
1056 |
+
"format": "raw-shard",
|
1057 |
+
"nbytes": 23068672,
|
1058 |
+
"records": [
|
1059 |
+
{
|
1060 |
+
"name": "model.layers.12.mlp.down_proj.weight",
|
1061 |
+
"shape": [
|
1062 |
+
2048,
|
1063 |
+
5632
|
1064 |
+
],
|
1065 |
+
"dtype": "float16",
|
1066 |
+
"format": "f32-to-bf16",
|
1067 |
+
"nbytes": 23068672,
|
1068 |
+
"byteOffset": 0
|
1069 |
+
}
|
1070 |
+
],
|
1071 |
+
"md5sum": "a768676b315d80ef29fcfad22479586a"
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"dataPath": "params_shard_33.bin",
|
1075 |
+
"format": "raw-shard",
|
1076 |
+
"nbytes": 29368320,
|
1077 |
+
"records": [
|
1078 |
+
{
|
1079 |
+
"name": "model.layers.12.self_attn.qkv_proj.weight",
|
1080 |
+
"shape": [
|
1081 |
+
2560,
|
1082 |
+
2048
|
1083 |
+
],
|
1084 |
+
"dtype": "float16",
|
1085 |
+
"format": "f32-to-bf16",
|
1086 |
+
"nbytes": 10485760,
|
1087 |
+
"byteOffset": 0
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"name": "model.layers.12.self_attn.o_proj.weight",
|
1091 |
+
"shape": [
|
1092 |
+
2048,
|
1093 |
+
2048
|
1094 |
+
],
|
1095 |
+
"dtype": "float16",
|
1096 |
+
"format": "f32-to-bf16",
|
1097 |
+
"nbytes": 8388608,
|
1098 |
+
"byteOffset": 10485760
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"name": "model.layers.12.input_layernorm.weight",
|
1102 |
+
"shape": [
|
1103 |
+
2048
|
1104 |
+
],
|
1105 |
+
"dtype": "float16",
|
1106 |
+
"format": "f32-to-bf16",
|
1107 |
+
"nbytes": 4096,
|
1108 |
+
"byteOffset": 18874368
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"name": "model.layers.12.post_attention_layernorm.weight",
|
1112 |
+
"shape": [
|
1113 |
+
2048
|
1114 |
+
],
|
1115 |
+
"dtype": "float16",
|
1116 |
+
"format": "f32-to-bf16",
|
1117 |
+
"nbytes": 4096,
|
1118 |
+
"byteOffset": 18878464
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"name": "model.layers.13.self_attn.qkv_proj.weight",
|
1122 |
+
"shape": [
|
1123 |
+
2560,
|
1124 |
+
2048
|
1125 |
+
],
|
1126 |
+
"dtype": "float16",
|
1127 |
+
"format": "f32-to-bf16",
|
1128 |
+
"nbytes": 10485760,
|
1129 |
+
"byteOffset": 18882560
|
1130 |
+
}
|
1131 |
+
],
|
1132 |
+
"md5sum": "0ce96d9d481118f7ac43dbfc171ecb4b"
|
1133 |
+
},
|
1134 |
+
{
|
1135 |
+
"dataPath": "params_shard_34.bin",
|
1136 |
+
"format": "raw-shard",
|
1137 |
+
"nbytes": 46137344,
|
1138 |
+
"records": [
|
1139 |
+
{
|
1140 |
+
"name": "model.layers.13.mlp.gate_up_proj.weight",
|
1141 |
+
"shape": [
|
1142 |
+
11264,
|
1143 |
+
2048
|
1144 |
+
],
|
1145 |
+
"dtype": "float16",
|
1146 |
+
"format": "f32-to-bf16",
|
1147 |
+
"nbytes": 46137344,
|
1148 |
+
"byteOffset": 0
|
1149 |
+
}
|
1150 |
+
],
|
1151 |
+
"md5sum": "92690ce271707746793acba0ae9e6ffd"
|
1152 |
+
},
|
1153 |
+
{
|
1154 |
+
"dataPath": "params_shard_35.bin",
|
1155 |
+
"format": "raw-shard",
|
1156 |
+
"nbytes": 31465472,
|
1157 |
+
"records": [
|
1158 |
+
{
|
1159 |
+
"name": "model.layers.13.self_attn.o_proj.weight",
|
1160 |
+
"shape": [
|
1161 |
+
2048,
|
1162 |
+
2048
|
1163 |
+
],
|
1164 |
+
"dtype": "float16",
|
1165 |
+
"format": "f32-to-bf16",
|
1166 |
+
"nbytes": 8388608,
|
1167 |
+
"byteOffset": 0
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"name": "model.layers.13.mlp.down_proj.weight",
|
1171 |
+
"shape": [
|
1172 |
+
2048,
|
1173 |
+
5632
|
1174 |
+
],
|
1175 |
+
"dtype": "float16",
|
1176 |
+
"format": "f32-to-bf16",
|
1177 |
+
"nbytes": 23068672,
|
1178 |
+
"byteOffset": 8388608
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"name": "model.layers.13.input_layernorm.weight",
|
1182 |
+
"shape": [
|
1183 |
+
2048
|
1184 |
+
],
|
1185 |
+
"dtype": "float16",
|
1186 |
+
"format": "f32-to-bf16",
|
1187 |
+
"nbytes": 4096,
|
1188 |
+
"byteOffset": 31457280
|
1189 |
+
},
|
1190 |
+
{
|
1191 |
+
"name": "model.layers.13.post_attention_layernorm.weight",
|
1192 |
+
"shape": [
|
1193 |
+
2048
|
1194 |
+
],
|
1195 |
+
"dtype": "float16",
|
1196 |
+
"format": "f32-to-bf16",
|
1197 |
+
"nbytes": 4096,
|
1198 |
+
"byteOffset": 31461376
|
1199 |
+
}
|
1200 |
+
],
|
1201 |
+
"md5sum": "c870963c9079f502d95ed8a60916aa09"
|
1202 |
+
},
|
1203 |
+
{
|
1204 |
+
"dataPath": "params_shard_36.bin",
|
1205 |
+
"format": "raw-shard",
|
1206 |
+
"nbytes": 46137344,
|
1207 |
+
"records": [
|
1208 |
+
{
|
1209 |
+
"name": "model.layers.14.mlp.gate_up_proj.weight",
|
1210 |
+
"shape": [
|
1211 |
+
11264,
|
1212 |
+
2048
|
1213 |
+
],
|
1214 |
+
"dtype": "float16",
|
1215 |
+
"format": "f32-to-bf16",
|
1216 |
+
"nbytes": 46137344,
|
1217 |
+
"byteOffset": 0
|
1218 |
+
}
|
1219 |
+
],
|
1220 |
+
"md5sum": "7af04b96dd3e71c5e3a1f44ad173bfea"
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"dataPath": "params_shard_37.bin",
|
1224 |
+
"format": "raw-shard",
|
1225 |
+
"nbytes": 23068672,
|
1226 |
+
"records": [
|
1227 |
+
{
|
1228 |
+
"name": "model.layers.14.mlp.down_proj.weight",
|
1229 |
+
"shape": [
|
1230 |
+
2048,
|
1231 |
+
5632
|
1232 |
+
],
|
1233 |
+
"dtype": "float16",
|
1234 |
+
"format": "f32-to-bf16",
|
1235 |
+
"nbytes": 23068672,
|
1236 |
+
"byteOffset": 0
|
1237 |
+
}
|
1238 |
+
],
|
1239 |
+
"md5sum": "1cac728a2b22e3b77fb5dbbd1e9229b0"
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"dataPath": "params_shard_38.bin",
|
1243 |
+
"format": "raw-shard",
|
1244 |
+
"nbytes": 29368320,
|
1245 |
+
"records": [
|
1246 |
+
{
|
1247 |
+
"name": "model.layers.14.self_attn.qkv_proj.weight",
|
1248 |
+
"shape": [
|
1249 |
+
2560,
|
1250 |
+
2048
|
1251 |
+
],
|
1252 |
+
"dtype": "float16",
|
1253 |
+
"format": "f32-to-bf16",
|
1254 |
+
"nbytes": 10485760,
|
1255 |
+
"byteOffset": 0
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"name": "model.layers.14.self_attn.o_proj.weight",
|
1259 |
+
"shape": [
|
1260 |
+
2048,
|
1261 |
+
2048
|
1262 |
+
],
|
1263 |
+
"dtype": "float16",
|
1264 |
+
"format": "f32-to-bf16",
|
1265 |
+
"nbytes": 8388608,
|
1266 |
+
"byteOffset": 10485760
|
1267 |
+
},
|
1268 |
+
{
|
1269 |
+
"name": "model.layers.14.input_layernorm.weight",
|
1270 |
+
"shape": [
|
1271 |
+
2048
|
1272 |
+
],
|
1273 |
+
"dtype": "float16",
|
1274 |
+
"format": "f32-to-bf16",
|
1275 |
+
"nbytes": 4096,
|
1276 |
+
"byteOffset": 18874368
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"name": "model.layers.14.post_attention_layernorm.weight",
|
1280 |
+
"shape": [
|
1281 |
+
2048
|
1282 |
+
],
|
1283 |
+
"dtype": "float16",
|
1284 |
+
"format": "f32-to-bf16",
|
1285 |
+
"nbytes": 4096,
|
1286 |
+
"byteOffset": 18878464
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"name": "model.layers.15.self_attn.qkv_proj.weight",
|
1290 |
+
"shape": [
|
1291 |
+
2560,
|
1292 |
+
2048
|
1293 |
+
],
|
1294 |
+
"dtype": "float16",
|
1295 |
+
"format": "f32-to-bf16",
|
1296 |
+
"nbytes": 10485760,
|
1297 |
+
"byteOffset": 18882560
|
1298 |
+
}
|
1299 |
+
],
|
1300 |
+
"md5sum": "4b5371f16710560fa21e987b817454da"
|
1301 |
+
},
|
1302 |
+
{
|
1303 |
+
"dataPath": "params_shard_39.bin",
|
1304 |
+
"format": "raw-shard",
|
1305 |
+
"nbytes": 46137344,
|
1306 |
+
"records": [
|
1307 |
+
{
|
1308 |
+
"name": "model.layers.15.mlp.gate_up_proj.weight",
|
1309 |
+
"shape": [
|
1310 |
+
11264,
|
1311 |
+
2048
|
1312 |
+
],
|
1313 |
+
"dtype": "float16",
|
1314 |
+
"format": "f32-to-bf16",
|
1315 |
+
"nbytes": 46137344,
|
1316 |
+
"byteOffset": 0
|
1317 |
+
}
|
1318 |
+
],
|
1319 |
+
"md5sum": "cb4c8bf7627c3697ba73cec668f987d1"
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"dataPath": "params_shard_40.bin",
|
1323 |
+
"format": "raw-shard",
|
1324 |
+
"nbytes": 31465472,
|
1325 |
+
"records": [
|
1326 |
+
{
|
1327 |
+
"name": "model.layers.15.self_attn.o_proj.weight",
|
1328 |
+
"shape": [
|
1329 |
+
2048,
|
1330 |
+
2048
|
1331 |
+
],
|
1332 |
+
"dtype": "float16",
|
1333 |
+
"format": "f32-to-bf16",
|
1334 |
+
"nbytes": 8388608,
|
1335 |
+
"byteOffset": 0
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"name": "model.layers.15.mlp.down_proj.weight",
|
1339 |
+
"shape": [
|
1340 |
+
2048,
|
1341 |
+
5632
|
1342 |
+
],
|
1343 |
+
"dtype": "float16",
|
1344 |
+
"format": "f32-to-bf16",
|
1345 |
+
"nbytes": 23068672,
|
1346 |
+
"byteOffset": 8388608
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"name": "model.layers.15.input_layernorm.weight",
|
1350 |
+
"shape": [
|
1351 |
+
2048
|
1352 |
+
],
|
1353 |
+
"dtype": "float16",
|
1354 |
+
"format": "f32-to-bf16",
|
1355 |
+
"nbytes": 4096,
|
1356 |
+
"byteOffset": 31457280
|
1357 |
+
},
|
1358 |
+
{
|
1359 |
+
"name": "model.layers.15.post_attention_layernorm.weight",
|
1360 |
+
"shape": [
|
1361 |
+
2048
|
1362 |
+
],
|
1363 |
+
"dtype": "float16",
|
1364 |
+
"format": "f32-to-bf16",
|
1365 |
+
"nbytes": 4096,
|
1366 |
+
"byteOffset": 31461376
|
1367 |
+
}
|
1368 |
+
],
|
1369 |
+
"md5sum": "8fe785d8625614bc39f3ed1208e58474"
|
1370 |
+
},
|
1371 |
+
{
|
1372 |
+
"dataPath": "params_shard_41.bin",
|
1373 |
+
"format": "raw-shard",
|
1374 |
+
"nbytes": 46137344,
|
1375 |
+
"records": [
|
1376 |
+
{
|
1377 |
+
"name": "model.layers.16.mlp.gate_up_proj.weight",
|
1378 |
+
"shape": [
|
1379 |
+
11264,
|
1380 |
+
2048
|
1381 |
+
],
|
1382 |
+
"dtype": "float16",
|
1383 |
+
"format": "f32-to-bf16",
|
1384 |
+
"nbytes": 46137344,
|
1385 |
+
"byteOffset": 0
|
1386 |
+
}
|
1387 |
+
],
|
1388 |
+
"md5sum": "f514dd7d4766f1c8a60da5165c242ed2"
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"dataPath": "params_shard_42.bin",
|
1392 |
+
"format": "raw-shard",
|
1393 |
+
"nbytes": 23068672,
|
1394 |
+
"records": [
|
1395 |
+
{
|
1396 |
+
"name": "model.layers.16.mlp.down_proj.weight",
|
1397 |
+
"shape": [
|
1398 |
+
2048,
|
1399 |
+
5632
|
1400 |
+
],
|
1401 |
+
"dtype": "float16",
|
1402 |
+
"format": "f32-to-bf16",
|
1403 |
+
"nbytes": 23068672,
|
1404 |
+
"byteOffset": 0
|
1405 |
+
}
|
1406 |
+
],
|
1407 |
+
"md5sum": "b13d9ae43b7fa845b48c5b6de94570a7"
|
1408 |
+
},
|
1409 |
+
{
|
1410 |
+
"dataPath": "params_shard_43.bin",
|
1411 |
+
"format": "raw-shard",
|
1412 |
+
"nbytes": 29368320,
|
1413 |
+
"records": [
|
1414 |
+
{
|
1415 |
+
"name": "model.layers.16.self_attn.qkv_proj.weight",
|
1416 |
+
"shape": [
|
1417 |
+
2560,
|
1418 |
+
2048
|
1419 |
+
],
|
1420 |
+
"dtype": "float16",
|
1421 |
+
"format": "f32-to-bf16",
|
1422 |
+
"nbytes": 10485760,
|
1423 |
+
"byteOffset": 0
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"name": "model.layers.16.self_attn.o_proj.weight",
|
1427 |
+
"shape": [
|
1428 |
+
2048,
|
1429 |
+
2048
|
1430 |
+
],
|
1431 |
+
"dtype": "float16",
|
1432 |
+
"format": "f32-to-bf16",
|
1433 |
+
"nbytes": 8388608,
|
1434 |
+
"byteOffset": 10485760
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"name": "model.layers.16.input_layernorm.weight",
|
1438 |
+
"shape": [
|
1439 |
+
2048
|
1440 |
+
],
|
1441 |
+
"dtype": "float16",
|
1442 |
+
"format": "f32-to-bf16",
|
1443 |
+
"nbytes": 4096,
|
1444 |
+
"byteOffset": 18874368
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"name": "model.layers.16.post_attention_layernorm.weight",
|
1448 |
+
"shape": [
|
1449 |
+
2048
|
1450 |
+
],
|
1451 |
+
"dtype": "float16",
|
1452 |
+
"format": "f32-to-bf16",
|
1453 |
+
"nbytes": 4096,
|
1454 |
+
"byteOffset": 18878464
|
1455 |
+
},
|
1456 |
+
{
|
1457 |
+
"name": "model.layers.17.self_attn.qkv_proj.weight",
|
1458 |
+
"shape": [
|
1459 |
+
2560,
|
1460 |
+
2048
|
1461 |
+
],
|
1462 |
+
"dtype": "float16",
|
1463 |
+
"format": "f32-to-bf16",
|
1464 |
+
"nbytes": 10485760,
|
1465 |
+
"byteOffset": 18882560
|
1466 |
+
}
|
1467 |
+
],
|
1468 |
+
"md5sum": "2cf9caca3db423106041ffe5cf949e53"
|
1469 |
+
},
|
1470 |
+
{
|
1471 |
+
"dataPath": "params_shard_44.bin",
|
1472 |
+
"format": "raw-shard",
|
1473 |
+
"nbytes": 46137344,
|
1474 |
+
"records": [
|
1475 |
+
{
|
1476 |
+
"name": "model.layers.17.mlp.gate_up_proj.weight",
|
1477 |
+
"shape": [
|
1478 |
+
11264,
|
1479 |
+
2048
|
1480 |
+
],
|
1481 |
+
"dtype": "float16",
|
1482 |
+
"format": "f32-to-bf16",
|
1483 |
+
"nbytes": 46137344,
|
1484 |
+
"byteOffset": 0
|
1485 |
+
}
|
1486 |
+
],
|
1487 |
+
"md5sum": "1d4c5281fe2e612feeb25bbbc88bf456"
|
1488 |
+
},
|
1489 |
+
{
|
1490 |
+
"dataPath": "params_shard_45.bin",
|
1491 |
+
"format": "raw-shard",
|
1492 |
+
"nbytes": 31465472,
|
1493 |
+
"records": [
|
1494 |
+
{
|
1495 |
+
"name": "model.layers.17.self_attn.o_proj.weight",
|
1496 |
+
"shape": [
|
1497 |
+
2048,
|
1498 |
+
2048
|
1499 |
+
],
|
1500 |
+
"dtype": "float16",
|
1501 |
+
"format": "f32-to-bf16",
|
1502 |
+
"nbytes": 8388608,
|
1503 |
+
"byteOffset": 0
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"name": "model.layers.17.mlp.down_proj.weight",
|
1507 |
+
"shape": [
|
1508 |
+
2048,
|
1509 |
+
5632
|
1510 |
+
],
|
1511 |
+
"dtype": "float16",
|
1512 |
+
"format": "f32-to-bf16",
|
1513 |
+
"nbytes": 23068672,
|
1514 |
+
"byteOffset": 8388608
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"name": "model.layers.17.input_layernorm.weight",
|
1518 |
+
"shape": [
|
1519 |
+
2048
|
1520 |
+
],
|
1521 |
+
"dtype": "float16",
|
1522 |
+
"format": "f32-to-bf16",
|
1523 |
+
"nbytes": 4096,
|
1524 |
+
"byteOffset": 31457280
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"name": "model.layers.17.post_attention_layernorm.weight",
|
1528 |
+
"shape": [
|
1529 |
+
2048
|
1530 |
+
],
|
1531 |
+
"dtype": "float16",
|
1532 |
+
"format": "f32-to-bf16",
|
1533 |
+
"nbytes": 4096,
|
1534 |
+
"byteOffset": 31461376
|
1535 |
+
}
|
1536 |
+
],
|
1537 |
+
"md5sum": "c46540c97c546722e81d362b9b2053d0"
|
1538 |
+
},
|
1539 |
+
{
|
1540 |
+
"dataPath": "params_shard_46.bin",
|
1541 |
+
"format": "raw-shard",
|
1542 |
+
"nbytes": 46137344,
|
1543 |
+
"records": [
|
1544 |
+
{
|
1545 |
+
"name": "model.layers.18.mlp.gate_up_proj.weight",
|
1546 |
+
"shape": [
|
1547 |
+
11264,
|
1548 |
+
2048
|
1549 |
+
],
|
1550 |
+
"dtype": "float16",
|
1551 |
+
"format": "f32-to-bf16",
|
1552 |
+
"nbytes": 46137344,
|
1553 |
+
"byteOffset": 0
|
1554 |
+
}
|
1555 |
+
],
|
1556 |
+
"md5sum": "92534c963098e40f8e494024f7cc171a"
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"dataPath": "params_shard_47.bin",
|
1560 |
+
"format": "raw-shard",
|
1561 |
+
"nbytes": 23068672,
|
1562 |
+
"records": [
|
1563 |
+
{
|
1564 |
+
"name": "model.layers.18.mlp.down_proj.weight",
|
1565 |
+
"shape": [
|
1566 |
+
2048,
|
1567 |
+
5632
|
1568 |
+
],
|
1569 |
+
"dtype": "float16",
|
1570 |
+
"format": "f32-to-bf16",
|
1571 |
+
"nbytes": 23068672,
|
1572 |
+
"byteOffset": 0
|
1573 |
+
}
|
1574 |
+
],
|
1575 |
+
"md5sum": "9b9d559b2302c551f2433ffe8781934c"
|
1576 |
+
},
|
1577 |
+
{
|
1578 |
+
"dataPath": "params_shard_48.bin",
|
1579 |
+
"format": "raw-shard",
|
1580 |
+
"nbytes": 29368320,
|
1581 |
+
"records": [
|
1582 |
+
{
|
1583 |
+
"name": "model.layers.18.self_attn.qkv_proj.weight",
|
1584 |
+
"shape": [
|
1585 |
+
2560,
|
1586 |
+
2048
|
1587 |
+
],
|
1588 |
+
"dtype": "float16",
|
1589 |
+
"format": "f32-to-bf16",
|
1590 |
+
"nbytes": 10485760,
|
1591 |
+
"byteOffset": 0
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"name": "model.layers.18.self_attn.o_proj.weight",
|
1595 |
+
"shape": [
|
1596 |
+
2048,
|
1597 |
+
2048
|
1598 |
+
],
|
1599 |
+
"dtype": "float16",
|
1600 |
+
"format": "f32-to-bf16",
|
1601 |
+
"nbytes": 8388608,
|
1602 |
+
"byteOffset": 10485760
|
1603 |
+
},
|
1604 |
+
{
|
1605 |
+
"name": "model.layers.18.input_layernorm.weight",
|
1606 |
+
"shape": [
|
1607 |
+
2048
|
1608 |
+
],
|
1609 |
+
"dtype": "float16",
|
1610 |
+
"format": "f32-to-bf16",
|
1611 |
+
"nbytes": 4096,
|
1612 |
+
"byteOffset": 18874368
|
1613 |
+
},
|
1614 |
+
{
|
1615 |
+
"name": "model.layers.18.post_attention_layernorm.weight",
|
1616 |
+
"shape": [
|
1617 |
+
2048
|
1618 |
+
],
|
1619 |
+
"dtype": "float16",
|
1620 |
+
"format": "f32-to-bf16",
|
1621 |
+
"nbytes": 4096,
|
1622 |
+
"byteOffset": 18878464
|
1623 |
+
},
|
1624 |
+
{
|
1625 |
+
"name": "model.layers.19.self_attn.qkv_proj.weight",
|
1626 |
+
"shape": [
|
1627 |
+
2560,
|
1628 |
+
2048
|
1629 |
+
],
|
1630 |
+
"dtype": "float16",
|
1631 |
+
"format": "f32-to-bf16",
|
1632 |
+
"nbytes": 10485760,
|
1633 |
+
"byteOffset": 18882560
|
1634 |
+
}
|
1635 |
+
],
|
1636 |
+
"md5sum": "7089659a826cdffdd85fc286918b3c0e"
|
1637 |
+
},
|
1638 |
+
{
|
1639 |
+
"dataPath": "params_shard_49.bin",
|
1640 |
+
"format": "raw-shard",
|
1641 |
+
"nbytes": 46137344,
|
1642 |
+
"records": [
|
1643 |
+
{
|
1644 |
+
"name": "model.layers.19.mlp.gate_up_proj.weight",
|
1645 |
+
"shape": [
|
1646 |
+
11264,
|
1647 |
+
2048
|
1648 |
+
],
|
1649 |
+
"dtype": "float16",
|
1650 |
+
"format": "f32-to-bf16",
|
1651 |
+
"nbytes": 46137344,
|
1652 |
+
"byteOffset": 0
|
1653 |
+
}
|
1654 |
+
],
|
1655 |
+
"md5sum": "0b818102d48e4f8060cc389ba0d8c7bd"
|
1656 |
+
},
|
1657 |
+
{
|
1658 |
+
"dataPath": "params_shard_50.bin",
|
1659 |
+
"format": "raw-shard",
|
1660 |
+
"nbytes": 31465472,
|
1661 |
+
"records": [
|
1662 |
+
{
|
1663 |
+
"name": "model.layers.19.self_attn.o_proj.weight",
|
1664 |
+
"shape": [
|
1665 |
+
2048,
|
1666 |
+
2048
|
1667 |
+
],
|
1668 |
+
"dtype": "float16",
|
1669 |
+
"format": "f32-to-bf16",
|
1670 |
+
"nbytes": 8388608,
|
1671 |
+
"byteOffset": 0
|
1672 |
+
},
|
1673 |
+
{
|
1674 |
+
"name": "model.layers.19.mlp.down_proj.weight",
|
1675 |
+
"shape": [
|
1676 |
+
2048,
|
1677 |
+
5632
|
1678 |
+
],
|
1679 |
+
"dtype": "float16",
|
1680 |
+
"format": "f32-to-bf16",
|
1681 |
+
"nbytes": 23068672,
|
1682 |
+
"byteOffset": 8388608
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"name": "model.layers.19.input_layernorm.weight",
|
1686 |
+
"shape": [
|
1687 |
+
2048
|
1688 |
+
],
|
1689 |
+
"dtype": "float16",
|
1690 |
+
"format": "f32-to-bf16",
|
1691 |
+
"nbytes": 4096,
|
1692 |
+
"byteOffset": 31457280
|
1693 |
+
},
|
1694 |
+
{
|
1695 |
+
"name": "model.layers.19.post_attention_layernorm.weight",
|
1696 |
+
"shape": [
|
1697 |
+
2048
|
1698 |
+
],
|
1699 |
+
"dtype": "float16",
|
1700 |
+
"format": "f32-to-bf16",
|
1701 |
+
"nbytes": 4096,
|
1702 |
+
"byteOffset": 31461376
|
1703 |
+
}
|
1704 |
+
],
|
1705 |
+
"md5sum": "da376ebd90a6fb758ae26a1e5f1bb459"
|
1706 |
+
},
|
1707 |
+
{
|
1708 |
+
"dataPath": "params_shard_51.bin",
|
1709 |
+
"format": "raw-shard",
|
1710 |
+
"nbytes": 46137344,
|
1711 |
+
"records": [
|
1712 |
+
{
|
1713 |
+
"name": "model.layers.20.mlp.gate_up_proj.weight",
|
1714 |
+
"shape": [
|
1715 |
+
11264,
|
1716 |
+
2048
|
1717 |
+
],
|
1718 |
+
"dtype": "float16",
|
1719 |
+
"format": "f32-to-bf16",
|
1720 |
+
"nbytes": 46137344,
|
1721 |
+
"byteOffset": 0
|
1722 |
+
}
|
1723 |
+
],
|
1724 |
+
"md5sum": "07983db1555010f4e29efc70ae893c31"
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"dataPath": "params_shard_52.bin",
|
1728 |
+
"format": "raw-shard",
|
1729 |
+
"nbytes": 23068672,
|
1730 |
+
"records": [
|
1731 |
+
{
|
1732 |
+
"name": "model.layers.20.mlp.down_proj.weight",
|
1733 |
+
"shape": [
|
1734 |
+
2048,
|
1735 |
+
5632
|
1736 |
+
],
|
1737 |
+
"dtype": "float16",
|
1738 |
+
"format": "f32-to-bf16",
|
1739 |
+
"nbytes": 23068672,
|
1740 |
+
"byteOffset": 0
|
1741 |
+
}
|
1742 |
+
],
|
1743 |
+
"md5sum": "8f144f9da86834343511a82586a630a1"
|
1744 |
+
},
|
1745 |
+
{
|
1746 |
+
"dataPath": "params_shard_53.bin",
|
1747 |
+
"format": "raw-shard",
|
1748 |
+
"nbytes": 29368320,
|
1749 |
+
"records": [
|
1750 |
+
{
|
1751 |
+
"name": "model.layers.20.self_attn.qkv_proj.weight",
|
1752 |
+
"shape": [
|
1753 |
+
2560,
|
1754 |
+
2048
|
1755 |
+
],
|
1756 |
+
"dtype": "float16",
|
1757 |
+
"format": "f32-to-bf16",
|
1758 |
+
"nbytes": 10485760,
|
1759 |
+
"byteOffset": 0
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"name": "model.layers.20.self_attn.o_proj.weight",
|
1763 |
+
"shape": [
|
1764 |
+
2048,
|
1765 |
+
2048
|
1766 |
+
],
|
1767 |
+
"dtype": "float16",
|
1768 |
+
"format": "f32-to-bf16",
|
1769 |
+
"nbytes": 8388608,
|
1770 |
+
"byteOffset": 10485760
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"name": "model.layers.20.input_layernorm.weight",
|
1774 |
+
"shape": [
|
1775 |
+
2048
|
1776 |
+
],
|
1777 |
+
"dtype": "float16",
|
1778 |
+
"format": "f32-to-bf16",
|
1779 |
+
"nbytes": 4096,
|
1780 |
+
"byteOffset": 18874368
|
1781 |
+
},
|
1782 |
+
{
|
1783 |
+
"name": "model.layers.20.post_attention_layernorm.weight",
|
1784 |
+
"shape": [
|
1785 |
+
2048
|
1786 |
+
],
|
1787 |
+
"dtype": "float16",
|
1788 |
+
"format": "f32-to-bf16",
|
1789 |
+
"nbytes": 4096,
|
1790 |
+
"byteOffset": 18878464
|
1791 |
+
},
|
1792 |
+
{
|
1793 |
+
"name": "model.layers.21.self_attn.qkv_proj.weight",
|
1794 |
+
"shape": [
|
1795 |
+
2560,
|
1796 |
+
2048
|
1797 |
+
],
|
1798 |
+
"dtype": "float16",
|
1799 |
+
"format": "f32-to-bf16",
|
1800 |
+
"nbytes": 10485760,
|
1801 |
+
"byteOffset": 18882560
|
1802 |
+
}
|
1803 |
+
],
|
1804 |
+
"md5sum": "d9e65b87963f1b12a61db61b5e22b006"
|
1805 |
+
},
|
1806 |
+
{
|
1807 |
+
"dataPath": "params_shard_54.bin",
|
1808 |
+
"format": "raw-shard",
|
1809 |
+
"nbytes": 46137344,
|
1810 |
+
"records": [
|
1811 |
+
{
|
1812 |
+
"name": "model.layers.21.mlp.gate_up_proj.weight",
|
1813 |
+
"shape": [
|
1814 |
+
11264,
|
1815 |
+
2048
|
1816 |
+
],
|
1817 |
+
"dtype": "float16",
|
1818 |
+
"format": "f32-to-bf16",
|
1819 |
+
"nbytes": 46137344,
|
1820 |
+
"byteOffset": 0
|
1821 |
+
}
|
1822 |
+
],
|
1823 |
+
"md5sum": "cca1c44db48008d5c6c9ac8ebf8b4725"
|
1824 |
+
},
|
1825 |
+
{
|
1826 |
+
"dataPath": "params_shard_55.bin",
|
1827 |
+
"format": "raw-shard",
|
1828 |
+
"nbytes": 131072000,
|
1829 |
+
"records": [
|
1830 |
+
{
|
1831 |
+
"name": "lm_head.weight",
|
1832 |
+
"shape": [
|
1833 |
+
32000,
|
1834 |
+
2048
|
1835 |
+
],
|
1836 |
+
"dtype": "float16",
|
1837 |
+
"format": "f32-to-bf16",
|
1838 |
+
"nbytes": 131072000,
|
1839 |
+
"byteOffset": 0
|
1840 |
+
}
|
1841 |
+
],
|
1842 |
+
"md5sum": "7a3246d2a0c89b32df828dd06944d490"
|
1843 |
+
},
|
1844 |
+
{
|
1845 |
+
"dataPath": "params_shard_56.bin",
|
1846 |
+
"format": "raw-shard",
|
1847 |
+
"nbytes": 31469568,
|
1848 |
+
"records": [
|
1849 |
+
{
|
1850 |
+
"name": "model.layers.21.self_attn.o_proj.weight",
|
1851 |
+
"shape": [
|
1852 |
+
2048,
|
1853 |
+
2048
|
1854 |
+
],
|
1855 |
+
"dtype": "float16",
|
1856 |
+
"format": "f32-to-bf16",
|
1857 |
+
"nbytes": 8388608,
|
1858 |
+
"byteOffset": 0
|
1859 |
+
},
|
1860 |
+
{
|
1861 |
+
"name": "model.layers.21.mlp.down_proj.weight",
|
1862 |
+
"shape": [
|
1863 |
+
2048,
|
1864 |
+
5632
|
1865 |
+
],
|
1866 |
+
"dtype": "float16",
|
1867 |
+
"format": "f32-to-bf16",
|
1868 |
+
"nbytes": 23068672,
|
1869 |
+
"byteOffset": 8388608
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"name": "model.layers.21.input_layernorm.weight",
|
1873 |
+
"shape": [
|
1874 |
+
2048
|
1875 |
+
],
|
1876 |
+
"dtype": "float16",
|
1877 |
+
"format": "f32-to-bf16",
|
1878 |
+
"nbytes": 4096,
|
1879 |
+
"byteOffset": 31457280
|
1880 |
+
},
|
1881 |
+
{
|
1882 |
+
"name": "model.layers.21.post_attention_layernorm.weight",
|
1883 |
+
"shape": [
|
1884 |
+
2048
|
1885 |
+
],
|
1886 |
+
"dtype": "float16",
|
1887 |
+
"format": "f32-to-bf16",
|
1888 |
+
"nbytes": 4096,
|
1889 |
+
"byteOffset": 31461376
|
1890 |
+
},
|
1891 |
+
{
|
1892 |
+
"name": "model.norm.weight",
|
1893 |
+
"shape": [
|
1894 |
+
2048
|
1895 |
+
],
|
1896 |
+
"dtype": "float16",
|
1897 |
+
"format": "f32-to-bf16",
|
1898 |
+
"nbytes": 4096,
|
1899 |
+
"byteOffset": 31465472
|
1900 |
+
}
|
1901 |
+
],
|
1902 |
+
"md5sum": "697def5fa1e5ab0181768796ae6277f3"
|
1903 |
+
}
|
1904 |
+
]
|
1905 |
+
}
|
params_shard_0.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a19f7f87718f06954955b57c12f6bb06799afd7c2e69e0c5352fbbe2ff2e4b7
|
3 |
+
size 131072000
|
params_shard_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0bb37ca3c8d29d52008bcd0ed5d5059ef33ede11d74decbe1a0b56339c36c49
|
3 |
+
size 46137344
|
params_shard_10.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:236f98bc531b1cbee4135347f3653c52b5e31d57705af2c5ab9a2bbbc09152fe
|
3 |
+
size 31465472
|
params_shard_11.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a281af83fda395ad64b189345fb9c813a7400c1034de2480217bd4aff94ed1e2
|
3 |
+
size 46137344
|
params_shard_12.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1d9664db54c46e805f8d5971097ac3876bb158458a6b53ed5478f95165aa1ae
|
3 |
+
size 23068672
|
params_shard_13.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6626b08a7f7bfde93f6e4bb1d55f7ad1d72fa7cad63f25164a413784d2b6bd29
|
3 |
+
size 29368320
|
params_shard_14.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0671e669bbd4ebf22caf6dd5bc6473847be93096ee303646e404537f018f28da
|
3 |
+
size 46137344
|
params_shard_15.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f99c94b7ee0a6d58f6d51b377d58b4925c1657859455aae1d17533e6cf32c0ba
|
3 |
+
size 31465472
|
params_shard_16.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a56aeb27dc04381158197813f221ef42954d6f9ebc33dcb1ab99b3aff693c7c
|
3 |
+
size 46137344
|
params_shard_17.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d714abbdb5057ea6a8d3f8ff97205109ca001c72bca69c0a7f33b47179ac18f1
|
3 |
+
size 23068672
|
params_shard_18.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e353be0f87cbf94c119258def104caa2181d15d28d4f169d59a1a383e55ea8e5
|
3 |
+
size 29368320
|
params_shard_19.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1824e15c9572a396d92731c33ce864cdfdcb8a2b32447aac2c2c2e15ad7b7453
|
3 |
+
size 46137344
|
params_shard_2.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48309a4eebae5233fd903e9743916dafd02e4e7e785dc533325e875616e45124
|
3 |
+
size 23068672
|
params_shard_20.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c8d1d14479aa5f042d5757e24dffb7b0e8a964e0ca921cee5b35395cc1d80f1
|
3 |
+
size 31465472
|
params_shard_21.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5c79f38b2c234e4c217d2c4bf848f8d2b34cd5122633208af9678b2ee82b6e5
|
3 |
+
size 46137344
|
params_shard_22.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d2e4d208d111abd7eb7e2fa54b1c05bc828d6d80ec6885ec8011c3b701c5274
|
3 |
+
size 23068672
|
params_shard_23.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f34df87275db5d647663ba9b4577131bc9b3e49d6f0741768de8a02f719e957
|
3 |
+
size 29368320
|
params_shard_24.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c548520c8cf0d3010b7e6158bfb4f9f9bfe47e6fd2814cc23efd79e4f65184e4
|
3 |
+
size 46137344
|
params_shard_25.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caa48af12d0604667764c66b7c3841f02f9cf471f4377f174b9899cc63dd686f
|
3 |
+
size 31465472
|
params_shard_26.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87a25a0f7712ac72051511f5e8fae0fa700699a3a8b19f76dfaa04becb008e93
|
3 |
+
size 46137344
|
params_shard_27.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c6a0ab4872b427e4647c91376637306111701a9da3b5d439791454eed8d9f37
|
3 |
+
size 23068672
|
params_shard_28.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:253fa2b671f6916828df6cd573fcc84d6f80af52d218e154fa4d0fc52e428332
|
3 |
+
size 29368320
|
params_shard_29.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd347158caf3bc1aa7186ed82554a2f65834e7491c0efe0936ec339ac06bbf99
|
3 |
+
size 46137344
|
params_shard_3.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34a4978cd44570aacd981229d9e3629b8c285f276b048bd572f09329f9bdeb5d
|
3 |
+
size 29368320
|
params_shard_30.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce1122b25abf0646170c8d6ff103bea557641d9a9afdad743520925a1f2d53b8
|
3 |
+
size 31465472
|
params_shard_31.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d544c272d158341b054510efa38bde5bb1c9bbd4379343431d62cfdf5bf0dd70
|
3 |
+
size 46137344
|
params_shard_32.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71a4a6603fb20b7eb2bbe43c76ad37de51f8eb2f0cf34d9e8877edc6b7654014
|
3 |
+
size 23068672
|
params_shard_33.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:763e55000a3782718d88ed3857d7336b09ad33cde7a67344b924d6eefd32489d
|
3 |
+
size 29368320
|
params_shard_34.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1146d7a6970acf8301e2cb81f5feb293ae0bbfe6fe19bad4ed4d9c541eaec04
|
3 |
+
size 46137344
|
params_shard_35.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6344112916225b1fc518360d551ebc04f7eb13151a297dead59b062d3ebfb871
|
3 |
+
size 31465472
|
params_shard_36.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9a76adb19bd9e062e94c9d7432e09b2777452c2989e496d4d91364fa893730b
|
3 |
+
size 46137344
|
params_shard_37.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d9d9538c88ed10f0cdda0962b7a539b09dea66580afd5a14ef7d50c3eca281d
|
3 |
+
size 23068672
|
params_shard_38.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9d6dbfbc278b0fc5a920a38ddaa79eceb11455484dccb0fc7df716ef8a7cc58
|
3 |
+
size 29368320
|
params_shard_39.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:664397497e13cf9ace889bf90826c70ec16abf31e700baeda04ef58d31e8ec6b
|
3 |
+
size 46137344
|
params_shard_4.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f147d209fd1a2fa1a292e88f4cf66094183482a22b87129278894d1a8192a30f
|
3 |
+
size 46137344
|
params_shard_40.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d39d0d5752cd9c541e29a7c51e62a8622eba6aa9a16f859b2d3044e7fa14510e
|
3 |
+
size 31465472
|
params_shard_41.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:979ae35a1fb6fc7078418e62c9366c11e5fe18b0e2a12b445dcef48bbc18508c
|
3 |
+
size 46137344
|
params_shard_42.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a36b631c4cc8fbcf5ef11570dbba9129be5465a9cb04aac8530ff392e4c742c
|
3 |
+
size 23068672
|
params_shard_43.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc027388c71eb379d700385b27d4dbc5f0c5df3cec9ce6b3253f1dcede88178c
|
3 |
+
size 29368320
|
params_shard_44.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:424018465f961c43a6175cf34d4c5aab2310a1cfc51b2cb43e3172493146905f
|
3 |
+
size 46137344
|
params_shard_45.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f06b6ccb80d1853128955c2fd7e4683f8ed52ba6288819114afbdef8210cb482
|
3 |
+
size 31465472
|
params_shard_46.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d7e49025a4e8d7bfe278f1d9164c7af5c0ed94f1213ea6bd45fe0168b7d1085
|
3 |
+
size 46137344
|
params_shard_47.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e4d56cb9613c840b09c33c2be7c7e85bad1a2c404350f07e90bb7d133be3b18
|
3 |
+
size 23068672
|
params_shard_48.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49438b6e3a8ddd57839d5c21d6474c7a38f19613d0df78e8ed95f53a98ee78ef
|
3 |
+
size 29368320
|
params_shard_49.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa1c3d8018d424c7bd7969c86a5fd40627ce838426f7c06a8a4d613a22f6716e
|
3 |
+
size 46137344
|
params_shard_5.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:680092984265bbc007409cb7b7bfa89fb653478fa94bf051fcc5e416b017cbca
|
3 |
+
size 31465472
|