stelterlab/EuroLLM-9B-Instruct-AWQ
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Upload 9 files

Browse Source 
Initial commit - first quantization
This commit is contained in:
Christian Otto Stelter
2024-12-04 18:03:45 +00:00
committed by system
parent 96c36b88b0
commit cfe7eb5f61
10 changed files with 3172 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.gitattributes vendored
View File

@@ -33,3 +33,4 @@ saved_model/**/* 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
tokenizer.json filter=lfs diff=lfs merge=lfs -text

38
config.json Normal file
View File

@@ -0,0 +1,38 @@
{
"_name_or_path": "/data/hf/models/models--utter-project--EuroLLM-9B-Instruct/snapshots/880ffbd6f9fb66b82471a21cd43621e0cff780fb",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 4,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"max_position_embeddings": 4096,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 42,
"num_key_value_heads": 8,
"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": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.46.1",
"use_cache": false,
"vocab_size": 128000
}

7
generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 3,
"do_sample": true,
"eos_token_id": 4,
"transformers_version": "4.46.1"
}

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a4fcdbeed92b3d9d2650c74324afad5e29c503508b6a4064ab837832c883aa1a
size 4980364296

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b0c94364d11df83a11c782a24108a01189ba2422fad61d20768085d96bbd5bc1
size 1327561192

976
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,976 @@
{
"metadata": {
"total_size": 6307815424
},
"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.layers.32.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.32.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.32.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.32.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.32.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.32.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.32.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.32.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.32.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.32.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.32.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.32.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.32.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.32.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.32.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.32.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.32.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.32.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.32.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.32.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.32.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.33.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.33.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.33.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.33.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.33.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.33.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.33.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.33.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.33.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.33.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.33.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.33.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.33.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.33.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.33.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.33.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.33.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.33.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.33.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.33.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.33.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.34.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.34.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.34.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.34.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.34.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.34.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.34.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.34.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.34.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.34.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.34.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.34.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.34.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.34.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.34.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.34.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.34.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.34.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.34.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.34.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.34.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.35.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.35.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.35.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.35.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.35.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.35.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.35.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.35.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.35.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.35.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.35.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.35.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.35.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.35.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.35.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.35.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.35.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.35.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.35.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.35.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.35.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.36.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.36.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.36.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.36.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.36.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.36.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.36.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.36.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.36.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.36.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.36.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.36.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.36.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.36.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.36.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.36.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.36.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.36.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.36.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.36.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.36.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.36.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.36.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.37.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.37.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.37.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.37.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.37.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.37.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.37.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.37.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.37.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.37.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.37.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.37.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.37.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.37.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.37.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.37.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.37.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.37.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.37.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.37.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.37.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.37.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.37.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.38.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.38.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.38.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.38.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.38.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.38.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.38.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.38.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.38.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.38.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.38.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.38.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.38.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.38.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.38.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.38.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.38.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.38.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.38.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.38.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.38.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.38.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.38.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.39.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.39.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.39.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.39.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.39.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.39.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.39.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.39.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.39.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.39.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.39.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.39.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.39.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
"model.layers.39.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
"model.layers.39.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.39.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
"model.layers.39.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
"model.layers.39.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.39.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
"model.layers.39.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
"model.layers.39.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.40.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
"model.layers.40.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
"model.layers.40.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.40.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
"model.layers.40.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
"model.layers.40.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.40.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
"model.layers.40.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
"model.layers.40.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.40.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
"model.layers.40.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
"model.layers.40.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.40.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
"model.layers.40.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
"model.layers.40.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.40.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
"model.layers.40.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
"model.layers.40.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.40.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
"model.layers.40.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
"model.layers.40.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.40.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.40.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.41.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
"model.layers.41.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
"model.layers.41.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.41.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
"model.layers.41.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
"model.layers.41.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.41.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
"model.layers.41.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
"model.layers.41.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.41.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
"model.layers.41.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
"model.layers.41.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.41.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
"model.layers.41.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
"model.layers.41.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.41.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
"model.layers.41.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
"model.layers.41.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.41.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
"model.layers.41.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
"model.layers.41.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
"model.layers.41.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.41.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.norm.weight": "model-00002-of-00002.safetensors",
"lm_head.weight": "model-00002-of-00002.safetensors"
}
}

30
special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bddecaa5b362553591b9c989b601f60490b417be3d595698e81fcfb27353c6ae
size 15783334

3
tokenizer.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:42957aec88804838805b335da1bbcce9d116024a20c6c4b56757648b9e348254
size 2408875

2108
tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff