Joseph717171 commited on
Commit
25b4910
1 Parent(s): c542630

Upload folder using huggingface_hub

Browse files
.DS_Store ADDED
Binary file (8.2 kB). View file
 
README.md ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: []
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+
8
+ ---
9
+ # ANIMA-Phi-Neptune-Mistral-10.7B
10
+
11
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
12
+
13
+ ## Merge Details
14
+ ### Merge Method
15
+
16
+ This model was merged using the passthrough merge method.
17
+
18
+ ### Models Merged
19
+
20
+ The following models were included in the merge:
21
+ * /Users/jsarnecki/opt/Workspace/Severian/ANIMA-Phi-Neptune-Mistral-7B
22
+
23
+ ### Configuration
24
+
25
+ The following YAML configuration was used to produce this model:
26
+
27
+ ```yaml
28
+ dtype: bfloat16
29
+ merge_method: passthrough
30
+ slices:
31
+ - sources:
32
+ - layer_range: [0, 24]
33
+ model: /Users/jsarnecki/opt/Workspace/Severian/ANIMA-Phi-Neptune-Mistral-7B
34
+ - sources:
35
+ - layer_range: [8, 32]
36
+ model: /Users/jsarnecki/opt/Workspace/Severian/ANIMA-Phi-Neptune-Mistral-7B
37
+
38
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/Users/jsarnecki/opt/Workspace/Severian/ANIMA-Phi-Neptune-Mistral-7B",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 48,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.39.0.dev0",
24
+ "use_cache": false,
25
+ "vocab_size": 32000
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ dtype: bfloat16
2
+ merge_method: passthrough
3
+ slices:
4
+ - sources:
5
+ - layer_range: [0, 24]
6
+ model: /Users/jsarnecki/opt/Workspace/Severian/ANIMA-Phi-Neptune-Mistral-7B
7
+ - sources:
8
+ - layer_range: [8, 32]
9
+ model: /Users/jsarnecki/opt/Workspace/Severian/ANIMA-Phi-Neptune-Mistral-7B
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5bf27ce1f321154581e151e9ff92547c3cbf298d47f54c60bf7c1c5cbd6c1e0
3
+ size 3892454760
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4885116722f479c94ba432493ca998fa36d4f7993e1d0b28bacaa91f657418c
3
+ size 3993134096
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5025a852170e43649b64f7b773d26181fab463bfd57803f839943f27ebf63a6e
3
+ size 3976357432
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9515f47d7a2abc353074db856cce94e6cda93a2be54fa11afd9dae3195b0378b
3
+ size 3976365696
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91295d2e729b7a2e7c1c143d3d0749fa6a041085027d0c34994305f4db7a2aa4
3
+ size 3997319448
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b425a6b0514d702ca2dccc9f3a2f08b471212d81f4628e9eb9cf313fbdc2334
3
+ size 1627467400
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.38.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.33.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.32.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.1.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.0.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.embed_tokens.weight": "model-00005-of-00006.safetensors", "lm_head.weight": "model-00005-of-00006.safetensors", "model.norm.weight": "model-00005-of-00006.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.47.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.46.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.45.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.44.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.43.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.42.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00006.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
30
+ "additional_special_tokens": [
31
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "clean_up_tokenization_spaces": false,
37
+ "eos_token": "</s>",
38
+ "legacy": true,
39
+ "max_length": 1024,
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_to_multiple_of": null,
42
+ "pad_token": "</s>",
43
+ "pad_token_type_id": 0,
44
+ "padding_side": "right",
45
+ "sp_model_kwargs": {},
46
+ "spaces_between_special_tokens": false,
47
+ "stride": 0,
48
+ "tokenizer_class": "LlamaTokenizer",
49
+ "truncation_side": "right",
50
+ "truncation_strategy": "longest_first",
51
+ "trust_remote_code": true,
52
+ "unk_token": "<unk>",
53
+ "use_default_system_prompt": true,
54
+ "use_fast": true
55
+ }