初始化项目，由ModelHub XC社区提供模型
Model: pentagoniac/SEMIKONG-8b-GPTQ Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
182
config.json
Normal file
182
config.json
Normal file
File diff suppressed because one or more lines are too long
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
128001,
|
||||
128009
|
||||
],
|
||||
"max_length": 4096,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.41.2"
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2674a868e7af673e98aa1349af127c724703b50cf415312dd6efc0ebafcd0f25
|
||||
size 1980428176
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:96e22606137b3171519353c94c09e39945990088f22852ae5b05fc2ffce37cda
|
||||
size 1990370296
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b8809cfea0b4733c1a3aeaa28d1ae5cc92cb7228f7f3be56f4baa7acd9813f8a
|
||||
size 1762144816
|
||||
970
model.safetensors.index.json
Normal file
970
model.safetensors.index.json
Normal file
@@ -0,0 +1,970 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 5732835328
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00003-of-00003.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.g_idx": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.scales": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.g_idx": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
410563
tokenizer.json
Normal file
410563
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
2065
tokenizer_config.json
Normal file
2065
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user