DavidAU commited on
Commit
6ac5ffb
1 Parent(s): 3e56a97

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: []
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+
8
+ ---
9
+
10
+ <h2>Mistral-Nemo-Instruct-2407-13.35B-BRAINSTORM-5x-FORM-11</h2>
11
+
12
+ This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats.
13
+ The source code can also be used directly.
14
+
15
+ For full information about this model, including:
16
+
17
+ - Details about this model and its use case(s).
18
+ - Context limits
19
+ - Special usage notes / settings.
20
+ - Any model(s) used to create this model.
21
+ - Template(s) used to access/use this model.
22
+ - Example generation(s)
23
+ - GGUF quants of this model
24
+
25
+ Please go to:
26
+
27
+ [ https://huggingface.co/DavidAU/Mistral-Nemo-Instruct-2407-13.35B-BRAINSTORM-5x-FORM-11-GGUF ]
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "G:/11b/Mistral-Nemo-Instruct-2407-12B",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 1024000,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 44,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.43.3",
25
+ "use_cache": true,
26
+ "vocab_size": 131072
27
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.4", "total_size": 26676684800}, "weight_map": {"lm_head.weight": "model-00001-of-00028.safetensors", "model.embed_tokens.weight": "model-00002-of-00028.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00028.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00028.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00028.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00028.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00028.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00028.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00028.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00028.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00028.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00028.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00028.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00028.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00028.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00028.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00028.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00028.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00028.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00028.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00028.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00028.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00028.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00028.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00028.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00028.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00028.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00028.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00028.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00028.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00028.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00028.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00028.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00028.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00006-of-00028.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00028.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00028.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00028.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00028.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00028.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00028.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00028.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00028.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00028.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00028.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00028.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00028.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00028.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00028.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00009-of-00028.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00028.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00028.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00028.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.input_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00028.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00009-of-00028.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00010-of-00028.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00010-of-00028.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00028.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00028.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00028.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.input_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00028.safetensors", "model.layers.21.input_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00028.safetensors", "model.layers.22.input_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00011-of-00028.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00028.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00011-of-00028.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00028.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00028.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00028.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.input_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00028.safetensors", "model.layers.24.input_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00012-of-00028.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00028.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00028.safetensors", "model.layers.25.input_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00013-of-00028.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00013-of-00028.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00013-of-00028.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00028.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00028.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00028.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00028.safetensors", "model.layers.26.input_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00013-of-00028.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", "model.layers.27.input_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00014-of-00028.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00014-of-00028.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00014-of-00028.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00028.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", "model.layers.28.input_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00015-of-00028.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00015-of-00028.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00015-of-00028.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00015-of-00028.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00015-of-00028.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00015-of-00028.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00015-of-00028.safetensors", "model.layers.29.input_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00015-of-00028.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00015-of-00028.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00015-of-00028.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00015-of-00028.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00016-of-00028.safetensors", "model.layers.3.input_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00016-of-00028.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00016-of-00028.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00016-of-00028.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00016-of-00028.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00016-of-00028.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00016-of-00028.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00016-of-00028.safetensors", "model.layers.30.input_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00016-of-00028.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00016-of-00028.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00017-of-00028.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00017-of-00028.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00017-of-00028.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00017-of-00028.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00017-of-00028.safetensors", "model.layers.31.input_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00017-of-00028.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00017-of-00028.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00017-of-00028.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00017-of-00028.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00017-of-00028.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00017-of-00028.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00017-of-00028.safetensors", "model.layers.32.input_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00017-of-00028.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00018-of-00028.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00018-of-00028.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00018-of-00028.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00018-of-00028.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00018-of-00028.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00018-of-00028.safetensors", "model.layers.33.input_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00018-of-00028.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00018-of-00028.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00018-of-00028.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00018-of-00028.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00018-of-00028.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00018-of-00028.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00018-of-00028.safetensors", "model.layers.34.input_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00019-of-00028.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00019-of-00028.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00019-of-00028.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00019-of-00028.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00019-of-00028.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00019-of-00028.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00028.safetensors", "model.layers.35.input_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00019-of-00028.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00019-of-00028.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00019-of-00028.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00019-of-00028.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00020-of-00028.safetensors", "model.layers.36.input_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00020-of-00028.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00020-of-00028.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00020-of-00028.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00020-of-00028.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00020-of-00028.safetensors", "model.layers.37.input_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00020-of-00028.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00020-of-00028.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00021-of-00028.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00021-of-00028.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00021-of-00028.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00021-of-00028.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00021-of-00028.safetensors", "model.layers.38.input_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00021-of-00028.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00021-of-00028.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00021-of-00028.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00021-of-00028.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00021-of-00028.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00021-of-00028.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00021-of-00028.safetensors", "model.layers.43.input_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.42.input_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.41.input_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.40.input_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.39.input_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00021-of-00028.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00022-of-00028.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00022-of-00028.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00022-of-00028.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00022-of-00028.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00022-of-00028.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00022-of-00028.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00023-of-00028.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00023-of-00028.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00023-of-00028.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00023-of-00028.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00023-of-00028.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00023-of-00028.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00024-of-00028.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00024-of-00028.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00024-of-00028.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00024-of-00028.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00024-of-00028.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00024-of-00028.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00024-of-00028.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00024-of-00028.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00024-of-00028.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00024-of-00028.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00024-of-00028.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.input_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00025-of-00028.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00025-of-00028.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00025-of-00028.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00025-of-00028.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00025-of-00028.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.input_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00025-of-00028.safetensors", "model.layers.6.input_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.input_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00027-of-00028.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00027-of-00028.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.input_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00027-of-00028.safetensors", "model.layers.9.input_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00027-of-00028.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00027-of-00028.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00028-of-00028.safetensors", "model.norm.weight": "model-00028-of-00028.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff