chargoddard commited on
Commit
5cdb23a
1 Parent(s): 767756e

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - anthracite-org/magnum-v3-34b
4
+ - abacusai/Smaug-34B-v0.1
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+
10
+ ---
11
+ # merge
12
+
13
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
14
+
15
+ ## Merge Details
16
+ ### Merge Method
17
+
18
+ This model was merged using the SLERP merge method.
19
+
20
+ ### Models Merged
21
+
22
+ The following models were included in the merge:
23
+ * [anthracite-org/magnum-v3-34b](https://huggingface.co/anthracite-org/magnum-v3-34b)
24
+ * [abacusai/Smaug-34B-v0.1](https://huggingface.co/abacusai/Smaug-34B-v0.1)
25
+
26
+ ### Configuration
27
+
28
+ The following YAML configuration was used to produce this model:
29
+
30
+ ```yaml
31
+ models:
32
+ - model: abacusai/Smaug-34B-v0.1
33
+ - model: anthracite-org/magnum-v3-34b
34
+ merge_method: slerp
35
+ base_model: abacusai/Smaug-34B-v0.1
36
+ dtype: bfloat16
37
+ parameters:
38
+ t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers
39
+
40
+ ```
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "abacusai/Smaug-34B-v0.1",
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": 200000,
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": "bfloat16",
27
+ "transformers_version": "4.44.1",
28
+ "use_cache": true,
29
+ "vocab_size": 64000
30
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: abacusai/Smaug-34B-v0.1
3
+ - model: anthracite-org/magnum-v3-34b
4
+ merge_method: slerp
5
+ base_model: abacusai/Smaug-34B-v0.1
6
+ dtype: bfloat16
7
+ parameters:
8
+ t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers
model-00001-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:691378660a87c9a3020b92ec9491ec6f60c4f8300b36e5b990fdc0122ff8b450
3
+ size 4961950664
model-00002-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cddda390ad5814da4fd2ed007f4d4989565211b659522b1123f8ad6bca7f414
3
+ size 4976675528
model-00003-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cb3b499ee9579c0c52d7ea37677c88026b492239c9862715ba1e0ad78a00da3
3
+ size 4756459760
model-00004-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d87088797078cfc64e501cb12babe87300e30f97a3c991ecc6efff785eda9221
3
+ size 4991370152
model-00005-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6144f1b3426b243352dfac4ff1e269539aceea0011821d3922f127f3d1dc67d9
3
+ size 4756459768
model-00006-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7b8ad14b59550528751a12018dc7a375879a9893dcfd6e37212bc435ad07d72
3
+ size 4756459752
model-00007-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ccf731d8ffb37b80b4063264d62ec25be727afccf09b8897cb0586e2c45b5da
3
+ size 4991370160
model-00008-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc241568fb07800d02350ae3fd31264c99d839b46740cf8f01fd7a21f13428b
3
+ size 4756459768
model-00009-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39a9f339e7d3e2aa5227a02eb887fee952abb043654e54443637eedbf4fe3afa
3
+ size 4756459752
model-00010-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df96e3d7f4bcfa9b593651eaca320c946b7d8775a2c04ab2735b1ec760865310
3
+ size 4991370160
model-00011-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a04d89fd3db55158726c0c98bb68353b500a4f18dee15a2e5c40fd830f208e0
3
+ size 4756459760
model-00012-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58d247cb0a19e5ed87ca9f6264f9279c424962d33dd90aebae31c39f3a5b5ab2
3
+ size 4756459760
model-00013-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a08e40ff08260a2a689c7f734f86bcae1861f27944e9630f9822a55d6065272f
3
+ size 4991370160
model-00014-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:455868c4bfbf36d5e7c4802e7082b7388200242105942d89f79f25079269eb45
3
+ size 4756459736
model-00015-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:988f546c45568d28ee9f8b41cbd4528f5aae00cf62381e499c79a5b4781c52d9
3
+ size 822113184
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": "<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
+ "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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' ' + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1024,
37
+ "pad_token": "<unk>",
38
+ "padding_side": "left",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
+ }