初始化项目，由ModelHub XC社区提供模型
Model: Heralax/Augmentoolkit-DataSpecialist-gptqmodel-4bit 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
|
||||
4
chat_template.jinja
Normal file
4
chat_template.jinja
Normal file
@@ -0,0 +1,4 @@
|
||||
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
|
||||
' + message['content'] + '<|im_end|>' + '
|
||||
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
||||
' }}{% endif %}
|
||||
49
config.json
Normal file
49
config.json
Normal file
@@ -0,0 +1,49 @@
|
||||
{
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"quantization_config": {
|
||||
"bits": 4,
|
||||
"checkpoint_format": "gptq",
|
||||
"desc_act": true,
|
||||
"group_size": 128,
|
||||
"lm_head": false,
|
||||
"meta": {
|
||||
"damp_auto_increment": 0.01,
|
||||
"damp_percent": 0.05,
|
||||
"mse": 0.0,
|
||||
"quantizer": [
|
||||
"gptqmodel:4.0.0-dev"
|
||||
],
|
||||
"static_groups": false,
|
||||
"true_sequential": true,
|
||||
"uri": "https://github.com/modelcloud/gptqmodel",
|
||||
"v2": false,
|
||||
"v2_alpha": 0.25
|
||||
},
|
||||
"pack_dtype": "int32",
|
||||
"quant_method": "gptq",
|
||||
"sym": true
|
||||
},
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.52.4",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32768
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.52.4"
|
||||
}
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c9200139f239143627037a3f47473a48df796f2627c2e12c54a2baea109e0296
|
||||
size 3900032728
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:661889574baf601eec8099e39476b04dcb8edbefcc209b72f155d3908ddcb26e
|
||||
size 268435584
|
||||
970
model.safetensors.index.json
Normal file
970
model.safetensors.index.json
Normal file
@@ -0,0 +1,970 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 4168359936
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00002-of-00002.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00001-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
225
quant_log.csv
Normal file
225
quant_log.csv
Normal file
@@ -0,0 +1,225 @@
|
||||
layer,module,loss,samples,damp,time
|
||||
0,self_attn.k_proj,0.0000000243,0.05000,1.346
|
||||
0,self_attn.v_proj,0.0000000040,0.05000,1.044
|
||||
0,self_attn.q_proj,0.0000000903,0.05000,1.080
|
||||
0,self_attn.o_proj,0.0000000000,0.05000,1.098
|
||||
0,mlp.gate_proj,0.0000000940,0.05000,1.349
|
||||
0,mlp.up_proj,0.0000000836,0.05000,1.323
|
||||
0,mlp.down_proj,0.0000000001,0.05000,4.570
|
||||
1,self_attn.k_proj,0.0000001356,0.05000,1.074
|
||||
1,self_attn.v_proj,0.0000000265,0.05000,1.093
|
||||
1,self_attn.q_proj,0.0000002987,0.05000,1.117
|
||||
1,self_attn.o_proj,0.0000000001,0.05000,1.154
|
||||
1,mlp.gate_proj,0.0000003163,0.05000,1.123
|
||||
1,mlp.up_proj,0.0000002789,0.05000,1.105
|
||||
1,mlp.down_proj,0.0000000908,0.05000,4.407
|
||||
2,self_attn.k_proj,0.0000009065,0.05000,1.114
|
||||
2,self_attn.v_proj,0.0000000839,0.05000,1.056
|
||||
2,self_attn.q_proj,0.0000016890,0.05000,1.104
|
||||
2,self_attn.o_proj,0.0000000001,0.05000,1.082
|
||||
2,mlp.gate_proj,0.0000006744,0.05000,1.100
|
||||
2,mlp.up_proj,0.0000005911,0.05000,1.105
|
||||
2,mlp.down_proj,0.0000000003,0.05000,4.560
|
||||
3,self_attn.k_proj,0.0000006056,0.05000,1.147
|
||||
3,self_attn.v_proj,0.0000000826,0.05000,1.076
|
||||
3,self_attn.q_proj,0.0000011741,0.05000,1.094
|
||||
3,self_attn.o_proj,0.0000000001,0.05000,1.081
|
||||
3,mlp.gate_proj,0.0000011593,0.05000,1.104
|
||||
3,mlp.up_proj,0.0000010041,0.05000,1.086
|
||||
3,mlp.down_proj,0.0000000005,0.05000,4.424
|
||||
4,self_attn.k_proj,0.0000008699,0.05000,1.165
|
||||
4,self_attn.v_proj,0.0000001383,0.05000,1.057
|
||||
4,self_attn.q_proj,0.0000018787,0.05000,1.104
|
||||
4,self_attn.o_proj,0.0000000002,0.05000,1.063
|
||||
4,mlp.gate_proj,0.0000017767,0.05000,1.102
|
||||
4,mlp.up_proj,0.0000014464,0.05000,1.073
|
||||
4,mlp.down_proj,0.0000000010,0.05000,4.394
|
||||
5,self_attn.k_proj,0.0000011964,0.05000,1.125
|
||||
5,self_attn.v_proj,0.0000001727,0.05000,1.074
|
||||
5,self_attn.q_proj,0.0000026247,0.05000,1.063
|
||||
5,self_attn.o_proj,0.0000000004,0.05000,1.098
|
||||
5,mlp.gate_proj,0.0000026750,0.05000,1.144
|
||||
5,mlp.up_proj,0.0000020422,0.05000,1.143
|
||||
5,mlp.down_proj,0.0000000018,0.05000,4.481
|
||||
6,self_attn.k_proj,0.0000012233,0.05000,1.092
|
||||
6,self_attn.v_proj,0.0000001751,0.05000,1.063
|
||||
6,self_attn.q_proj,0.0000025896,0.05000,1.096
|
||||
6,self_attn.o_proj,0.0000000005,0.05000,1.093
|
||||
6,mlp.gate_proj,0.0000033022,0.05000,1.108
|
||||
6,mlp.up_proj,0.0000025730,0.05000,1.122
|
||||
6,mlp.down_proj,0.0000000026,0.05000,4.475
|
||||
7,self_attn.k_proj,0.0000015788,0.05000,1.092
|
||||
7,self_attn.v_proj,0.0000002271,0.05000,1.053
|
||||
7,self_attn.q_proj,0.0000032580,0.05000,1.086
|
||||
7,self_attn.o_proj,0.0000000009,0.05000,1.101
|
||||
7,mlp.gate_proj,0.0000040918,0.05000,1.105
|
||||
7,mlp.up_proj,0.0000031199,0.05000,1.098
|
||||
7,mlp.down_proj,0.0000000035,0.05000,4.402
|
||||
8,self_attn.k_proj,0.0000013194,0.05000,1.116
|
||||
8,self_attn.v_proj,0.0000002595,0.05000,1.085
|
||||
8,self_attn.q_proj,0.0000028454,0.05000,1.102
|
||||
8,self_attn.o_proj,0.0000000011,0.05000,1.071
|
||||
8,mlp.gate_proj,0.0000046629,0.05000,1.125
|
||||
8,mlp.up_proj,0.0000036305,0.05000,1.095
|
||||
8,mlp.down_proj,0.0000000043,0.05000,4.342
|
||||
9,self_attn.k_proj,0.0000019476,0.05000,1.046
|
||||
9,self_attn.v_proj,0.0000003167,0.05000,1.053
|
||||
9,self_attn.q_proj,0.0000040997,0.05000,1.078
|
||||
9,self_attn.o_proj,0.0000000013,0.05000,1.072
|
||||
9,mlp.gate_proj,0.0000050292,0.05000,1.109
|
||||
9,mlp.up_proj,0.0000040537,0.05000,1.096
|
||||
9,mlp.down_proj,0.0000000050,0.05000,4.360
|
||||
10,self_attn.k_proj,0.0000017725,0.05000,1.063
|
||||
10,self_attn.v_proj,0.0000002921,0.05000,1.088
|
||||
10,self_attn.q_proj,0.0000036800,0.05000,1.225
|
||||
10,self_attn.o_proj,0.0000000018,0.05000,1.099
|
||||
10,mlp.gate_proj,0.0000052495,0.05000,1.118
|
||||
10,mlp.up_proj,0.0000043227,0.05000,1.088
|
||||
10,mlp.down_proj,0.0000000060,0.05000,4.511
|
||||
11,self_attn.k_proj,0.0000021077,0.05000,1.058
|
||||
11,self_attn.v_proj,0.0000004395,0.05000,1.063
|
||||
11,self_attn.q_proj,0.0000045010,0.05000,1.069
|
||||
11,self_attn.o_proj,0.0000000029,0.05000,1.066
|
||||
11,mlp.gate_proj,0.0000057856,0.05000,1.111
|
||||
11,mlp.up_proj,0.0000048466,0.05000,1.083
|
||||
11,mlp.down_proj,0.0000000072,0.05000,4.406
|
||||
12,self_attn.k_proj,0.0000027316,0.05000,1.064
|
||||
12,self_attn.v_proj,0.0000004806,0.05000,1.100
|
||||
12,self_attn.q_proj,0.0000059322,0.05000,1.121
|
||||
12,self_attn.o_proj,0.0000000029,0.05000,1.075
|
||||
12,mlp.gate_proj,0.0000064971,0.05000,1.098
|
||||
12,mlp.up_proj,0.0000055545,0.05000,1.127
|
||||
12,mlp.down_proj,0.0000000088,0.05000,4.425
|
||||
13,self_attn.k_proj,0.0000024133,0.05000,1.064
|
||||
13,self_attn.v_proj,0.0000005040,0.05000,1.064
|
||||
13,self_attn.q_proj,0.0000049132,0.05000,1.111
|
||||
13,self_attn.o_proj,0.0000000038,0.05000,1.058
|
||||
13,mlp.gate_proj,0.0000072860,0.05000,1.325
|
||||
13,mlp.up_proj,0.0000064150,0.05000,1.165
|
||||
13,mlp.down_proj,0.0000000112,0.05000,4.474
|
||||
14,self_attn.k_proj,0.0000024321,0.05000,1.054
|
||||
14,self_attn.v_proj,0.0000008004,0.05000,1.082
|
||||
14,self_attn.q_proj,0.0000056635,0.05000,1.112
|
||||
14,self_attn.o_proj,0.0000000058,0.05000,1.097
|
||||
14,mlp.gate_proj,0.0000083033,0.05000,1.100
|
||||
14,mlp.up_proj,0.0000073240,0.05000,1.117
|
||||
14,mlp.down_proj,0.0000000147,0.05000,4.616
|
||||
15,self_attn.k_proj,0.0000032265,0.05000,1.105
|
||||
15,self_attn.v_proj,0.0000009160,0.05000,1.047
|
||||
15,self_attn.q_proj,0.0000071495,0.05000,1.086
|
||||
15,self_attn.o_proj,0.0000000060,0.05000,1.086
|
||||
15,mlp.gate_proj,0.0000098523,0.05000,1.120
|
||||
15,mlp.up_proj,0.0000083736,0.05000,1.130
|
||||
15,mlp.down_proj,0.0000000185,0.05000,4.463
|
||||
16,self_attn.k_proj,0.0000031272,0.05000,1.091
|
||||
16,self_attn.v_proj,0.0000009370,0.05000,1.104
|
||||
16,self_attn.q_proj,0.0000068247,0.05000,1.105
|
||||
16,self_attn.o_proj,0.0000000068,0.05000,1.062
|
||||
16,mlp.gate_proj,0.0000123035,0.05000,1.140
|
||||
16,mlp.up_proj,0.0000099590,0.05000,1.118
|
||||
16,mlp.down_proj,0.0000000257,0.05000,4.493
|
||||
17,self_attn.k_proj,0.0000025959,0.05000,1.102
|
||||
17,self_attn.v_proj,0.0000008746,0.05000,1.019
|
||||
17,self_attn.q_proj,0.0000061843,0.05000,1.097
|
||||
17,self_attn.o_proj,0.0000000070,0.05000,1.062
|
||||
17,mlp.gate_proj,0.0000143714,0.05000,1.106
|
||||
17,mlp.up_proj,0.0000116310,0.05000,1.075
|
||||
17,mlp.down_proj,0.0000000354,0.05000,4.374
|
||||
18,self_attn.k_proj,0.0000031679,0.05000,1.108
|
||||
18,self_attn.v_proj,0.0000010451,0.05000,1.063
|
||||
18,self_attn.q_proj,0.0000077381,0.05000,1.101
|
||||
18,self_attn.o_proj,0.0000000081,0.05000,1.116
|
||||
18,mlp.gate_proj,0.0000163663,0.05000,1.183
|
||||
18,mlp.up_proj,0.0000131605,0.05000,1.079
|
||||
18,mlp.down_proj,0.0000000498,0.05000,4.473
|
||||
19,self_attn.k_proj,0.0000032494,0.05000,1.097
|
||||
19,self_attn.v_proj,0.0000012439,0.05000,1.052
|
||||
19,self_attn.q_proj,0.0000074487,0.05000,1.106
|
||||
19,self_attn.o_proj,0.0000000095,0.05000,1.069
|
||||
19,mlp.gate_proj,0.0000187246,0.05000,1.102
|
||||
19,mlp.up_proj,0.0000147143,0.05000,1.099
|
||||
19,mlp.down_proj,0.0000000669,0.05000,4.367
|
||||
20,self_attn.k_proj,0.0000034868,0.05000,1.079
|
||||
20,self_attn.v_proj,0.0000013987,0.05000,1.067
|
||||
20,self_attn.q_proj,0.0000081005,0.05000,1.068
|
||||
20,self_attn.o_proj,0.0000000096,0.05000,1.068
|
||||
20,mlp.gate_proj,0.0000216847,0.05000,1.121
|
||||
20,mlp.up_proj,0.0000165116,0.05000,1.085
|
||||
20,mlp.down_proj,0.0000000704,0.05000,4.444
|
||||
21,self_attn.k_proj,0.0000034291,0.05000,1.102
|
||||
21,self_attn.v_proj,0.0000015221,0.05000,1.075
|
||||
21,self_attn.q_proj,0.0000080014,0.05000,1.108
|
||||
21,self_attn.o_proj,0.0000000102,0.05000,1.090
|
||||
21,mlp.gate_proj,0.0000261188,0.05000,1.127
|
||||
21,mlp.up_proj,0.0000185324,0.05000,1.129
|
||||
21,mlp.down_proj,0.0000000756,0.05000,4.455
|
||||
22,self_attn.k_proj,0.0000032560,0.05000,1.095
|
||||
22,self_attn.v_proj,0.0000016688,0.05000,1.114
|
||||
22,self_attn.q_proj,0.0000078390,0.05000,1.093
|
||||
22,self_attn.o_proj,0.0000000073,0.05000,1.072
|
||||
22,mlp.gate_proj,0.0000279689,0.05000,1.113
|
||||
22,mlp.up_proj,0.0000200703,0.05000,1.082
|
||||
22,mlp.down_proj,0.0000000813,0.05000,4.367
|
||||
23,self_attn.k_proj,0.0000031836,0.05000,1.087
|
||||
23,self_attn.v_proj,0.0000016718,0.05000,1.033
|
||||
23,self_attn.q_proj,0.0000079744,0.05000,1.077
|
||||
23,self_attn.o_proj,0.0000000097,0.05000,1.138
|
||||
23,mlp.gate_proj,0.0000311143,0.05000,1.119
|
||||
23,mlp.up_proj,0.0000222295,0.05000,1.104
|
||||
23,mlp.down_proj,0.0000000910,0.05000,4.489
|
||||
24,self_attn.k_proj,0.0000037302,0.05000,1.076
|
||||
24,self_attn.v_proj,0.0000019298,0.05000,1.046
|
||||
24,self_attn.q_proj,0.0000092244,0.05000,1.073
|
||||
24,self_attn.o_proj,0.0000000099,0.05000,1.096
|
||||
24,mlp.gate_proj,0.0000349600,0.05000,1.102
|
||||
24,mlp.up_proj,0.0000245547,0.05000,1.057
|
||||
24,mlp.down_proj,0.0000000984,0.05000,4.411
|
||||
25,self_attn.k_proj,0.0000035627,0.05000,1.108
|
||||
25,self_attn.v_proj,0.0000022298,0.05000,1.061
|
||||
25,self_attn.q_proj,0.0000092782,0.05000,1.120
|
||||
25,self_attn.o_proj,0.0000000102,0.05000,1.109
|
||||
25,mlp.gate_proj,0.0000381017,0.05000,1.124
|
||||
25,mlp.up_proj,0.0000269863,0.05000,1.131
|
||||
25,mlp.down_proj,0.0000001128,0.05000,4.506
|
||||
26,self_attn.k_proj,0.0000033970,0.05000,1.119
|
||||
26,self_attn.v_proj,0.0000023643,0.05000,1.134
|
||||
26,self_attn.q_proj,0.0000088182,0.05000,1.124
|
||||
26,self_attn.o_proj,0.0000000131,0.05000,1.094
|
||||
26,mlp.gate_proj,0.0000397645,0.05000,1.222
|
||||
26,mlp.up_proj,0.0000291584,0.05000,1.126
|
||||
26,mlp.down_proj,0.0000001288,0.05000,4.435
|
||||
27,self_attn.k_proj,0.0000032655,0.05000,1.078
|
||||
27,self_attn.v_proj,0.0000021690,0.05000,1.054
|
||||
27,self_attn.q_proj,0.0000090136,0.05000,1.098
|
||||
27,self_attn.o_proj,0.0000000146,0.05000,1.074
|
||||
27,mlp.gate_proj,0.0000431077,0.05000,1.092
|
||||
27,mlp.up_proj,0.0000319081,0.05000,1.129
|
||||
27,mlp.down_proj,0.0000001526,0.05000,4.389
|
||||
28,self_attn.k_proj,0.0000033885,0.05000,1.079
|
||||
28,self_attn.v_proj,0.0000031190,0.05000,1.050
|
||||
28,self_attn.q_proj,0.0000090153,0.05000,1.100
|
||||
28,self_attn.o_proj,0.0000000257,0.05000,1.092
|
||||
28,mlp.gate_proj,0.0000462653,0.05000,1.106
|
||||
28,mlp.up_proj,0.0000354446,0.05000,1.100
|
||||
28,mlp.down_proj,0.0000002016,0.05000,4.429
|
||||
29,self_attn.k_proj,0.0000032734,0.05000,1.080
|
||||
29,self_attn.v_proj,0.0000044012,0.05000,1.043
|
||||
29,self_attn.q_proj,0.0000103499,0.05000,1.089
|
||||
29,self_attn.o_proj,0.0000000528,0.05000,1.084
|
||||
29,mlp.gate_proj,0.0000452730,0.05000,1.120
|
||||
29,mlp.up_proj,0.0000361531,0.05000,1.125
|
||||
29,mlp.down_proj,0.0000002568,0.05000,4.422
|
||||
30,self_attn.k_proj,0.0000033870,0.05000,1.224
|
||||
30,self_attn.v_proj,0.0000048556,0.05000,1.072
|
||||
30,self_attn.q_proj,0.0000102100,0.05000,1.077
|
||||
30,self_attn.o_proj,0.0000000454,0.05000,1.065
|
||||
30,mlp.gate_proj,0.0000465985,0.05000,1.123
|
||||
30,mlp.up_proj,0.0000379377,0.05000,1.112
|
||||
30,mlp.down_proj,0.0000003248,0.05000,4.327
|
||||
31,self_attn.k_proj,0.0000031314,0.05000,1.107
|
||||
31,self_attn.v_proj,0.0000050672,0.05000,1.026
|
||||
31,self_attn.q_proj,0.0000093823,0.05000,1.097
|
||||
31,self_attn.o_proj,0.0000000755,0.05000,1.084
|
||||
31,mlp.gate_proj,0.0000427195,0.05000,1.119
|
||||
31,mlp.up_proj,0.0000335756,0.05000,1.123
|
||||
31,mlp.down_proj,0.0000004450,0.05000,4.457
|
||||
|
23
quantize_config.json
Normal file
23
quantize_config.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bits": 4,
|
||||
"group_size": 128,
|
||||
"desc_act": true,
|
||||
"sym": true,
|
||||
"lm_head": false,
|
||||
"quant_method": "gptq",
|
||||
"checkpoint_format": "gptq",
|
||||
"pack_dtype": "int32",
|
||||
"meta": {
|
||||
"quantizer": [
|
||||
"gptqmodel:4.0.0-dev"
|
||||
],
|
||||
"uri": "https://github.com/modelcloud/gptqmodel",
|
||||
"damp_percent": 0.05,
|
||||
"damp_auto_increment": 0.01,
|
||||
"static_groups": false,
|
||||
"true_sequential": true,
|
||||
"mse": 0.0,
|
||||
"v2": false,
|
||||
"v2_alpha": 0.25
|
||||
}
|
||||
}
|
||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<unk>",
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
275733
tokenizer.json
Normal file
275733
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
|
||||
size 587404
|
||||
6188
tokenizer_config.json
Normal file
6188
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user