step 103
Browse files- config.json +51 -0
- generation_config.json +6 -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 +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"DeepseekV3ForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"aux_loss_alpha": 0.001,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"eos_token_id": 1,
|
10 |
+
"ep_size": 1,
|
11 |
+
"first_k_dense_replace": 62,
|
12 |
+
"head_dim": 64,
|
13 |
+
"hidden_act": "silu",
|
14 |
+
"hidden_size": 5120,
|
15 |
+
"initializer_range": 0.006,
|
16 |
+
"intermediate_size": 36864,
|
17 |
+
"kv_lora_rank": 512,
|
18 |
+
"max_position_embeddings": 2048,
|
19 |
+
"model_type": "deepseek_v3",
|
20 |
+
"moe_intermediate_size": 2048,
|
21 |
+
"moe_layer_freq": 1,
|
22 |
+
"n_group": 8,
|
23 |
+
"n_routed_experts": null,
|
24 |
+
"n_shared_experts": 1,
|
25 |
+
"norm_topk_prob": true,
|
26 |
+
"num_attention_heads": 64,
|
27 |
+
"num_experts_per_tok": 8,
|
28 |
+
"num_hidden_layers": 61,
|
29 |
+
"num_key_value_heads": 64,
|
30 |
+
"num_nextn_predict_layers": 1,
|
31 |
+
"pretraining_tp": 1,
|
32 |
+
"q_lora_rank": 1024,
|
33 |
+
"qk_head_dim": 192,
|
34 |
+
"qk_nope_head_dim": 128,
|
35 |
+
"qk_rope_head_dim": 64,
|
36 |
+
"rms_norm_eps": 1e-06,
|
37 |
+
"rope_interleave": true,
|
38 |
+
"rope_scaling": null,
|
39 |
+
"rope_theta": 10000,
|
40 |
+
"routed_scaling_factor": 2.5,
|
41 |
+
"scoring_func": "sigmoid",
|
42 |
+
"seq_aux": true,
|
43 |
+
"tie_word_embeddings": false,
|
44 |
+
"topk_group": 4,
|
45 |
+
"topk_method": "noaux_tc",
|
46 |
+
"torch_dtype": "bfloat16",
|
47 |
+
"transformers_version": "4.51.3",
|
48 |
+
"use_cache": true,
|
49 |
+
"v_head_dim": 128,
|
50 |
+
"vocab_size": 129280
|
51 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"transformers_version": "4.51.3"
|
6 |
+
}
|
model-00001-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:346278fc5c4bec59e4dcabde7653189a802fe90b4113bcac36f6615613a21fae
|
3 |
+
size 5197065320
|
model-00002-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0dba61408609bd5c8c33236a8085ab5ee174fd2b28c5d91a4b75f64df16907d7
|
3 |
+
size 5098800752
|
model-00003-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00122afd31a57fd16ab2a09fb1c6776cbd63c52cff33c0c35b3d54b0197b95c6
|
3 |
+
size 5098800752
|
model-00004-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:021a14d725982082ce6a1e5320f74e3dd6cb873702f1ffb97f4f1d4a83a6475d
|
3 |
+
size 5098800736
|
model-00005-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ca4c4d5d5a4012d6d8d15fea047f495a5a1b722123d6ca3da36e61853fb6de1
|
3 |
+
size 5098800752
|
model-00006-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ad2d329aa4ffe9a938045b04585f636b760b9881a9d5737cf346c97fd102cdb
|
3 |
+
size 5098800752
|
model-00007-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a904e7d7754750d2ce4c1c02b58393274e5abfef6f4fd78ecf12a0bf1ee3287b
|
3 |
+
size 5098800736
|
model-00008-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0f2ad71c3fe292059548cb4b06eeae00e5da32c901f75729bae5205effddad1
|
3 |
+
size 5098800752
|
model-00009-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3fa06e181ea333f9efd1fa4e9c46cfdeadff73fb9ff23a442f321fafeccf3e1
|
3 |
+
size 5098800752
|
model-00010-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76cd5cb6c449ee7ae6cc3bc06668eca33e4a738889c26cbb9ecce8d076eb2409
|
3 |
+
size 5098800736
|
model-00011-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e12b9e0dab1a12ee5487ae4175c7cc65d2e66a0411155c58dc39cf2111c4ddc0
|
3 |
+
size 5098800752
|
model-00012-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba470a100f925048087a2ef652662ff7daeff2dc5d239ef9824c64ed5555e094
|
3 |
+
size 5098800736
|
model-00013-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca237a760f2f70bab599e669b01666b15f4f112f2901b76b61bd3a397fea9864
|
3 |
+
size 5098800752
|
model-00014-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:043ce0c9fe920a3c0406cb19d5b9e66b563e0687bb06d27ae9e595234758ed01
|
3 |
+
size 5098800752
|
model-00015-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e673e2201f0a514bb5e2edeca2dc8d5fbd02d88c91a0d88e36bcdd30246c9d14
|
3 |
+
size 5098800736
|
model-00016-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ede027ac52c84442efd6ec1e7280e8c52843511a8d07aa73c263c1e9a12eb78b
|
3 |
+
size 3824100512
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata":{"total_size":80404288512},"weight_map":{"lm_head.weight":"model-00001-of-00016.safetensors","model.embed_tokens.weight":"model-00001-of-00016.safetensors","model.layers.0.input_layernorm.weight":"model-00001-of-00016.safetensors","model.layers.0.mlp.down_proj.weight":"model-00001-of-00016.safetensors","model.layers.0.mlp.gate_proj.weight":"model-00001-of-00016.safetensors","model.layers.0.mlp.up_proj.weight":"model-00001-of-00016.safetensors","model.layers.0.post_attention_layernorm.weight":"model-00001-of-00016.safetensors","model.layers.0.self_attn.kv_a_layernorm.weight":"model-00001-of-00016.safetensors","model.layers.0.self_attn.kv_a_proj_with_mqa.weight":"model-00001-of-00016.safetensors","model.layers.0.self_attn.kv_b_proj.weight":"model-00001-of-00016.safetensors","model.layers.0.self_attn.o_proj.weight":"model-00001-of-00016.safetensors","model.layers.0.self_attn.q_a_layernorm.weight":"model-00001-of-00016.safetensors","model.layers.0.self_attn.q_a_proj.weight":"model-00001-of-00016.safetensors","model.layers.0.self_attn.q_b_proj.weight":"model-00001-of-00016.safetensors","model.layers.1.input_layernorm.weight":"model-00001-of-00016.safetensors","model.layers.1.mlp.down_proj.weight":"model-00001-of-00016.safetensors","model.layers.1.mlp.gate_proj.weight":"model-00001-of-00016.safetensors","model.layers.1.mlp.up_proj.weight":"model-00001-of-00016.safetensors","model.layers.1.post_attention_layernorm.weight":"model-00001-of-00016.safetensors","model.layers.1.self_attn.kv_a_layernorm.weight":"model-00001-of-00016.safetensors","model.layers.1.self_attn.kv_a_proj_with_mqa.weight":"model-00001-of-00016.safetensors","model.layers.1.self_attn.kv_b_proj.weight":"model-00001-of-00016.safetensors","model.layers.1.self_attn.o_proj.weight":"model-00001-of-00016.safetensors","model.layers.1.self_attn.q_a_layernorm.weight":"model-00001-of-00016.safetensors","model.layers.1.self_attn.q_a_proj.weight":"model-00001-of-00016.safetensors","model.layers.1.self_attn.q_b_proj.weight":"model-00001-of-00016.safetensors","model.layers.10.input_layernorm.weight":"model-00001-of-00016.safetensors","model.layers.10.mlp.down_proj.weight":"model-00002-of-00016.safetensors","model.layers.10.mlp.gate_proj.weight":"model-00002-of-00016.safetensors","model.layers.10.mlp.up_proj.weight":"model-00002-of-00016.safetensors","model.layers.10.post_attention_layernorm.weight":"model-00002-of-00016.safetensors","model.layers.10.self_attn.kv_a_layernorm.weight":"model-00002-of-00016.safetensors","model.layers.10.self_attn.kv_a_proj_with_mqa.weight":"model-00002-of-00016.safetensors","model.layers.10.self_attn.kv_b_proj.weight":"model-00002-of-00016.safetensors","model.layers.10.self_attn.o_proj.weight":"model-00002-of-00016.safetensors","model.layers.10.self_attn.q_a_layernorm.weight":"model-00002-of-00016.safetensors","model.layers.10.self_attn.q_a_proj.weight":"model-00002-of-00016.safetensors","model.layers.10.self_attn.q_b_proj.weight":"model-00002-of-00016.safetensors","model.layers.11.input_layernorm.weight":"model-00002-of-00016.safetensors","model.layers.11.mlp.down_proj.weight":"model-00002-of-00016.safetensors","model.layers.11.mlp.gate_proj.weight":"model-00002-of-00016.safetensors","model.layers.11.mlp.up_proj.weight":"model-00002-of-00016.safetensors","model.layers.11.post_attention_layernorm.weight":"model-00002-of-00016.safetensors","model.layers.11.self_attn.kv_a_layernorm.weight":"model-00002-of-00016.safetensors","model.layers.11.self_attn.kv_a_proj_with_mqa.weight