Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- chat_template.jinja +87 -0
- config.json +31 -0
- model-00001-of-00016.safetensors +3 -0
- model-00002-of-00016.safetensors +3 -0
- model-00003-of-00016.safetensors +3 -0
- model-00004-of-00016.safetensors +3 -0
- model-00005-of-00016.safetensors +3 -0
- model-00006-of-00016.safetensors +3 -0
- model-00007-of-00016.safetensors +3 -0
- model-00008-of-00016.safetensors +3 -0
- model-00009-of-00016.safetensors +3 -0
- model-00010-of-00016.safetensors +3 -0
- model-00011-of-00016.safetensors +3 -0
- model-00012-of-00016.safetensors +3 -0
- model-00013-of-00016.safetensors +3 -0
- model-00014-of-00016.safetensors +3 -0
- model-00015-of-00016.safetensors +3 -0
- model-00016-of-00016.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +24 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
chat_template.jinja
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{%- if messages[0]["role"] == "system" %}
|
2 |
+
{%- set system_message = messages[0]["content"] %}
|
3 |
+
{%- set loop_messages = messages[1:] %}
|
4 |
+
{%- else %}
|
5 |
+
{%- set loop_messages = messages %}
|
6 |
+
{%- endif %}
|
7 |
+
{%- if not tools is defined %}
|
8 |
+
{%- set tools = none %}
|
9 |
+
{%- endif %}
|
10 |
+
{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
|
11 |
+
|
12 |
+
{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
|
13 |
+
{%- set ns = namespace() %}
|
14 |
+
{%- set ns.index = 0 %}
|
15 |
+
{%- for message in loop_messages %}
|
16 |
+
{%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
|
17 |
+
{%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
|
18 |
+
{{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
|
19 |
+
{%- endif %}
|
20 |
+
{%- set ns.index = ns.index + 1 %}
|
21 |
+
{%- endif %}
|
22 |
+
{%- endfor %}
|
23 |
+
|
24 |
+
{{- bos_token }}
|
25 |
+
{%- for message in loop_messages %}
|
26 |
+
{%- if message["role"] == "user" %}
|
27 |
+
{%- if tools is not none and (message == user_messages[-1]) %}
|
28 |
+
{{- "[AVAILABLE_TOOLS][" }}
|
29 |
+
{%- for tool in tools %}
|
30 |
+
{%- set tool = tool.function %}
|
31 |
+
{{- '{"type": "function", "function": {' }}
|
32 |
+
{%- for key, val in tool.items() if key != "return" %}
|
33 |
+
{%- if val is string %}
|
34 |
+
{{- '"' + key + '": "' + val + '"' }}
|
35 |
+
{%- else %}
|
36 |
+
{{- '"' + key + '": ' + val|tojson }}
|
37 |
+
{%- endif %}
|
38 |
+
{%- if not loop.last %}
|
39 |
+
{{- ", " }}
|
40 |
+
{%- endif %}
|
41 |
+
{%- endfor %}
|
42 |
+
{{- "}}" }}
|
43 |
+
{%- if not loop.last %}
|
44 |
+
{{- ", " }}
|
45 |
+
{%- else %}
|
46 |
+
{{- "]" }}
|
47 |
+
{%- endif %}
|
48 |
+
{%- endfor %}
|
49 |
+
{{- "[/AVAILABLE_TOOLS]" }}
|
50 |
+
{%- endif %}
|
51 |
+
{%- if loop.last and system_message is defined %}
|
52 |
+
{{- "[INST]" + system_message + "\n\n" + message["content"] + "[/INST]" }}
|
53 |
+
{%- else %}
|
54 |
+
{{- "[INST]" + message["content"] + "[/INST]" }}
|
55 |
+
{%- endif %}
|
56 |
+
{%- elif (message.tool_calls is defined and message.tool_calls is not none) %}
|
57 |
+
{{- "[TOOL_CALLS][" }}
|
58 |
+
{%- for tool_call in message.tool_calls %}
|
59 |
+
{%- set out = tool_call.function|tojson %}
|
60 |
+
{{- out[:-1] }}
|
61 |
+
{%- if not tool_call.id is defined or tool_call.id|length != 9 %}
|
62 |
+
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
63 |
+
{%- endif %}
|
64 |
+
{{- ', "id": "' + tool_call.id + '"}' }}
|
65 |
+
{%- if not loop.last %}
|
66 |
+
{{- ", " }}
|
67 |
+
{%- else %}
|
68 |
+
{{- "]" + eos_token }}
|
69 |
+
{%- endif %}
|
70 |
+
{%- endfor %}
|
71 |
+
{%- elif message["role"] == "assistant" %}
|
72 |
+
{{- message["content"] + eos_token}}
|
73 |
+
{%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
|
74 |
+
{%- if message.content is defined and message.content.content is defined %}
|
75 |
+
{%- set content = message.content.content %}
|
76 |
+
{%- else %}
|
77 |
+
{%- set content = message.content %}
|
78 |
+
{%- endif %}
|
79 |
+
{{- '[TOOL_RESULTS]{"content": ' + content|string + ", " }}
|
80 |
+
{%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
|
81 |
+
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
82 |
+
{%- endif %}
|
83 |
+
{{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
|
84 |
+
{%- else %}
|
85 |
+
{{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
|
86 |
+
{%- endif %}
|
87 |
+
{%- endfor %}
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"MixtralForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"head_dim": 128,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 5120,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 1024000,
|
14 |
+
"model_type": "mixtral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
+
"num_hidden_layers": 40,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"num_local_experts": 4,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_theta": 1000000.0,
|
23 |
+
"router_aux_loss_coef": 0.001,
|
24 |
+
"router_jitter_noise": 0.0,
|
25 |
+
"sliding_window": null,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "bfloat16",
|
28 |
+
"transformers_version": "4.52.4",
|
29 |
+
"use_cache": false,
|
30 |
+
"vocab_size": 131072
|
31 |
+
}
|
model-00001-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18dc85dfdc8ca7363fb7cf0c8b5c1f9707942f1e54644daabc5218453218479e
|
3 |
+
size 4928352712
|
model-00002-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d38490ea7867c568bdb5362b22375cce10face453ac414c05f10f8f5812adac4
|
3 |
+
size 4865460264
|
model-00003-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7670b3cc94287924ea71445f8454fc0b05b48367c8e03277a638ba259d3da0f
|
3 |
+
size 4865460264
|
model-00004-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e4a99fa0613f3519905377f64df0d625a007101f5dd6b68c3c9b2e3c7ee1920
|
3 |
+
size 4907382256
|
model-00005-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac3c882153185e9c705ce6d8f7bc4a37be41fd0f5e9e4569b9364e2d9aa7b93b
|
3 |
+
size 4865460304
|
model-00006-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3341f844e78507ca72999bc9768fce420320583379223c0ba42ce7a0203321c
|
3 |
+
size 4970307560
|
model-00007-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fac3c81d3f2486671d966cf587fd3fd0b2b3f1fca137277bbcece86f0f1687d0
|
3 |
+
size 4949335816
|
model-00008-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef7d2484770176018b7e3903c8141566cf718fd49b93d3bccf836f084caaccf0
|
3 |
+
size 4865460312
|
model-00009-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f0a4b66e9757bb05438c80bea6acbc12bbb0b30a85f0cdf263569b7136679f8
|
3 |
+
size 4907382296
|
model-00010-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb665e6442f15a2f62a10d112f5b363e73f82622a3462c57dd7f1b4ccdd3bcf6
|
3 |
+
size 4865460312
|
model-00011-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d315dfaa9464ca7a6255fef99b7e8a2febc16cf98c47c3f8c66fde497fe063a
|
3 |
+
size 4865460312
|
model-00012-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:698cbd13def09364c492356419d61fa9881654df5ae9378e29b8e601fbeadb4b
|
3 |
+
size 4907382296
|
model-00013-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e492d69fb8fa00f0a0a36fca256a19937a2696f076c1e490d9e39cbdcbed91c
|
3 |
+
size 4865460312
|
model-00014-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:129dccd55c175b051341790f0ca61e9822946ba7fba8f6958f820cbbbe383b64
|
3 |
+
size 4970307560
|
model-00015-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fd53c3a3c9be71a4b9367c80f3a545f1bec80f4e80d4093d6a4ef66a7bc5c5c
|
3 |
+
size 4949335816
|
model-00016-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f21eb09f0403dc912770c4490d1caf85033e030a4dede913758112aaa1ab2b7
|
3 |
+
size 3797522064
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.1.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00016.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00016.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00016.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00016.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00016.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00016.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00016.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00016.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00016.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00016.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00016.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00016.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00016.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00016.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00016.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00016.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00016.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00016.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00016.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00016.safetensors", "model.layers.19.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00016.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00016.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00016.safetensors", "model.layers.22.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00016.safetensors", "model.layers.23.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00016.safetensors", "model.layers.24.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00016.safetensors", "model.layers.25.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00016.safetensors", "model.layers.26.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00016.safetensors", "model.layers.27.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00016.safetensors", "model.layers.28.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00016.safetensors", "model.layers.29.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00016.safetensors", "model.layers.30.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00016.safetensors", "model.layers.31.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00016.safetensors", "model.layers.32.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00016.safetensors", "model.layers.33.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00016.safetensors", "model.layers.34.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00016.safetensors", "model.layers.35.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00016.safetensors", "model.layers.36.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00016.safetensors", "model.layers.37.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00016.safetensors", "model.layers.38.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00016.safetensors", "model.layers.39.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00016.safetensors", "model.norm.weight": "model-00016-of-00016.safetensors", "lm_head.weight": "model-00016-of-00016.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a046b64b5eda8178d73f3a3b5c9ff1278e6c55b2ff2628dc20bee39b3371ab7
|
3 |
+
size 17078444
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|