chargoddard commited on
Commit
d26cb27
1 Parent(s): ae2989a

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - 01-ai/Yi-34B
4
+ - abacusai/Smaug-34B-v0.1
5
+ - anthracite-org/magnum-v3-34b
6
+ library_name: transformers
7
+ tags:
8
+ - mergekit
9
+ - merge
10
+
11
+ ---
12
+ # merge
13
+
14
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
15
+
16
+ ## Merge Details
17
+ ### Merge Method
18
+
19
+ This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [01-ai/Yi-34B](https://huggingface.co/01-ai/Yi-34B) as a base.
20
+
21
+ ### Models Merged
22
+
23
+ The following models were included in the merge:
24
+ * [abacusai/Smaug-34B-v0.1](https://huggingface.co/abacusai/Smaug-34B-v0.1)
25
+ * [anthracite-org/magnum-v3-34b](https://huggingface.co/anthracite-org/magnum-v3-34b)
26
+
27
+ ### Configuration
28
+
29
+ The following YAML configuration was used to produce this model:
30
+
31
+ ```yaml
32
+ models:
33
+ - model: 01-ai/Yi-34B
34
+ #no parameters necessary for base model
35
+ - model: anthracite-org/magnum-v3-34b
36
+ parameters:
37
+ density: 0.5
38
+ weight: 0.5
39
+ - model: abacusai/Smaug-34B-v0.1
40
+ parameters:
41
+ density: 0.5
42
+ weight: 0.5
43
+
44
+ merge_method: ties
45
+ base_model: 01-ai/Yi-34B
46
+ parameters:
47
+ normalize: false
48
+ int8_mask: true
49
+ dtype: float16
50
+ ```
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "01-ai/Yi-34B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 7168,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 20480,
14
+ "max_position_embeddings": 4096,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 56,
18
+ "num_hidden_layers": 60,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 0,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 5000000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.44.1",
28
+ "use_cache": true,
29
+ "vocab_size": 64000
30
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: 01-ai/Yi-34B
3
+ #no parameters necessary for base model
4
+ - model: anthracite-org/magnum-v3-34b
5
+ parameters:
6
+ density: 0.5
7
+ weight: 0.5
8
+ - model: abacusai/Smaug-34B-v0.1
9
+ parameters:
10
+ density: 0.5
11
+ weight: 0.5
12
+
13
+ merge_method: ties
14
+ base_model: 01-ai/Yi-34B
15
+ parameters:
16
+ normalize: false
17
+ int8_mask: true
18
+ dtype: float16
model-00001-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5ea3c00a686595c1fd0291b2f8e7f20643984c6a978331e3d7993cd95d974a
3
+ size 4961950632
model-00002-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d0cd2038e87fc7980579c9b737c0f0d1601c1844cf05761904064fa76a5121f
3
+ size 4976675488
model-00003-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fab1d66d0bcab0b92f8018cf87f25558796d6bff9508cd633d08a72bcb040bf3
3
+ size 4756459728
model-00004-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4424349d5a1cf9682f44f6091d6b9d477560b4695b1de9229543c53f27d9c6c2
3
+ size 4991370112
model-00005-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc6d3a04bf73bffd2966aad73856c8bee17714ef7c4be38303efe3284a15f521
3
+ size 4756459728
model-00006-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebebea6113e7192bfb2716b5627819499923ef3b415e6c47bed187a51fad6535
3
+ size 4756459720
model-00007-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a2f06e13746bb14b31c03ba86979856561769d96f66b0f8371dbfb6bd1088a1
3
+ size 4991370120
model-00008-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c9dcb8b76d15b3b7af7bf6698f38c08463cdc3c67a220194e0b9bd6086fc15e
3
+ size 4756459728
model-00009-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:977a59af162f1994ea02b206ee4ff7c7c278c6eb9a81dd9c16fbd4afd540b38d
3
+ size 4756459720
model-00010-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9297c76217f7a2fcb4c104b05c4478c2f85df91eeefc32d151e986c781bd9c2c
3
+ size 4991370120
model-00011-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42db3208cc2a7a3afc2836840a51c851c203e34ce0ca94c12ba7d092dad18030
3
+ size 4756459720
model-00012-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c21b7afec71213ef75f88acf61ab89449d5d2696a77348a8fba7b2aa256f16a
3
+ size 4756459728
model-00013-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6954e01719415bf25636ce816fa9a73979548276e288c520277a76ceed82c337
3
+ size 4991370120
model-00014-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18a92cc078e01cb652499885d5198b7d29f69074afa54b3192562fbdfa8521e3
3
+ size 4756459704
model-00015-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14caa90fab3d52ba9744e78dab3300952f0cedcc697215999e0830deab4b8f67
3
+ size 822113176
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.4", "total_size": 68777834496}, "weight_map": {"lm_head.weight": "model-00001-of-00015.safetensors", "model.embed_tokens.weight": "model-00001-of-00015.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.35.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.39.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.42.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.47.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.50.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.54.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.59.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.9.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00015-of-00015.safetensors", "model.norm.weight": "model-00015-of-00015.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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 sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
+ size 1033105
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|startoftext|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<|endoftext|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<|startoftext|>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "<|endoftext|>",
34
+ "legacy": true,
35
+ "model_max_length": 4096,
36
+ "pad_token": "<unk>",
37
+ "sp_model_kwargs": {},
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false
41
+ }