":"model-00002-of-00016.safetensors","model.layers.11.self_attn.kv_b_proj.weight":"model-00002-of-00016.safetensors","model.layers.11.self_attn.o_proj.weight":"model-00002-of-00016.safetensors","model.layers.11.self_attn.q_a_layernorm.weight":"model-00002-of-00016.safetensors","model.layers.11.self_attn.q_a_proj.weight":"model-00002-of-00016.safetensors","model.layers.11.self_attn.q_b_proj.weight":"model-00002-of-00016.safetensors","model.layers.12.input_layernorm.weight":"model-00002-of-00016.safetensors","model.layers.12.mlp.down_proj.weight":"model-00002-of-00016.safetensors","model.layers.12.mlp.gate_proj.weight":"model-00002-of-00016.safetensors","model.layers.12.mlp.up_proj.weight":"model-00002-of-00016.safetensors","model.layers.12.post_attention_layernorm.weight":"model-00002-of-00016.safetensors","model.layers.12.self_attn.kv_a_layernorm.weight":"model-00002-of-00016.safetensors","model.layers.12.self_attn.kv_a_proj_with_mqa.weight":"model-00002-of-00016.safetensors","model.layers.12.self_attn.kv_b_proj.weight":"model-00002-of-00016.safetensors","model.layers.12.self_attn.o_proj.weight":"model-00002-of-00016.safetensors","model.layers.12.self_attn.q_a_layernorm.weight":"model-00002-of-00016.safetensors","model.layers.12.self_attn.q_a_proj.weight":"model-00002-of-00016.safetensors","model.layers.12.self_attn.q_b_proj.weight":"model-00002-of-00016.safetensors","model.layers.13.input_layernorm.weight":"model-00002-of-00016.safetensors","model.layers.13.mlp.down_proj.weight":"model-00002-of-00016.safetensors","model.layers.13.mlp.gate_proj.weight":"model-00002-of-00016.safetensors","model.layers.13.mlp.up_proj.weight":"model-00002-of-00016.safetensors","model.layers.13.post_attention_layernorm.weight":"model-00002-of-00016.safetensors","model.layers.13.self_attn.kv_a_layernorm.weight":"model-00002-of-00016.safetensors","model.layers.13.self_attn.kv_a_proj_with_mqa.weight":"model-00002-of-00016.safetensors","model.layers.13.self_attn.kv_b_proj.weight":"model-00002-of-00016.safetensors","model.layers.13.self_attn.o_proj.weight":"model-00002-of-00016.safetensors","model.layers.13.self_attn.q_a_layernorm.weight":"model-00002-of-00016.safetensors","model.layers.13.self_attn.q_a_proj.weight":"model-00002-of-00016.safetensors","model.layers.13.self_attn.q_b_proj.weight":"model-00002-of-00016.safetensors","model.layers.14.input_layernorm.weight":"model-00002-of-00016.safetensors","model.layers.14.mlp.down_proj.weight":"model-00003-of-00016.safetensors","model.layers.14.mlp.gate_proj.weight":"model-00003-of-00016.safetensors","model.layers.14.mlp.up_proj.weight":"model-00003-of-00016.safetensors","model.layers.14.post_attention_layernorm.weight":"model-00003-of-00016.safetensors","model.layers.14.self_attn.kv_a_layernorm.weight":"model-00003-of-00016.safetensors","model.layers.14.self_attn.kv_a_proj_with_mqa.weight":"model-00003-of-00016.safetensors","model.layers.14.self_attn.kv_b_proj.weight":"model-00003-of-00016.safetensors","model.layers.14.self_attn.o_proj.weight":"model-00003-of-00016.safetensors","model.layers.14.self_attn.q_a_layernorm.weight":"model-00003-of-00016.safetensors","model.layers.14.self_attn.q_a_proj.weight":"model-00003-of-00016.safetensors","model.layers.14.self_attn.q_b_proj.weight":"model-00003-of-00016.safetensors","model.layers.15.input_layernorm.weight":"model-00003-of-00016.safetensors","model.layers.15.mlp.down_proj.weight":"model-00003-of-00016.safetensors","model.layers.15.mlp.gate_proj.weight":"model-00003-of-00016.safetensors","model.layers.15.mlp.up_proj.weight":"model-00003-of-00016.safetensors","model.layers.15.post_attention_layernorm.weight":"model-00003-of-00016.safetensors","model.layers.15.self_attn.kv_a_layernorm.weight":"model-00003-of-00016.safetensors","model.layers.15.self_attn.kv_a_proj_with_mqa.weight":"model-00003-of-00016.safetensors","model.layers.15.self_attn.kv_b_proj.weight":"model-00003-of-00016.safetensors","model.layers.15.self_attn.o_proj.weight":"model-00003-of-00016.safetensors","model.layers.15.self_attn.q_a_layernorm.weight":"model-00003-of-00016.safetensors","model.layers.15.self_attn.q_a_proj.weight":"model-00003-of-00016.safetensors","model.layers.15.self_attn.q_b_proj.weight":"model-00003-of-00016.safetensors","model.layers.16.input_layernorm.weight":"model-00003-of-00016.safetensors","model.layers.16.mlp.down_proj.weight":"model-00003-of-00016.safetensors","model.layers.16.mlp.gate_proj.weight":"model-00003-of-00016.safetensors","model.layers.16.mlp.up_proj.weight":"model-00003-of-00016.safetensors","model.layers.16.post_attention_layernorm.weight":"model-00003-of-00016.safetensors","model.layers.16.self_attn.kv_a_layernorm.weight":"model-00003-of-00016.safetensors","model.layers.16.self_attn.kv_a_proj_with_mqa.weight":"model-00003-of-00016.safetensors","model.layers.16.self_attn.kv_b_proj.weight":"model-00003-of-00016.safetensors","model.layers.16.self_attn.o_proj.weight":"model-00003-of-00016.safetensors","model.layers.16.self_attn.q_a_layernorm.weight":"model-00003-of-00016.safetensors","model.layers.16.self_attn.q_a_proj.weight":"model-00003-of-00016.safetensors","model.layers.16.self_attn.q_b_proj.weight":"model-00003-of-00016.safetensors","model.layers.17.input_layernorm.weight":"model-00003-of-00016.safetensors","model.layers.17.mlp.down_proj.weight":"model-00003-of-00016.safetensors","model.layers.17.mlp.gate_proj.weight":"model-00003-of-00016.safetensors","model.layers.17.mlp.up_proj.weight":"model-00003-of-00016.safetensors","model.layers.17.post_attention_layernorm.weight":"model-00003-of-00016.safetensors","model.layers.17.self_attn.kv_a_layernorm.weight":"model-00003-of-00016.safetensors","model.layers.17.self_attn.kv_a_proj_with_mqa.weight":"model-00003-of-00016.safetensors","model.layers.17.self_attn.kv_b_proj.weight":"model-00003-of-00016.safetensors","model.layers.17.self_attn.o_proj.weight":"model-00003-of-00016.safetensors","model.layers.17.self_attn.q_a_layernorm.weight":"model-00003-of-00016.safetensors","model.layers.17.self_attn.q_a_proj.weight":"model-00003-of-00016.safetensors","model.layers.17.self_attn.q_b_proj.weight":"model-00003-of-00016.safetensors","model.layers.18.input_layernorm.weight":"model-00003-of-00016.safetensors","model.layers.18.mlp.down_proj.weight":"model-00004-of-00016.safetensors","model.layers.18.mlp.gate_proj.weight":"model-00004-of-00016.safetensors","model.layers.18.mlp.up_proj.weight":"model-00004-of-00016.safetensors","model.layers.18.post_attention_layernorm.weight":"model-00004-of-00016.safetensors","model.layers.18.self_attn.kv_a_layernorm.weight":"model-00004-of-00016.safetensors","model.layers.18.self_attn.kv_a_proj_with_mqa.weight":"model-00004-of-00016.safetensors","model.layers.18.self_attn.kv_b_proj.weight":"model-00004-of-00016.safetensors","model.layers.18.self_attn.o_proj.weight":"model-00004-of-00016.safetensors","model.layers.18.self_attn.q_a_layernorm.weight":"model-00004-of-00016.safetensors","model.layers.18.self_attn.q_a_proj.weight":"model-00004-of-00016.safetensors","model.layers.18.self_attn.q_b_proj.weight":"model-00004-of-00016.safetensors","model.layers.19.input_layernorm.weight":"model-00004-of-00016.safetensors","model.layers.19.mlp.down_proj.weight":"model-00004-of-00016.safetensors","model.layers.19.mlp.gate_proj.weight":"model-00004-of-00016.safetensors","model.layers.19.mlp.up_proj.weight":"model-00004-of-00016.safetensors","model.layers.19.post_attention_layernorm.weight":"model-00004-of-00016.safetensors","model.layers.19.self_attn.kv_a_layernorm.weight":"model-00004-of-00016.safetensors","model.layers.19.self_attn.kv_a_proj_with_mqa.weight":"model-00004-of-00016.safetensors","model.layers.19.self_attn.kv_b_proj.weight":"model-00004-of-00016.safetensors","model.layers.19.self_attn.o_proj.weight":"model-00004-of-00016.safetensors","model.layers.19.self_attn.q_a_layernorm.weight":"model-00004-of-00016.safetensors","model.layers.19.self_attn.q_a_proj.weight":"model-00004-of-00016.safetensors","model.layers.19.self_attn.q_b_proj.weight":"model-00004-of-00016.safetensors","model.layers.2.input_layernorm.weight":"model-00004-of-00016.safetensors","model.layers.2.mlp.down_proj.weight":"model-00004-of-00016.safetensors","model.layers.2.mlp.gate_proj.weight":"model-00004-of-00016.safetensors","model.layers.2.mlp.up_proj.weight":"model-00004-of-00016.safetensors","model.layers.2.post_attention_layernorm.weight":"model-00004-of-00016.safetensors","model.layers.2.self_attn.kv_a_layernorm.weight":"model-00004-of-00016.safetensors","model.layers.2.self_attn.kv_a_proj_with_mqa.weight":"model-00004-of-00016.safetensors","model.layers.2.self_attn.kv_b_proj.weight":"model-00004-of-00016.safetensors","model.layers.2.self_attn.o_proj.weight":"model-00004-of-00016.safetensors","model.layers.2.self_attn.q_a_layernorm.weight":"model-00004-of-00016.safetensors","model.layers.2.self_attn.q_a_proj.weight":"model-00004-of-00016.safetensors","model.layers.2.self_attn.q_b_proj.weight":"model-00004-of-00016.safetensors","model.layers.20.input_layernorm.weight":"model-00004-of-00016.safetensors","model.layers.20.mlp.down_proj.weight":"model-00004-of-00016.safetensors","model.layers.20.mlp.gate_proj.weight":"model-00004-of-00016.safetensors","model.layers.20.mlp.up_proj.weight":"model-00004-of-00016.safetensors","model.layers.20.post_attention_layernorm.weight":"model-00004-of-00016.safetensors","model.layers.20.self_attn.kv_a_layernorm.weight":"model-00004-of-00016.safetensors","model.layers.20.self_attn.kv_a_proj_with_mqa.weight":"model-00004-of-00016.safetensors","model.layers.20.self_attn.kv_b_proj.weight":"model-00004-of-00016.safetensors","model.layers.20.self_attn.o_proj.weight":"model-00004-of-00016.safetensors","model.layers.20.self_attn.q_a_layernorm.weight":"model-00004-of-00016.safetensors","model.layers.20.self_attn.q_a_proj.weight":"model-00004-of-00016.safetensors","model.layers.20.self_attn.q_b_proj.weight":"model-00004-of-00016.safetensors","model.layers.21.input_layernorm.weight":"model-00004-of-00016.safetensors","model.layers.21.mlp.down_proj.weight":"model-00005-of-00016.safetensors","model.layers.21.mlp.gate_proj.weight":"model-00005-of-00016.safetensors","model.layers.21.mlp.up_proj.weight":"model-00005-of-00016.safetensors","model.layers.21.post_attention_layernorm.weight":"model-00005-of-00016.safetensors","model.layers.21.self_attn.kv_a_layernorm.weight":"model-00005-of-00016.safetensors","model.layers.21.self_attn.kv_a_proj_with_mqa.weight":"model-00005-of-00016.safetensors","model.layers.21.self_attn.kv_b_proj.weight":"model-00005-of-00016.safetensors","model.layers.21.self_attn.o_proj.weight":"model-00005-of-00016.safetensors","model.layers.21.self_attn.q_a_layernorm.weight":"model-00005-of-00016.safetensors","model.layers.21.self_attn.q_a_proj.weight":"model-00005-of-00016.safetensors","model.layers.21.self_attn.q_b_proj.weight":"model-00005-of-00016.safetensors","model.layers.22.input_layernorm.weight":"model-00005-of-00016.safetensors","model.layers.22.mlp.down_proj.weight":"model-00005-of-00016.safetensors","model.layers.22.mlp.gate_proj.weight":"model-00005-of-00016.safetensors","model.layers.22.mlp.up_proj.weight":"model-00005-of-00016.safetensors","model.layers.22.post_attention_layernorm.weight":"model-00005-of-00016.safetensors","model.layers.22.self_attn.kv_a_layernorm.weight":"model-00005-of-00016.safetensors","model.layers.22.self_attn.kv_a_proj_with_mqa.weight":"model-00005-of-00016.safetensors","model.layers.22.self_attn.kv_b_proj.weight":"model-00005-of-00016.safetensors","model.layers.22.self_attn.o_proj.weight":"model-00005-of-00016.safetensors","model.layers.22.self_attn.q_a_layernorm.weight":"model-00005-of-00016.safetensors","model.layers.22.self_attn.q_a_proj.weight":"model-00005-of-00016.safetensors","model.layers.22.self_attn.q_b_proj.weight":"model-00005-of-00016.safetensors","model.layers.23.input_layernorm.weight":"model-00005-of-00016.safetensors","model.layers.23.mlp.down_proj.weight":"model-00005-of-00016.safetensors","model.layers.23.mlp.gate_proj.weight":"model-00005-of-00016.safetensors","model.layers.23.mlp.up_proj.weight":"model-00005-of-00016.safetensors","model.layers.23.post_attention_layernorm.weight":"model-00005-of-00016.safetensors","model.layers.23.self_attn.kv_a_layernorm.weight":"model-00005-of-00016.safetensors","model.layers.23.self_attn.kv_a_proj_with_mqa.weight":"model-00005-of-00016.safetensors","model.layers.23.self_attn.kv_b_proj.weight":"model-00005-of-00016.safetensors","model.layers.23.self_attn.o_proj.weight":"model-00005-of-00016.safetensors","model.layers.23.self_attn.q_a_layernorm.weight":"model-00005-of-00016.safetensors","model.layers.23.self_attn.q_a_proj.weight":"model-00005-of-00016.safetensors","model.layers.23.self_attn.q_b_proj.weight":"model-00005-of-00016.safetensors","model.layers.24.input_layernorm.weight":"model-00005-of-00016.safetensors","model.layers.24.mlp.down_proj.weight":"model-00005-of-00016.safetensors","model.layers.24.mlp.gate_proj.weight":"model-00005-of-00016.safetensors","model.layers.24.mlp.up_proj.weight":"model-00005-of-00016.safetensors","model.layers.24.post_attention_layernorm.weight":"model-00005-of-00016.safetensors","model.layers.24.self_attn.kv_a_layernorm.weight":"model-00005-of-00016.safetensors","model.layers.24.self_attn.kv_a_proj_with_mqa.weight":"model-00005-of-00016.safetensors","model.layers.24.self_attn.kv_b_proj.weight":"model-00005-of-00016.safetensors","model.layers.24.self_attn.o_proj.weight":"model-00005-of-00016.safetensors","model.layers.24.self_attn.q_a_layernorm.weight":"model-00005-of-00016.safetensors","model.layers.24.self_attn.q_a_proj.weight":"model-00005-of-00016.safetensors","model.layers.24.self_attn.q_b_proj.weight":"model-00005-of-00016.safetensors","model.layers.25.input_layernorm.weight":"model-00005-of-00016.safetensors","model.layers.25.mlp.down_proj.weight":"model-00006-of-00016.safetensors","model.layers.25.mlp.gate_proj.weight":"model-00006-of-00016.safetensors","model.layers.25.mlp.up_proj.weight":"model-00006-of-00016.safetensors","model.layers.25.post_attention_layernorm.weight":"model-00006-of-00016.safetensors","model.layers.25.self_attn.kv_a_layernorm.weight":"model-00006-of-00016.safetensors","model.layers.25.self_attn.kv_a_proj_with_mqa.weight":"model-00006-of-00016.safetensors","model.layers.25.self_attn.kv_b_proj.weight":"model-00006-of-00016.safetensors","model.layers.25.self_attn.o_proj.weight":"model-00006-of-00016.safetensors","model.layers.25.self_attn.q_a_layernorm.weight":"model-00006-of-00016.safetensors","model.layers.25.self_attn.q_a_proj.weight":"model-00006-of-00016.safetensors","model.layers.25.self_attn.q_b_proj.weight":"model-00006-of-00016.safetensors","model.layers.26.input_layernorm.weight":"model-00006-of-00016.safetensors","model.layers.26.mlp.down_proj.weight":"model-00006-of-00016.safetensors","model.layers.26.mlp.gate_proj.weight":"model-00006-of-00016.safetensors","model.layers.26.mlp.up_proj.weight":"model-00006-of-00016.safetensors","model.layers.26.post_attention_layernorm.weight":"model-00006-of-00016.safetensors","model.layers.26.self_attn.kv_a_layernorm.weight":"model-00006-of-00016.safetensors","model.layers.26.self_attn.kv_a_proj_with_mqa.weight":"model-00006-of-00016.safetensors","model.layers.26.self_attn.kv_b_proj.weight":"model-00006-of-00016.safetensors","model.layers.26.self_attn.o_proj.weight":"model-00006-of-00016.safetensors","model.layers.26.self_attn.q_a_layernorm.weight":"model-00006-of-00016.safetensors","model.layers.26.self_attn.q_a_proj.weight":"model-00006-of-00016.safetensors","model.layers.26.self_attn.q_b_proj.weight":"model-00006-of-00016.safetensors","model.layers.27.input_layernorm.weight":"model-00006-of-00016.safetensors","model.layers.27.mlp.down_proj.weight":"model-00006-of-00016.safetensors","model.layers.27.mlp.gate_proj.weight":"model-00006-of-00016.safetensors","model.layers.27.mlp.up_proj.weight":"model-00006-of-00016.safetensors","model.layers.27.post_attention_layernorm.weight":"model-00006-of-00016.safetensors","model.layers.27.self_attn.kv_a_layernorm.weight":"model-00006-of-00016.safetensors","model.layers.27.self_attn.kv_a_proj_with_mqa.weight":"model-00006-of-00016.safetensors","model.layers.27.self_attn.kv_b_proj.weight":"model-00006-of-00016.safetensors","model.layers.27.self_attn.o_proj.weight":"model-00006-of-00016.safetensors","model.layers.27.self_attn.q_a_layernorm.weight":"model-00006-of-00016.safetensors","model.layers.27.self_attn.q_a_proj.weight":"model-00006-of-00016.safetensors","model.layers.27.self_attn.q_b_proj.weight":"model-00006-of-00016.safetensors","model.layers.28.input_layernorm.weight":"model-00006-of-00016.safetensors","model.layers.28.mlp.down_proj.weight":"model-00006-of-00016.safetensors","model.layers.28.mlp.gate_proj.weight":"model-00006-of-00016.safetensors","model.layers.28.mlp.up_proj.weight":"model-00006-of-00016.safetensors","model.layers.28.post_attention_layernorm.weight":"model-00006-of-00016.safetensors","model.layers.28.self_attn.kv_a_layernorm.weight":"model-00006-of-00016.safetensors","model.layers.28.self_attn.kv_a_proj_with_mqa.weight":"model-00006-of-00016.safetensors","model.layers.28.self_attn.kv_b_proj.weight":"model-00006-of-00016.safetensors","model.layers.28.self_attn.o_proj.weight":"model-00006-of-00016.safetensors","model.layers.28.self_attn.q_a_layernorm.weight":"model-00006-of-00016.safetensors","model.layers.28.self_attn.q_a_proj.weight":"model-00006-of-00016.safetensors","model.layers.28.self_attn.q_b_proj.weight":"model-00006-of-00016.safetensors","model.layers.29.input_layernorm.weight":"model-00006-of-00016.safetensors","model.layers.29.mlp.down_proj.weight":"model-00007-of-00016.safetensors","model.layers.29.mlp.gate_proj.weight":"model-00007-of-00016.safetensors","model.layers.29.mlp.up_proj.weight":"model-00007-of-00016.safetensors","model.layers.29.post_attention_layernorm.weight":"model-00007-of-00016.safetensors","model.layers.29.self_attn.kv_a_layernorm.weight":"model-00007-of-00016.safetensors","model.layers.29.self_attn.kv_a_proj_with_mqa.weight":"model-00007-of-00016.safetensors","model.layers.29.self_attn.kv_b_proj.weight":"model-00007-of-00016.safetensors","model.layers.29.self_attn.o_proj.weight":"model-00007-of-00016.safetensors","model.layers.29.self_attn.q_a_layernorm.weight":"model-00007-of-00016.safetensors","model.layers.29.self_attn.q_a_proj.weight":"model-00007-of-00016.safetensors","model.layers.29.self_attn.q_b_proj.weight":"model-00007-of-00016.safetensors","model.layers.3.input_layernorm.weight":"model-00007-of-00016.safetensors","model.layers.3.mlp.down_proj.weight":"model-00007-of-00016.safetensors","model.layers.3.mlp.gate_proj.weight":"model-00007-of-00016.safetensors","model.layers.3.mlp.up_proj.weight":"model-00007-of-00016.safetensors","model.layers.3.post_attention_layernorm.weight":"model-00007-of-00016.safetensors","model.layers.3.self_attn.kv_a_layernorm.weight":"model-00007-of-00016.safetensors","model.layers.3.self_attn.kv_a_proj_with_mqa.weight":"model-00007-of-00016.safetensors","model.layers.3.self_attn.kv_b_proj.weight":"model-00007-of-00016.safetensors","model.layers.3.self_attn.o_proj.weight":"model-00007-of-00016.safetensors","model.layers.3.self_attn.q_a_layernorm.weight":"model-00007-of-00016.safetensors","model.layers.3.self_attn.q_a_proj.weight":"model-00007-of-00016.safetensors","model.layers.3.self_attn.q_b_proj.weight":"model-00007-of-00016.safetensors","model.layers.30.input_layernorm.weight":"model-00007-of-00016.safetensors","model.layers.30.mlp.down_proj.weight":"model-00007-of-00016.safetensors","model.layers.30.mlp.gate_proj.weight":"model-00007-of-00016.safetensors","model.layers.30.mlp.up_proj.weight":"model-00007-of-00016.safetensors","model.layers.30.post_attention_layernorm.weight":"model-00007-of-00016.safetensors","model.layers.30.self_attn.kv_a_layernorm.weight":"model-00007-of-00016.safetensors","model.layers.30.self_attn.kv_a_proj_with_mqa.weight":"model-00007-of-00016.safetensors","model.layers.30.self_attn.kv_b_proj.weight":"model-00007-of-00016.safetensors","model.layers.30.self_attn.o_proj.weight":"model-00007-of-00016.safetensors","model.layers.30.self_attn.q_a_layernorm.weight":"model-00007-of-00016.safetensors","model.layers.30.self_attn.q_a_proj.weight":"model-00007-of-00016.safetensors","model.layers.30.self_attn.q_b_proj.weight":"model-00007-of-00016.safetensors","model.layers.31.input_layernorm.weight":"model-00007-of-00016.safetensors","model.layers.31.mlp.down_proj.weight":"model-00007-of-00016.safetensors","model.layers.31.mlp.gate_proj.weight":"model-00007-of-00016.safetensors","model.layers.31.mlp.up_proj.weight":"model-00007-of-00016.safetensors","model.layers.31.post_attention_layernorm.weight":"model-00007-of-00016.safetensors","model.layers.31.self_attn.kv_a_layernorm.weight":"model-00007-of-00016.safetensors","model.layers.31.self_attn.kv_a_proj_with_mqa.weight":"model-00007-of-00016.safetensors","model.layers.31.self_attn.kv_b_proj.weight":"model-00007-of-00016.safetensors","model.layers.31.self_attn.o_proj.weight":"model-00007-of-00016.safetensors","model.layers.31.self_attn.q_a_layernorm.weight":"model-00007-of-00016.safetensors","model.layers.31.self_attn.q_a_proj.weight":"model-00007-of-00016.safetensors","model.layers.31.self_attn.q_b_proj.weight":"model-00007-of-00016.safetensors","model.layers.32.input_layernorm.weight":"model-00007-of-00016.safetensors","model.layers.32.mlp.down_proj.weight":"model-00008-of-00016.safetensors","model.layers.32.mlp.gate_proj.weight":"model-00008-of-00016.safetensors","model.layers.32.mlp.up_proj.weight":"model-00008-of-00016.safetensors","model.layers.32.post_attention_layernorm.weight":"model-00008-of-00016.safetensors","model.layers.32.self_attn.kv_a_layernorm.weight":"model-00008-of-00016.safetensors","model.layers.32.self_attn.kv_a_proj_with_mqa.weight":"model-00008-of-00016.safetensors","model.layers.32.self_attn.kv_b_proj.weight":"model-00008-of-00016.safetensors","model.layers.32.self_attn.o_proj.weight":"model-00008-of-00016.safetensors","model.layers.32.self_attn.q_a_layernorm.weight":"model-00008-of-00016.safetensors","model.layers.32.self_attn.q_a_proj.weight":"model-00008-of-00016.safetensors","model.layers.32.self_attn.q_b_proj.weight":"model-00008-of-00016.safetensors","model.layers.33.input_layernorm.weight":"model-00008-of-00016.safetensors","model.layers.33.mlp.down_proj.weight":"model-00008-of-00016.safetensors","model.layers.33.mlp.gate_proj.weight":"model-00008-of-00016.safetensors","model.layers.33.mlp.up_proj.weight":"model-00008-of-00016.safetensors","model.layers.33.post_attention_layernorm.weight":"model-00008-of-00016.safetensors","model.layers.33.self_attn.kv_a_layernorm.weight":"model-00008-of-00016.safetensors","model.layers.33.self_attn.kv_a_proj_with_mqa.weight":"model-00008-of-00016.safetensors","model.layers.33.self_attn.kv_b_proj.weight":"model-00008-of-00016.safetensors","model.layers.33.self_attn.o_proj.weight":"model-00008-of-00016.safetensors","model.layers.33.self_attn.q_a_layernorm.weight":"model-00008-of-00016.safetensors","model.layers.33.self_attn.q_a_proj.weight":"model-00008-of-00016.safetensors","model.layers.33.self_attn.q_b_proj.weight":"model-00008-of-00016.safetensors","model.layers.34.input_layernorm.weight":"model-00008-of-00016.safetensors","model.layers.34.mlp.down_proj.weight":"model-00008-of-00016.safetensors","model.layers.34.mlp.gate_proj.weight":"model-00008-of-00016.safetensors","model.layers.34.mlp.up_proj.weight":"model-00008-of-00016.safetensors","model.layers.34.post_attention_layernorm.weight":"model-00008-of-00016.safetensors","model.layers.34.self_attn.kv_a_layernorm.weight":"model-00008-of-00016.safetensors","model.layers.34.self_attn.kv_a_proj_with_mqa.weight":"model-00008-of-00016.safetensors","model.layers.34.self_attn.kv_b_proj.weight":"model-00008-of-00016.safetensors","model.layers.34.self_attn.o_proj.weight":"model-00008-of-00016.safetensors","model.layers.34.self_attn.q_a_layernorm.weight":"model-00008-of-00016.safetensors","model.layers.34.self_attn.q_a_proj.weight":"model-00008-of-00016.safetensors","model.layers.34.self_attn.q_b_proj.weight":"model-00008-of-00016.safetensors","model.layers.35.input_layernorm.weight":"model-00008-of-00016.safetensors","model.layers.35.mlp.down_proj.weight":"model-00008-of-00016.safetensors","model.layers.35.mlp.gate_proj.weight":"model-00008-of-00016.safetensors","model.layers.35.mlp.up_proj.weight":"model-00008-of-00016.safetensors","model.layers.35.post_attention_layernorm.weight":"model-00008-of-00016.safetensors","model.layers.35.self_attn.kv_a_layernorm.weight":"model-00008-of-00016.safetensors","model.layers.35.self_attn.kv_a_proj_with_mqa.weight":"model-00008-of-00016.safetensors","model.layers.35.self_attn.kv_b_proj.weight":"model-00008-of-00016.safetensors","model.layers.35.self_attn.o_proj.weight":"model-00008-of-00016.safetensors","model.layers.35.self_attn.q_a_layernorm.weight":"model-00008-of-00016.safetensors","model.layers.35.self_attn.q_a_proj.weight":"model-00008-of-00016.safetensors","model.layers.35.self_attn.q_b_proj.weight":"model-00008-of-00016.safetensors","model.layers.36.input_layernorm.weight":"model-00008-of-00016.safetensors","model.layers.36.mlp.down_proj.weight":"model-00009-of-00016.safetensors","model.layers.36.mlp.gate_proj.weight":"model-00009-of-00016.safetensors","model.layers.36.mlp.up_proj.weight":"model-00009-of-00016.safetensors","model.layers.36.post_attention_layernorm.weight":"model-00009-of-00016.safetensors","model.layers.36.self_attn.kv_a_layernorm.weight":"model-00009-of-00016.safetensors","model.layers.36.self_attn.kv_a_proj_with_mqa.weight":"model-00009-of-00016.safetensors","model.layers.36.self_attn.kv_b_proj.weight":"model-00009-of-00016.safetensors","model.layers.36.self_attn.o_proj.weight":"model-00009-of-00016.safetensors","model.layers.36.self_attn.q_a_layernorm.weight":"model-00009-of-00016.safetensors","model.layers.36.self_attn.q_a_proj.weight":"model-00009-of-00016.safetensors","model.layers.36.self_attn.q_b_proj.weight":"model-00009-of-00016.safetensors","model.layers.37.input_layernorm.weight":"model-00009-of-00016.safetensors","model.layers.37.mlp.down_proj.weight":"model-00009-of-00016.safetensors","model.layers.37.mlp.gate_proj.weight":"model-00009-of-00016.safetensors","model.layers.37.mlp.up_proj.weight":"model-00009-of-00016.safetensors","model.layers.37.post_attention_layernorm.weight":"model-00009-of-00016.safetensors","model.layers.37.self_attn.kv_a_layernorm.weight":"model-00009-of-00016.safetensors","model.layers.37.self_attn.kv_a_proj_with_mqa.weight":"model-00009-of-00016.safetensors","model.layers.37.self_attn.kv_b_proj.weight":"model-00009-of-00016.safetensors","model.layers.37.self_attn.o_proj.weight":"model-00009-of-00016.safetensors","model.layers.37.self_attn.q_a_layernorm.weight":"model-00009-of-00016.safetensors","model.layers.37.self_attn.q_a_proj.weight":"model-00009-of-00016.safetensors","model.layers.37.self_attn.q_b_proj.weight":"model-00009-of-00016.safetensors","model.layers.38.input_layernorm.weight":"model-00009-of-00016.safetensors","model.layers.38.mlp.down_proj.weight":"model-00009-of-00016.safetensors","model.layers.38.mlp.gate_proj.weight":"model-00009-of-00016.safetensors","model.layers.38.mlp.up_proj.weight":"model-00009-of-00016.safetensors","model.layers.38.post_attention_layernorm.weight":"model-00009-of-00016.safetensors","model.layers.38.self_attn.kv_a_layernorm.weight":"model-00009-of-00016.safetensors","model.layers.38.self_attn.kv_a_proj_with_mqa.weight":"model-00009-of-00016.safetensors","model.layers.38.self_attn.kv_b_proj.weight":"model-00009-of-00016.safetensors","model.layers.38.self_attn.o_proj.weight":"model-00009-of-00016.safetensors","model.layers.38.self_attn.q_a_layernorm.weight":"model-00009-of-00016.safetensors","model.layers.38.self_attn.q_a_proj.weight":"model-00009-of-00016.safetensors","model.layers.38.self_attn.q_b_proj.weight":"model-00009-of-00016.safetensors","model.layers.39.input_layernorm.weight":"model-00009-of-00016.safetensors","model.layers.39.mlp.down_proj.weight":"model-00009-of-00016.safetensors","model.layers.39.mlp.gate_proj.weight":"model-00009-of-00016.safetensors","model.layers.39.mlp.up_proj.weight":"model-00009-of-00016.safetensors","model.layers.39.post_attention_layernorm.weight":"model-00009-of-00016.safetensors","model.layers.39.self_attn.kv_a_layernorm.weight":"model-00009-of-00016.safetensors","model.layers.39.self_attn.kv_a_proj_with_mqa.weight":"model-00009-of-00016.safetensors","model.layers.39.self_attn.kv_b_proj.weight":"model-00009-of-00016.safetensors","model.layers.39.self_attn.o_proj.weight":"model-00009-of-00016.safetensors","model.layers.39.self_attn.q_a_layernorm.weight":"model-00009-of-00016.safetensors","model.layers.39.self_attn.q_a_proj.weight":"model-00009-of-00016.safetensors","model.layers.39.self_attn.q_b_proj.weight":"model-00009-of-00016.safetensors","model.layers.4.input_layernorm.weight":"model-00009-of-00016.safetensors","model.layers.4.mlp.down_proj.weight":"model-00010-of-00016.safetensors","model.layers.4.mlp.gate_proj.weight":"model-00010-of-00016.safetensors","model.layers.4.mlp.up_proj.weight":"model-00010-of-00016.safetensors","model.layers.4.post_attention_layernorm.weight":"model-00010-of-00016.safetensors","model.layers.4.self_attn.kv_a_layernorm.weight":"model-00010-of-00016.safetensors","model.layers.4.self_attn.kv_a_proj_with_mqa.weight":"model-00010-of-00016.safetensors","model.layers.4.self_attn.kv_b_proj.weight":"model-00010-of-00016.safetensors","model.layers.4.self_attn.o_proj.weight":"model-00010-of-00016.safetensors","model.layers.4.self_attn.q_a_layernorm.weight":"model-00010-of-00016.safetensors","model.layers.4.self_attn.q_a_proj.weight":"model-00010-of-00016.safetensors","model.layers.4.self_attn.q_b_proj.weight":"model-00010-of-00016.safetensors","model.layers.40.input_layernorm.weight":"model-00010-of-00016.safetensors","model.layers.40.mlp.down_proj.weight":"model-00010-of-00016.safetensors","model.layers.40.mlp.gate_proj.weight":"model-00010-of-00016.safetensors","model.layers.40.mlp.up_proj.weight":"model-00010-of-00016.safetensors","model.layers.40.post_attention_layernorm.weight":"model-00010-of-00016.safetensors","model.layers.40.self_attn.kv_a_layernorm.weight":"model-00010-of-00016.safetensors","model.layers.40.self_attn.kv_a_proj_with_mqa.weight":"model-00010-of-00016.safetensors","model.layers.40.self_attn.kv_b_proj.weight":"model-00010-of-00016.safetensors","model.layers.40.self_attn.o_proj.weight":"model-00010-of-00016.safetensors","model.layers.40.self_attn.q_a_layernorm.weight":"model-00010-of-00016.safetensors","model.layers.40.self_attn.q_a_proj.weight":"model-00010-of-00016.safetensors","model.layers.40.self_attn.q_b_proj.weight":"model-00010-of-00016.safetensors","model.layers.41.input_layernorm.weight":"model-00010-of-00016.safetensors","model.layers.41.mlp.down_proj.weight":"model-00010-of-00016.safetensors","model.layers.41.mlp.gate_proj.weight":"model-00010-of-00016.safetensors","model.layers.41.mlp.up_proj.weight":"model-00010-of-00016.safetensors","model.layers.41.post_attention_layernorm.weight":"model-00010-of-00016.safetensors","model.layers.41.self_attn.kv_a_layernorm.weight":"model-00010-of-00016.safetensors","model.layers.41.self_attn.kv_a_proj_with_mqa.weight":"model-00010-of-00016.safetensors","model.layers.41.self_attn.kv_b_proj.weight":"model-00010-of-00016.safetensors","model.layers.41.self_attn.o_proj.weight":"model-00010-of-00016.safetensors","model.layers.41.self_attn.q_a_layernorm.weight":"model-00010-of-00016.safetensors","model.layers.41.self_attn.q_a_proj.weight":"model-00010-of-00016.safetensors","model.layers.41.self_attn.q_b_proj.weight":"model-00010-of-00016.safetensors","model.layers.42.input_layernorm.weight":"model-00010-of-00016.safetensors","model.layers.42.mlp.down_proj.weight":"model-00010-of-00016.safetensors","model.layers.42.mlp.gate_proj.weight":"model-00010-of-00016.safetensors","model.layers.42.mlp.up_proj.weight":"model-00010-of-00016.safetensors","model.layers.42.post_attention_layernorm.weight":"model-00010-of-00016.safetensors","model.layers.42.self_attn.kv_a_layernorm.weight":"model-00010-of-00016.safetensors","model.layers.42.self_attn.kv_a_proj_with_mqa.weight":"model-00010-of-00016.safetensors","model.layers.42.self_attn.kv_b_proj.weight":"model-00010-of-00016.safetensors","model.layers.42.self_attn.o_proj.weight":"model-00010-of-00016.safetensors","model.layers.42.self_attn.q_a_layernorm.weight":"model-00010-of-00016.safetensors","model.layers.42.self_attn.q_a_proj.weight":"model-00010-of-00016.safetensors","model.layers.42.self_attn.q_b_proj.weight":"model-00010-of-00016.safetensors","model.layers.43.input_layernorm.weight":"model-00010-of-00016.safetensors","model.layers.43.mlp.down_proj.weight":"model-00011-of-00016.safetensors","model.layers.43.mlp.gate_proj.weight":"model-00011-of-00016.safetensors","model.layers.43.mlp.up_proj.weight":"model-00011-of-00016.safetensors","model.layers.43.post_attention_layernorm.weight":"model-00011-of-00016.safetensors","model.layers.43.self_attn.kv_a_layernorm.weight":"model-00011-of-00016.safetensors","model.layers.43.self_attn.kv_a_proj_with_mqa.weight":"model-00011-of-00016.safetensors","model.layers.43.self_attn.kv_b_proj.weight":"model-00011-of-00016.safetensors","model.layers.43.self_attn.o_proj.weight":"model-00011-of-00016.safetensors","model.layers.43.self_attn.q_a_layernorm.weight":"model-00011-of-00016.safetensors","model.layers.43.self_attn.q_a_proj.weight":"model-00011-of-00016.safetensors","model.layers.43.self_attn.q_b_proj.weight":"model-00011-of-00016.safetensors","model.layers.44.input_layernorm.weight":"model-00011-of-00016.safetensors","model.layers.44.mlp.down_proj.weight":"model-00011-of-00016.safetensors","model.layers.44.mlp.gate_proj.weight":"model-00011-of-00016.safetensors","model.layers.44.mlp.up_proj.weight":"model-00011-of-00016.safetensors","model.layers.44.post_attention_layernorm.weight":"model-00011-of-00016.safetensors","model.layers.44.self_attn.kv_a_layernorm.weight":"model-00011-of-00016.safetensors","model.layers.44.self_attn.kv_a_proj_with_mqa.weight":"model-00011-of-00016.safetensors","model.layers.44.self_attn.kv_b_proj.weight":"model-00011-of-00016.safetensors","model.layers.44.self_attn.o_proj.weight":"model-00011-of-00016.safetensors","model.layers.44.self_attn.q_a_layernorm.weight":"model-00011-of-00016.safetensors","model.layers.44.self_attn.q_a_proj.weight":"model-00011-of-00016.safetensors","model.layers.44.self_attn.q_b_proj.weight":"model-00011-of-00016.safetensors","model.layers.45.input_layernorm.weight":"model-00011-of-00016.safetensors","model.layers.45.mlp.down_proj.weight":"model-00011-of-00016.safetensors","model.layers.45.mlp.gate_proj.weight":"model-00011-of-00016.safetensors","model.layers.45.mlp.up_proj.weight":"model-00011-of-00016.safetensors","model.layers.45.post_attention_layernorm.weight":"model-00011-of-00016.safetensors","model.layers.45.self_attn.kv_a_layernorm.weight":"model-00011-of-00016.safetensors","model.layers.45.self_attn.kv_a_proj_with_mqa.weight":"model-00011-of-00016.safetensors","model.layers.45.self_attn.kv_b_proj.weight":"model-00011-of-00016.safetensors","model.layers.45.self_attn.o_proj.weight":"model-00011-of-00016.safetensors","model.layers.45.self_attn.q_a_layernorm.weight":"model-00011-of-00016.safetensors","model.layers.45.self_attn.q_a_proj.weight":"model-00011-of-00016.safetensors","model.layers.45.self_attn.q_b_proj.weight":"model-00011-of-00016.safetensors","model.layers.46.input_layernorm.weight":"model-00011-of-00016.safetensors","model.layers.46.mlp.down_proj.weight":"model-00011-of-00016.safetensors","model.layers.46.mlp.gate_proj.weight":"model-00011-of-00016.safetensors","model.layers.46.mlp.up_proj.weight":"model-00011-of-00016.safetensors","model.layers.46.post_attention_layernorm.weight":"model-00011-of-00016.safetensors","model.layers.46.self_attn.kv_a_layernorm.weight":"model-00011-of-00016.safetensors","model.layers.46.self_attn.kv_a_proj_with_mqa.weight":"model-00011-of-00016.safetensors","model.layers.46.self_attn.kv_b_proj.weight":"model-00011-of-00016.safetensors","model.layers.46.self_attn.o_proj.weight":"model-00011-of-00016.safetensors","model.layers.46.self_attn.q_a_layernorm.weight":"model-00011-of-00016.safetensors","model.layers.46.self_attn.q_a_proj.weight":"model-00011-of-00016.safetensors","model.layers.46.self_attn.q_b_proj.weight":"model-00011-of-00016.safetensors","model.layers.47.input_layernorm.weight":"model-00011-of-00016.safetensors","model.layers.47.mlp.down_proj.weight":"model-00012-of-00016.safetensors","model.layers.47.mlp.gate_proj.weight":"model-00012-of-00016.safetensors","model.layers.47.mlp.up_proj.weight":"model-00012-of-00016.safetensors","model.layers.47.post_attention_layernorm.weight":"model-00012-of-00016.safetensors","model.layers.47.self_attn.kv_a_layernorm.weight":"model-00012-of-00016.safetensors","model.layers.47.self_attn.kv_a_proj_with_mqa.weight":"model-00012-of-00016.safetensors","model.layers.47.self_attn.kv_b_proj.weight":"model-00012-of-00016.safetensors","model.layers.47.self_attn.o_proj.weight":"model-00012-of-00016.safetensors","model.layers.47.self_attn.q_a_layernorm.weight":"model-00012-of-00016.safetensors","model.layers.47.self_attn.q_a_proj.weight":"model-00012-of-00016.safetensors","model.layers.47.self_attn.q_b_proj.weight":"model-00012-of-00016.safetensors","model.layers.48.input_layernorm.weight":"model-00012-of-00016.safetensors","model.layers.48.mlp.down_proj.weight":"model-00012-of-00016.safetensors","model.layers.48.mlp.gate_proj.weight":"model-00012-of-00016.safetensors","model.layers.48.mlp.up_proj.weight":"model-00012-of-00016.safetensors","model.layers.48.post_attention_layernorm.weight":"model-00012-of-00016.safetensors","model.layers.48.self_attn.kv_a_layernorm.weight":"model-00012-of-00016.safetensors","model.layers.48.self_attn.kv_a_proj_with_mqa.weight":"model-00012-of-00016.safetensors","model.layers.48.self_attn.kv_b_proj.weight":"model-00012-of-00016.safetensors","model.layers.48.self_attn.o_proj.weight":"model-00012-of-00016.safetensors","model.layers.48.self_attn.q_a_layernorm.weight":"model-00012-of-00016.safetensors","model.layers.48.self_attn.q_a_proj.weight":"model-00012-of-00016.safetensors","model.layers.48.self_attn.q_b_proj.weight":"model-00012-of-00016.safetensors","model.layers.49.input_layernorm.weight":"model-00012-of-00016.safetensors","model.layers.49.mlp.down_proj.weight":"model-00012-of-00016.safetensors","model.layers.49.mlp.gate_proj.weight":"model-00012-of-00016.safetensors","model.layers.49.mlp.up_proj.weight":"model-00012-of-00016.safetensors","model.layers.49.post_attention_layernorm.weight":"model-00012-of-00016.safetensors","model.layers.49.self_attn.kv_a_layernorm.weight":"model-00012-of-00016.safetensors","model.layers.49.self_attn.kv_a_proj_with_mqa.weight":"model-00012-of-00016.safetensors","model.layers.49.self_attn.kv_b_proj.weight":"model-00012-of-00016.safetensors","model.layers.49.self_attn.o_proj.weight":"model-00012-of-00016.safetensors","model.layers.49.self_attn.q_a_layernorm.weight":"model-00012-of-00016.safetensors","model.layers.49.self_attn.q_a_proj.weight":"model-00012-of-00016.safetensors","model.layers.49.self_attn.q_b_proj.weight":"model-00012-of-00016.safetensors","model.layers.5.input_layernorm.weight":"model-00012-of-00016.safetensors","model.layers.5.mlp.down_proj.weight":"model-00012-of-00016.safetensors","model.layers.5.mlp.gate_proj.weight":"model-00012-of-00016.safetensors","model.layers.5.mlp.up_proj.weight":"model-00012-of-00016.safetensors","model.layers.5.post_attention_layernorm.weight":"model-00012-of-00016.safetensors","model.layers.5.self_attn.kv_a_layernorm.weight":"model-00012-of-00016.safetensors","model.layers.5.self_attn.kv_a_proj_with_mqa.weight":"model-00012-of-00016.safetensors","model.layers.5.self_attn.kv_b_proj.weight":"model-00012-of-00016.safetensors","model.layers.5.self_attn.o_proj.weight":"model-00012-of-00016.safetensors","model.layers.5.self_attn.q_a_layernorm.weight":"model-00012-of-00016.safetensors","model.layers.5.self_attn.q_a_proj.weight":"model-00012-of-00016.safetensors","model.layers.5.self_attn.q_b_proj.weight":"model-00012-of-00016.safetensors","model.layers.50.input_layernorm.weight":"model-00012-of-00016.safetensors","model.layers.50.mlp.down_proj.weight":"model-00013-of-00016.safetensors","model.layers.50.mlp.gate_proj.weight":"model-00013-of-00016.safetensors","model.layers.50.mlp.up_proj.weight":"model-00013-of-00016.safetensors","model.layers.50.post_attention_layernorm.weight":"model-00013-of-00016.safetensors","model.layers.50.self_attn.kv_a_layernorm.weight":"model-00013-of-00016.safetensors","model.layers.50.self_attn.kv_a_proj_with_mqa.weight":"model-00013-of-00016.safetensors","model.layers.50.self_attn.kv_b_proj.weight":"model-00013-of-00016.safetensors","model.layers.50.self_attn.o_proj.weight":"model-00013-of-00016.safetensors","model.layers.50.self_attn.q_a_layernorm.weight":"model-00013-of-00016.safetensors","model.layers.50.self_attn.q_a_proj.weight":"model-00013-of-00016.safetensors","model.layers.50.self_attn.q_b_proj.weight":"model-00013-of-00016.safetensors","model.layers.51.input_layernorm.weight":"model-00013-of-00016.safetensors","model.layers.51.mlp.down_proj.weight":"model-00013-of-00016.safetensors","model.layers.51.mlp.gate_proj.weight":"model-00013-of-00016.safetensors","model.layers.51.mlp.up_proj.weight":"model-00013-of-00016.safetensors","model.layers.51.post_attention_layernorm.weight":"model-00013-of-00016.safetensors","model.layers.51.self_attn.kv_a_layernorm.weight":"model-00013-of-00016.safetensors","model.layers.51.self_attn.kv_a_proj_with_mqa.weight":"model-00013-of-00016.safetensors","model.layers.51.self_attn.kv_b_proj.weight":"model-00013-of-00016.safetensors","model.layers.51.self_attn.o_proj.weight":"model-00013-of-00016.safetensors","model.layers.51.self_attn.q_a_layernorm.weight":"model-00013-of-00016.safetensors","model.layers.51.self_attn.q_a_proj.weight":"model-00013-of-00016.safetensors","model.layers.51.self_attn.q_b_proj.weight":"model-00013-of-00016.safetensors","model.layers.52.input_layernorm.weight":"model-00013-of-00016.safetensors","model.layers.52.mlp.down_proj.weight":"model-00013-of-00016.safetensors","model.layers.52.mlp.gate_proj.weight":"model-00013-of-00016.safetensors","model.layers.52.mlp.up_proj.weight":"model-00013-of-00016.safetensors","model.layers.52.post_attention_layernorm.weight":"model-00013-of-00016.safetensors","model.layers.52.self_attn.kv_a_layernorm.weight":"model-00013-of-00016.safetensors","model.layers.52.self_attn.kv_a_proj_with_mqa.weight":"model-00013-of-00016.safetensors","model.layers.52.self_attn.kv_b_proj.weight":"model-00013-of-00016.safetensors","model.layers.52.self_attn.o_proj.weight":"model-00013-of-00016.safetensors","model.layers.52.self_attn.q_a_layernorm.weight":"model-00013-of-00016.safetensors","model.layers.52.self_attn.q_a_proj.weight":"model-00013-of-00016.safetensors","model.layers.52.self_attn.q_b_proj.weight":"model-00013-of-00016.safetensors","model.layers.53.input_layernorm.weight":"model-00013-of-00016.safetensors","model.layers.53.mlp.down_proj.weight":"model-00013-of-00016.safetensors","model.layers.53.mlp.gate_proj.weight":"model-00013-of-00016.safetensors","model.layers.53.mlp.up_proj.weight":"model-00013-of-00016.safetensors","model.layers.53.post_attention_layernorm.weight":"model-00013-of-00016.safetensors","model.layers.53.self_attn.kv_a_layernorm.weight":"model-00013-of-00016.safetensors","model.layers.53.self_attn.kv_a_proj_with_mqa.weight":"model-00013-of-00016.safetensors","model.layers.53.self_attn.kv_b_proj.weight":"model-00013-of-00016.safetensors","model.layers.53.self_attn.o_proj.weight":"model-00013-of-00016.safetensors","model.layers.53.self_attn.q_a_layernorm.weight":"model-00013-of-00016.safetensors","model.layers.53.self_attn.q_a_proj.weight":"model-00013-of-00016.safetensors","model.layers.53.self_attn.q_b_proj.weight":"model-00013-of-00016.safetensors","model.layers.54.input_layernorm.weight":"model-00013-of-00016.safetensors","model.layers.54.mlp.down_proj.weight":"model-00014-of-00016.safetensors","model.layers.54.mlp.gate_proj.weight":"model-00014-of-00016.safetensors","model.layers.54.mlp.up_proj.weight":"model-00014-of-00016.safetensors","model.layers.54.post_attention_layernorm.weight":"model-00014-of-00016.safetensors","model.layers.54.self_attn.kv_a_layernorm.weight":"model-00014-of-00016.safetensors","model.layers.54.self_attn.kv_a_proj_with_mqa.weight":"model-00014-of-00016.safetensors","model.layers.54.self_attn.kv_b_proj.weight":"model-00014-of-00016.safetensors","model.layers.54.self_attn.o_proj.weight":"model-00014-of-00016.safetensors","model.layers.54.self_attn.q_a_layernorm.weight":"model-00014-of-00016.safetensors","model.layers.54.self_attn.q_a_proj.weight":"model-00014-of-00016.safetensors","model.layers.54.self_attn.q_b_proj.weight":"model-00014-of-00016.safetensors","model.layers.55.input_layernorm.weight":"model-00014-of-00016.safetensors","model.layers.55.mlp.down_proj.weight":"model-00014-of-00016.safetensors","model.layers.55.mlp.gate_proj.weight":"model-00014-of-00016.safetensors","model.layers.55.mlp.up_proj.weight":"model-00014-of-00016.safetensors","model.layers.55.post_attention_layernorm.weight":"model-00014-of-00016.safetensors","model.layers.55.self_attn.kv_a_layernorm.weight":"model-00014-of-00016.safetensors","model.layers.55.self_attn.kv_a_proj_with_mqa.weight":"model-00014-of-00016.safetensors","model.layers.55.self_attn.kv_b_proj.weight":"model-00014-of-00016.safetensors","model.layers.55.self_attn.o_proj.weight":"model-00014-of-00016.safetensors","model.layers.55.self_attn.q_a_layernorm.weight":"model-00014-of-00016.safetensors","model.layers.55.self_attn.q_a_proj.weight":"model-00014-of-00016.safetensors","model.layers.55.self_attn.q_b_proj.weight":"model-00014-of-00016.safetensors","model.layers.56.input_layernorm.weight":"model-00014-of-00016.safetensors","model.layers.56.mlp.down_proj.weight":"model-00014-of-00016.safetensors","model.layers.56.mlp.gate_proj.weight":"model-00014-of-00016.safetensors","model.layers.56.mlp.up_proj.weight":"model-00014-of-00016.safetensors","model.layers.56.post_attention_layernorm.weight":"model-00014-of-00016.safetensors","model.layers.56.self_attn.kv_a_layernorm.weight":"model-00014-of-00016.safetensors","model.layers.56.self_attn.kv_a_proj_with_mqa.weight":"model-00014-of-00016.safetensors","model.layers.56.self_attn.kv_b_proj.weight":"model-00014-of-00016.safetensors","model.layers.56.self_attn.o_proj.weight":"model-00014-of-00016.safetensors","model.layers.56.self_attn.q_a_layernorm.weight":"model-00014-of-00016.safetensors","model.layers.56.self_attn.q_a_proj.weight":"model-00014-of-00016.safetensors","model.layers.56.self_attn.q_b_proj.weight":"model-00014-of-00016.safetensors","model.layers.57.input_layernorm.weight":"model-00014-of-00016.safetensors","model.layers.57.mlp.down_proj.weight":"model-00014-of-00016.safetensors","model.layers.57.mlp.gate_proj.weight":"model-00014-of-00016.safetensors","model.layers.57.mlp.up_proj.weight":"model-00014-of-00016.safetensors","model.layers.57.post_attention_layernorm.weight":"model-00014-of-00016.safetensors","model.layers.57.self_attn.kv_a_layernorm.weight":"model-00014-of-00016.safetensors","model.layers.57.self_attn.kv_a_proj_with_mqa.weight":"model-00014-of-00016.safetensors","model.layers.57.self_attn.kv_b_proj.weight":"model-00014-of-00016.safetensors","model.layers.57.self_attn.o_proj.weight":"model-00014-of-00016.safetensors","model.layers.57.self_attn.q_a_layernorm.weight":"model-00014-of-00016.safetensors","model.layers.57.self_attn.q_a_proj.weight":"model-00014-of-00016.safetensors","model.layers.57.self_attn.q_b_proj.weight":"model-00014-of-00016.safetensors","model.layers.58.input_layernorm.weight":"model-00014-of-00016.safetensors","model.layers.58.mlp.down_proj.weight":"model-00015-of-00016.safetensors","model.layers.58.mlp.gate_proj.weight":"model-00015-of-00016.safetensors","model.layers.58.mlp.up_proj.weight":"model-00015-of-00016.safetensors","model.layers.58.post_attention_layernorm.weight":"model-00015-of-00016.safetensors","model.layers.58.self_attn.kv_a_layernorm.weight":"model-00015-of-00016.safetensors","model.layers.58.self_attn.kv_a_proj_with_mqa.weight":"model-00015-of-00016.safetensors","model.layers.58.self_attn.kv_b_proj.weight":"model-00015-of-00016.safetensors","model.layers.58.self_attn.o_proj.weight":"model-00015-of-00016.safetensors","model.layers.58.self_attn.q_a_layernorm.weight":"model-00015-of-00016.safetensors","model.layers.58.self_attn.q_a_proj.weight":"model-00015-of-00016.safetensors","model.layers.58.self_attn.q_b_proj.weight":"model-00015-of-00016.safetensors","model.layers.59.input_layernorm.weight":"model-00015-of-00016.safetensors","model.layers.59.mlp.down_proj.weight":"model-00015-of-00016.safetensors","model.layers.59.mlp.gate_proj.weight":"model-00015-of-00016.safetensors","model.layers.59.mlp.up_proj.weight":"model-00015-of-00016.safetensors","model.layers.59.post_attention_layernorm.weight":"model-00015-of-00016.safetensors","model.layers.59.self_attn.kv_a_layernorm.weight":"model-00015-of-00016.safetensors","model.layers.59.self_attn.kv_a_proj_with_mqa.weight":"model-00015-of-00016.safetensors","model.layers.59.self_attn.kv_b_proj.weight":"model-00015-of-00016.safetensors","model.layers.59.self_attn.o_proj.weight":"model-00015-of-00016.safetensors","model.layers.59.self_attn.q_a_layernorm.weight":"model-00015-of-00016.safetensors","model.layers.59.self_attn.q_a_proj.weight":"model-00015-of-00016.safetensors","model.layers.59.self_attn.q_b_proj.weight":"model-00015-of-00016.safetensors","model.layers.6.input_layernorm.weight":"model-00015-of-00016.safetensors","model.layers.6.mlp.down_proj.weight":"model-00015-of-00016.safetensors","model.layers.6.mlp.gate_proj.weight":"model-00015-of-00016.safetensors","model.layers.6.mlp.up_proj.weight":"model-00015-of-00016.safetensors","model.layers.6.post_attention_layernorm.weight":"model-00015-of-00016.safetensors","model.layers.6.self_attn.kv_a_layernorm.weight":"model-00015-of-00016.safetensors","model.layers.6.self_attn.kv_a_proj_with_mqa.weight":"model-00015-of-00016.safetensors","model.layers.6.self_attn.kv_b_proj.weight":"model-00015-of-00016.safetensors","model.layers.6.self_attn.o_proj.weight":"model-00015-of-00016.safetensors","model.layers.6.self_attn.q_a_layernorm.weight":"model-00015-of-00016.safetensors","model.layers.6.self_attn.q_a_proj.weight":"model-00015-of-00016.safetensors","model.layers.6.self_attn.q_b_proj.weight":"model-00015-of-00016.safetensors","model.layers.60.input_layernorm.weight":"model-00015-of-00016.safetensors","model.layers.60.mlp.down_proj.weight":"model-00015-of-00016.safetensors","model.layers.60.mlp.gate_proj.weight":"model-00015-of-00016.safetensors","model.layers.60.mlp.up_proj.weight":"model-00015-of-00016.safetensors","model.layers.60.post_attention_layernorm.weight":"model-00015-of-00016.safetensors","model.layers.60.self_attn.kv_a_layernorm.weight":"model-00015-of-00016.safetensors","model.layers.60.self_attn.kv_a_proj_with_mqa.weight":"model-00015-of-00016.safetensors","model.layers.60.self_attn.kv_b_proj.weight":"model-00015-of-00016.safetensors","model.layers.60.self_attn.o_proj.weight":"model-00015-of-00016.safetensors","model.layers.60.self_attn.q_a_layernorm.weight":"model-00015-of-00016.safetensors","model.layers.60.self_attn.q_a_proj.weight":"model-00015-of-00016.safetensors","model.layers.60.self_attn.q_b_proj.weight":"model-00015-of-00016.safetensors","model.layers.7.input_layernorm.weight":"model-00015-of-00016.safetensors","model.layers.7.mlp.down_proj.weight":"model-00016-of-00016.safetensors","model.layers.7.mlp.gate_proj.weight":"model-00016-of-00016.safetensors","model.layers.7.mlp.up_proj.weight":"model-00016-of-00016.safetensors","model.layers.7.post_attention_layernorm.weight":"model-00016-of-00016.safetensors","model.layers.7.self_attn.kv_a_layernorm.weight":"model-00016-of-00016.safetensors","model.layers.7.self_attn.kv_a_proj_with_mqa.weight":"model-00016-of-00016.safetensors","model.layers.7.self_attn.kv_b_proj.weight":"model-00016-of-00016.safetensors","model.layers.7.self_attn.o_proj.weight":"model-00016-of-00016.safetensors","model.layers.7.self_attn.q_a_layernorm.weight":"model-00016-of-00016.safetensors","model.layers.7.self_attn.q_a_proj.weight":"model-00016-of-00016.safetensors","model.layers.7.self_attn.q_b_proj.weight":"model-00016-of-00016.safetensors","model.layers.8.input_layernorm.weight":"model-00016-of-00016.safetensors","model.layers.8.mlp.down_proj.weight":"model-00016-of-00016.safetensors","model.layers.8.mlp.gate_proj.weight":"model-00016-of-00016.safetensors","model.layers.8.mlp.up_proj.weight":"model-00016-of-00016.safetensors","model.layers.8.post_attention_layernorm.weight":"model-00016-of-00016.safetensors","model.layers.8.self_attn.kv_a_layernorm.weight":"model-00016-of-00016.safetensors","model.layers.8.self_attn.kv_a_proj_with_mqa.weight":"model-00016-of-00016.safetensors","model.layers.8.self_attn.kv_b_proj.weight":"model-00016-of-00016.safetensors","model.layers.8.self_attn.o_proj.weight":"model-00016-of-00016.safetensors","model.layers.8.self_attn.q_a_layernorm.weight":"model-00016-of-00016.safetensors","model.layers.8.self_attn.q_a_proj.weight":"model-00016-of-00016.safetensors","model.layers.8.self_attn.q_b_proj.weight":"model-00016-of-00016.safetensors","model.layers.9.input_layernorm.weight":"model-00016-of-00016.safetensors","model.layers.9.mlp.down_proj.weight":"model-00016-of-00016.safetensors","model.layers.9.mlp.gate_proj.weight":"model-00016-of-00016.safetensors","model.layers.9.mlp.up_proj.weight":"model-00016-of-00016.safetensors","model.layers.9.post_attention_layernorm.weight":"model-00016-of-00016.safetensors","model.layers.9.self_attn.kv_a_layernorm.weight":"model-00016-of-00016.safetensors","model.layers.9.self_attn.kv_a_proj_with_mqa.weight":"model-00016-of-00016.safetensors","model.layers.9.self_attn.kv_b_proj.weight":"model-00016-of-00016.safetensors","model.layers.9.self_attn.o_proj.weight":"model-00016-of-00016.safetensors","model.layers.9.self_attn.q_a_layernorm.weight":"model-00016-of-00016.safetensors","model.layers.9.self_attn.q_a_proj.weight":"model-00016-of-00016.safetensors","model.layers.9.self_attn.q_b_proj.weight":"model-00016-of-00016.safetensors","model.norm.weight":"model-00016-of-00016.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin▁of▁sentence|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|end▁of▁sentence|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|end▁of▁sentence|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|