solidrust/Llama-3.1-8B-Lexi-Uncensored-V2-AWQ
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Upload quantized AWQ model

Browse Source
This commit is contained in:
Shaun Prince
2024-09-03 04:55:09 +00:00
committed by system
parent 30ae96977b
commit 2c0980f2d1
8 changed files with 413465 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
config.json Normal file
View File

@@ -0,0 +1,49 @@
{
"_name_or_path": "/opt/openbet/inference/data/Orenguteng-Llama-3.1-8B-Lexi-Uncensored-V2",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": [
128001,
128008,
128009
],
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pad_token_id": 128004,
"pretraining_tp": 1,
"quantization_config": {
"bits": 4,
"group_size": 128,
"modules_to_not_convert": null,
"quant_method": "awq",
"version": "gemm",
"zero_point": true
},
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 8.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.44.2",
"unsloth_version": "2024.8",
"use_cache": true,
"vocab_size": 128256
}

14
generation_config.json Normal file
View File

@@ -0,0 +1,14 @@
{
"bos_token_id": 128000,
"do_sample": true,
"eos_token_id": [
128001,
128008,
128009
],
"max_length": 131072,
"pad_token_id": 128004,
"temperature": 0.6,
"top_p": 0.9,
"transformers_version": "4.44.2"
}

3
model-00001-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f73fe27430e1cb3b1684e28e13c0d8fd48b27a21b9e3a5d58b3edc53b1f2919f
size 4677265296

3
model-00002-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3e9a36ad418b0cd9b253f65771552d7dc05cf1abf1170b94de4b4d546aac255d
size 1050673280

746
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,746 @@
{
"metadata": {
"total_size": 5727854592
},
"weight_map": {
"model.embed_tokens.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.19.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.20.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.21.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.22.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.23.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.24.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.25.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.26.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.27.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.28.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.29.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.30.post_attention_layernorm.weight": "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.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.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.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.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.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.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.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.norm.weight": "model-00001-of-00002.safetensors",
"lm_head.weight": "model-00002-of-00002.safetensors"
}
}

23
special_tokens_map.json Normal file
View File

@@ -0,0 +1,23 @@
{
"bos_token": {
"content": "<|begin_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|eot_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|finetune_right_pad_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

410563
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

2064
tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff