Leooyii/NTK_64k_Slimpajama_2B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Leooyii/NTK_64k_Slimpajama_2B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-11 14:40:00 +08:00
commit ce5041bbfc
13 changed files with 94606 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View File

@@ -0,0 +1,35 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

3
added_tokens.json Normal file
View File

@@ -0,0 +1,3 @@
{
"[PAD]": 32000
}

30
config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"_name_or_path": "meta-llama/Llama-2-7b-hf",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 8.0,
"type": "dynamic"
},
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.35.2",
"use_cache": false,
"vocab_size": 32001
}

3
model-00001-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2c7c60c1eef4140c8918aa887580cfd3411c7305a30ccff9dbbfda4da0b4bc50
size 4938993544

3
model-00002-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9b8f3731d8aa81941ac906b19a7df03cd1285f952ba3facf64481e9960d61d1a
size 4947390880

3
model-00003-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7d6f2dd080687a2f675b9b57cbf38c6c58d25164e1366f8a3594c60ee6f87e2a
size 3590497008

298
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,298 @@
{
"metadata": {
"total_size": 13476847616
},
"weight_map": {
"lm_head.weight": "model-00003-of-00003.safetensors",
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.norm.weight": "model-00003-of-00003.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": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

93400
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
tokenizer.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
size 499723

47
tokenizer_config.json Normal file
View File

@@ -0,0 +1,47 @@
{
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32000": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": false,
"model_max_length": 65536,
"pad_token": "[PAD]",
"padding_side": "right",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}

748
trainer_state.json Normal file
View File

@@ -0,0 +1,748 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.997920997920998,
"eval_steps": 500,
"global_step": 120,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.0,
"loss": 5.3569,
"step": 1
},
{
"epoch": 0.02,
"learning_rate": 4.6275642631951835e-06,
"loss": 4.4928,
"step": 2
},
{
"epoch": 0.02,
"learning_rate": 7.3345158268416935e-06,
"loss": 4.4425,
"step": 3
},
{
"epoch": 0.03,
"learning_rate": 9.255128526390367e-06,
"loss": 3.7693,
"step": 4
},
{
"epoch": 0.04,
"learning_rate": 1.0744871473609633e-05,
"loss": 3.3417,
"step": 5
},
{
"epoch": 0.05,
"learning_rate": 1.1962080090036879e-05,
"loss": 2.7971,
"step": 6
},
{
"epoch": 0.06,
"learning_rate": 1.299121531141887e-05,
"loss": 2.5958,
"step": 7
},
{
"epoch": 0.07,
"learning_rate": 1.388269278958555e-05,
"loss": 2.383,
"step": 8
},
{
"epoch": 0.07,
"learning_rate": 1.4669031653683387e-05,
"loss": 2.1741,
"step": 9
},
{
"epoch": 0.08,
"learning_rate": 1.537243573680482e-05,
"loss": 2.0406,
"step": 10
},
{
"epoch": 0.09,
"learning_rate": 1.600874212937343e-05,
"loss": 1.9426,
"step": 11
},
{
"epoch": 0.1,
"learning_rate": 1.6589644353232063e-05,
"loss": 1.9206,
"step": 12
},
{
"epoch": 0.11,
"learning_rate": 1.712402259777778e-05,
"loss": 1.839,
"step": 13
},
{
"epoch": 0.12,
"learning_rate": 1.7618779574614054e-05,
"loss": 1.8111,
"step": 14
},
{
"epoch": 0.12,
"learning_rate": 1.8079387300451327e-05,
"loss": 1.7821,
"step": 15
},
{
"epoch": 0.13,
"learning_rate": 1.8510257052780734e-05,
"loss": 1.7383,
"step": 16
},
{
"epoch": 0.14,
"learning_rate": 1.891499697130832e-05,
"loss": 1.7587,
"step": 17
},
{
"epoch": 0.15,
"learning_rate": 1.929659591687857e-05,
"loss": 1.6917,
"step": 18
},
{
"epoch": 0.16,
"learning_rate": 1.9657557553855117e-05,
"loss": 1.7491,
"step": 19
},
{
"epoch": 0.17,
"learning_rate": 2e-05,
"loss": 1.677,
"step": 20
},
{
"epoch": 0.17,
"learning_rate": 2e-05,
"loss": 1.6952,
"step": 21
},
{
"epoch": 0.18,
"learning_rate": 1.98e-05,
"loss": 1.6802,
"step": 22
},
{
"epoch": 0.19,
"learning_rate": 1.9600000000000002e-05,
"loss": 1.6731,
"step": 23
},
{
"epoch": 0.2,
"learning_rate": 1.94e-05,
"loss": 1.6718,
"step": 24
},
{
"epoch": 0.21,
"learning_rate": 1.9200000000000003e-05,
"loss": 1.6927,
"step": 25
},
{
"epoch": 0.22,
"learning_rate": 1.9e-05,
"loss": 1.6631,
"step": 26
},
{
"epoch": 0.22,
"learning_rate": 1.88e-05,
"loss": 1.6413,
"step": 27
},
{
"epoch": 0.23,
"learning_rate": 1.86e-05,
"loss": 1.6799,
"step": 28
},
{
"epoch": 0.24,
"learning_rate": 1.8400000000000003e-05,
"loss": 1.6413,
"step": 29
},
{
"epoch": 0.25,
"learning_rate": 1.8200000000000002e-05,
"loss": 1.6549,
"step": 30
},
{
"epoch": 0.26,
"learning_rate": 1.8e-05,
"loss": 1.6693,
"step": 31
},
{
"epoch": 0.27,
"learning_rate": 1.7800000000000002e-05,
"loss": 1.667,
"step": 32
},
{
"epoch": 0.27,
"learning_rate": 1.76e-05,
"loss": 1.6308,
"step": 33
},
{
"epoch": 0.28,
"learning_rate": 1.7400000000000003e-05,
"loss": 1.6509,
"step": 34
},
{
"epoch": 0.29,
"learning_rate": 1.72e-05,
"loss": 1.6222,
"step": 35
},
{
"epoch": 0.3,
"learning_rate": 1.7e-05,
"loss": 1.6285,
"step": 36
},
{
"epoch": 0.31,
"learning_rate": 1.6800000000000002e-05,
"loss": 1.6167,
"step": 37
},
{
"epoch": 0.32,
"learning_rate": 1.66e-05,
"loss": 1.6296,
"step": 38
},
{
"epoch": 0.32,
"learning_rate": 1.64e-05,
"loss": 1.6444,
"step": 39
},
{
"epoch": 0.33,
"learning_rate": 1.62e-05,
"loss": 1.6628,
"step": 40
},
{
"epoch": 0.34,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.6141,
"step": 41
},
{
"epoch": 0.35,
"learning_rate": 1.58e-05,
"loss": 1.639,
"step": 42
},
{
"epoch": 0.36,
"learning_rate": 1.5600000000000003e-05,
"loss": 1.618,
"step": 43
},
{
"epoch": 0.37,
"learning_rate": 1.54e-05,
"loss": 1.5938,
"step": 44
},
{
"epoch": 0.37,
"learning_rate": 1.5200000000000002e-05,
"loss": 1.6398,
"step": 45
},
{
"epoch": 0.38,
"learning_rate": 1.5000000000000002e-05,
"loss": 1.6212,
"step": 46
},
{
"epoch": 0.39,
"learning_rate": 1.48e-05,
"loss": 1.6495,
"step": 47
},
{
"epoch": 0.4,
"learning_rate": 1.46e-05,
"loss": 1.6114,
"step": 48
},
{
"epoch": 0.41,
"learning_rate": 1.4400000000000001e-05,
"loss": 1.643,
"step": 49
},
{
"epoch": 0.42,
"learning_rate": 1.4200000000000001e-05,
"loss": 1.6174,
"step": 50
},
{
"epoch": 0.42,
"learning_rate": 1.4e-05,
"loss": 1.5991,
"step": 51
},
{
"epoch": 0.43,
"learning_rate": 1.38e-05,
"loss": 1.6355,
"step": 52
},
{
"epoch": 0.44,
"learning_rate": 1.3600000000000002e-05,
"loss": 1.6439,
"step": 53
},
{
"epoch": 0.45,
"learning_rate": 1.3400000000000002e-05,
"loss": 1.6249,
"step": 54
},
{
"epoch": 0.46,
"learning_rate": 1.3200000000000002e-05,
"loss": 1.6543,
"step": 55
},
{
"epoch": 0.47,
"learning_rate": 1.3000000000000001e-05,
"loss": 1.6403,
"step": 56
},
{
"epoch": 0.47,
"learning_rate": 1.2800000000000001e-05,
"loss": 1.6351,
"step": 57
},
{
"epoch": 0.48,
"learning_rate": 1.2600000000000001e-05,
"loss": 1.6226,
"step": 58
},
{
"epoch": 0.49,
"learning_rate": 1.2400000000000002e-05,
"loss": 1.6459,
"step": 59
},
{
"epoch": 0.5,
"learning_rate": 1.22e-05,
"loss": 1.5992,
"step": 60
},
{
"epoch": 0.51,
"learning_rate": 1.2e-05,
"loss": 1.6293,
"step": 61
},
{
"epoch": 0.52,
"learning_rate": 1.18e-05,
"loss": 1.6327,
"step": 62
},
{
"epoch": 0.52,
"learning_rate": 1.16e-05,
"loss": 1.6132,
"step": 63
},
{
"epoch": 0.53,
"learning_rate": 1.14e-05,
"loss": 1.6111,
"step": 64
},
{
"epoch": 0.54,
"learning_rate": 1.1200000000000001e-05,
"loss": 1.6142,
"step": 65
},
{
"epoch": 0.55,
"learning_rate": 1.1000000000000001e-05,
"loss": 1.6114,
"step": 66
},
{
"epoch": 0.56,
"learning_rate": 1.0800000000000002e-05,
"loss": 1.6308,
"step": 67
},
{
"epoch": 0.57,
"learning_rate": 1.0600000000000002e-05,
"loss": 1.6181,
"step": 68
},
{
"epoch": 0.57,
"learning_rate": 1.04e-05,
"loss": 1.6185,
"step": 69
},
{
"epoch": 0.58,
"learning_rate": 1.02e-05,
"loss": 1.6336,
"step": 70
},
{
"epoch": 0.59,
"learning_rate": 1e-05,
"loss": 1.6343,
"step": 71
},
{
"epoch": 0.6,
"learning_rate": 9.800000000000001e-06,
"loss": 1.612,
"step": 72
},
{
"epoch": 0.61,
"learning_rate": 9.600000000000001e-06,
"loss": 1.633,
"step": 73
},
{
"epoch": 0.62,
"learning_rate": 9.4e-06,
"loss": 1.5895,
"step": 74
},
{
"epoch": 0.62,
"learning_rate": 9.200000000000002e-06,
"loss": 1.6387,
"step": 75
},
{
"epoch": 0.63,
"learning_rate": 9e-06,
"loss": 1.6415,
"step": 76
},
{
"epoch": 0.64,
"learning_rate": 8.8e-06,
"loss": 1.6191,
"step": 77
},
{
"epoch": 0.65,
"learning_rate": 8.6e-06,
"loss": 1.6317,
"step": 78
},
{
"epoch": 0.66,
"learning_rate": 8.400000000000001e-06,
"loss": 1.6239,
"step": 79
},
{
"epoch": 0.67,
"learning_rate": 8.2e-06,
"loss": 1.6315,
"step": 80
},
{
"epoch": 0.67,
"learning_rate": 8.000000000000001e-06,
"loss": 1.5979,
"step": 81
},
{
"epoch": 0.68,
"learning_rate": 7.800000000000002e-06,
"loss": 1.6171,
"step": 82
},
{
"epoch": 0.69,
"learning_rate": 7.600000000000001e-06,
"loss": 1.6199,
"step": 83
},
{
"epoch": 0.7,
"learning_rate": 7.4e-06,
"loss": 1.643,
"step": 84
},
{
"epoch": 0.71,
"learning_rate": 7.2000000000000005e-06,
"loss": 1.6,
"step": 85
},
{
"epoch": 0.72,
"learning_rate": 7e-06,
"loss": 1.6071,
"step": 86
},
{
"epoch": 0.72,
"learning_rate": 6.800000000000001e-06,
"loss": 1.6227,
"step": 87
},
{
"epoch": 0.73,
"learning_rate": 6.600000000000001e-06,
"loss": 1.5972,
"step": 88
},
{
"epoch": 0.74,
"learning_rate": 6.4000000000000006e-06,
"loss": 1.6356,
"step": 89
},
{
"epoch": 0.75,
"learning_rate": 6.200000000000001e-06,
"loss": 1.6205,
"step": 90
},
{
"epoch": 0.76,
"learning_rate": 6e-06,
"loss": 1.5796,
"step": 91
},
{
"epoch": 0.77,
"learning_rate": 5.8e-06,
"loss": 1.6274,
"step": 92
},
{
"epoch": 0.77,
"learning_rate": 5.600000000000001e-06,
"loss": 1.6383,
"step": 93
},
{
"epoch": 0.78,
"learning_rate": 5.400000000000001e-06,
"loss": 1.5923,
"step": 94
},
{
"epoch": 0.79,
"learning_rate": 5.2e-06,
"loss": 1.627,
"step": 95
},
{
"epoch": 0.8,
"learning_rate": 5e-06,
"loss": 1.6201,
"step": 96
},
{
"epoch": 0.81,
"learning_rate": 4.800000000000001e-06,
"loss": 1.6116,
"step": 97
},
{
"epoch": 0.81,
"learning_rate": 4.600000000000001e-06,
"loss": 1.6333,
"step": 98
},
{
"epoch": 0.82,
"learning_rate": 4.4e-06,
"loss": 1.6184,
"step": 99
},
{
"epoch": 0.83,
"learning_rate": 4.2000000000000004e-06,
"loss": 1.5916,
"step": 100
},
{
"epoch": 0.84,
"learning_rate": 4.000000000000001e-06,
"loss": 1.6153,
"step": 101
},
{
"epoch": 0.85,
"learning_rate": 3.8000000000000005e-06,
"loss": 1.5926,
"step": 102
},
{
"epoch": 0.86,
"learning_rate": 3.6000000000000003e-06,
"loss": 1.6308,
"step": 103
},
{
"epoch": 0.86,
"learning_rate": 3.4000000000000005e-06,
"loss": 1.6603,
"step": 104
},
{
"epoch": 0.87,
"learning_rate": 3.2000000000000003e-06,
"loss": 1.6227,
"step": 105
},
{
"epoch": 0.88,
"learning_rate": 3e-06,
"loss": 1.6172,
"step": 106
},
{
"epoch": 0.89,
"learning_rate": 2.8000000000000003e-06,
"loss": 1.6213,
"step": 107
},
{
"epoch": 0.9,
"learning_rate": 2.6e-06,
"loss": 1.6276,
"step": 108
},
{
"epoch": 0.91,
"learning_rate": 2.4000000000000003e-06,
"loss": 1.5951,
"step": 109
},
{
"epoch": 0.91,
"learning_rate": 2.2e-06,
"loss": 1.6211,
"step": 110
},
{
"epoch": 0.92,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.6203,
"step": 111
},
{
"epoch": 0.93,
"learning_rate": 1.8000000000000001e-06,
"loss": 1.6136,
"step": 112
},
{
"epoch": 0.94,
"learning_rate": 1.6000000000000001e-06,
"loss": 1.5951,
"step": 113
},
{
"epoch": 0.95,
"learning_rate": 1.4000000000000001e-06,
"loss": 1.6153,
"step": 114
},
{
"epoch": 0.96,
"learning_rate": 1.2000000000000002e-06,
"loss": 1.6057,
"step": 115
},
{
"epoch": 0.96,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.608,
"step": 116
},
{
"epoch": 0.97,
"learning_rate": 8.000000000000001e-07,
"loss": 1.6029,
"step": 117
},
{
"epoch": 0.98,
"learning_rate": 6.000000000000001e-07,
"loss": 1.6206,
"step": 118
},
{
"epoch": 0.99,
"learning_rate": 4.0000000000000003e-07,
"loss": 1.6221,
"step": 119
},
{
"epoch": 1.0,
"learning_rate": 2.0000000000000002e-07,
"loss": 1.6047,
"step": 120
},
{
"epoch": 1.0,
"step": 120,
"total_flos": 3215233992622080.0,
"train_loss": 1.783738382657369,
"train_runtime": 173137.391,
"train_samples_per_second": 0.178,
"train_steps_per_second": 0.001
}
],
"logging_steps": 1.0,
"max_steps": 120,
"num_train_epochs": 1,
"save_steps": 500,
"total_flos": 3215233992622080.0,
"trial_name": null,
"trial_params": null
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f1f42738fe31174c0e1e17a435ef2e8c4952a6928075b8534f2e13145d2b530f
size 6971