ddh0 commited on
Commit
cb2e965
1 Parent(s): 02dcdaa

upload metadata

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|end_of_turn|>": 32000,
3
+ "<|pad_0|>": 32001
4
+ }
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Starling-LM-10.7B-beta",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 32000,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 8192,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 48,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 32000,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 10000.0,
21
+ "sliding_window": 4096,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.38.2",
25
+ "use_cache": true,
26
+ "vocab_size": 32002
27
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ dtype: bfloat16
2
+ merge_method: passthrough
3
+ slices:
4
+ - sources:
5
+ - model: Starling-LM-7B-beta
6
+ layer_range: [0,9]
7
+ - sources:
8
+ - model: Starling-LM-7B-beta
9
+ layer_range: [5,14]
10
+ - sources:
11
+ - model: Starling-LM-7B-beta
12
+ layer_range: [10,19]
13
+ - sources:
14
+ - model: Starling-LM-7B-beta
15
+ layer_range: [15,24]
16
+ - sources:
17
+ - model: Starling-LM-7B-beta
18
+ layer_range: [20,32]
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1", "total_size": 21463080960}, "weight_map": {"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.embed_tokens.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.37.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.33.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.36.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "lm_head.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.47.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.46.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.44.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.43.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.42.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.40.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|end_of_turn|>",
4
+ "<|pad_0|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|end_of_turn|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<|end_of_turn|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|end_of_turn|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|pad_0|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "additional_special_tokens": [
47
+ "<|end_of_turn|>",
48
+ "<|pad_0|>"
49
+ ],
50
+ "bos_token": "<s>",
51
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
52
+ "clean_up_tokenization_spaces": false,
53
+ "eos_token": "<|end_of_turn|>",
54
+ "legacy": true,
55
+ "max_length": 1000,
56
+ "model_max_length": 1000000000000000019884624838656,
57
+ "pad_to_multiple_of": null,
58
+ "pad_token": "<|end_of_turn|>",
59
+ "pad_token_type_id": 0,
60
+ "padding_side": "left",
61
+ "sp_model_kwargs": {},
62
+ "spaces_between_special_tokens": false,
63
+ "stride": 0,
64
+ "tokenizer_class": "LlamaTokenizer",
65
+ "truncation_side": "right",
66
+ "truncation_strategy": "longest_first",
67
+ "unk_token": "<unk>",
68
+ "use_default_system_prompt": true
69
+ }