simplyinquisitive commited on
Commit
322926a
1 Parent(s): 6222c87

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - simplyinquisitive/codestral-7B-A
4
+ - simplyinquisitive/codestral-7B-B
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
+ * [simplyinquisitive/codestral-7B-A](https://huggingface.co/simplyinquisitive/codestral-7B-A)
24
+ * [simplyinquisitive/codestral-7B-B](https://huggingface.co/simplyinquisitive/codestral-7B-B)
25
+
26
+ ### Configuration
27
+
28
+ The following YAML configuration was used to produce this model:
29
+
30
+ ```yaml
31
+ slices:
32
+ - sources:
33
+ - model: simplyinquisitive/codestral-7B-A
34
+ layer_range: [0, 64]
35
+ - model: simplyinquisitive/codestral-7B-B
36
+ layer_range: [0, 64]
37
+ merge_method: slerp
38
+ base_model: simplyinquisitive/codestral-7B-A
39
+ parameters:
40
+ t:
41
+ - filter: self_attn
42
+ value: [0, 0.5, 0.3, 0.7, 1]
43
+ - filter: mlp
44
+ value: [1, 0.5, 0.7, 0.3, 0]
45
+ - value: 0.5
46
+ dtype: bfloat16
47
+ random_seed: 0
48
+
49
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "simplyinquisitive/codestral-7B-A",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 64,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 1000000.0,
20
+ "sliding_window": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.41.0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ slices:
2
+ - sources:
3
+ - model: simplyinquisitive/codestral-7B-A
4
+ layer_range: [0, 64]
5
+ - model: simplyinquisitive/codestral-7B-B
6
+ layer_range: [0, 64]
7
+ merge_method: slerp
8
+ base_model: simplyinquisitive/codestral-7B-A
9
+ parameters:
10
+ t:
11
+ - filter: self_attn
12
+ value: [0, 0.5, 0.3, 0.7, 1]
13
+ - filter: mlp
14
+ value: [1, 0.5, 0.7, 0.3, 0]
15
+ - value: 0.5
16
+ dtype: bfloat16
17
+ random_seed: 0
model-00001-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e61b741fcc8ca56894fc00a4c287167d81222264e360f72ee0c9968c4a9b0ff9
3
+ size 4985104624
model-00002-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02d70ac0a93094761d5ddd8171cf48315ada17553e05e608ec1cbcebb2a9b31e
3
+ size 4957867744
model-00003-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9756153e817e823e0ccb0801111a1ed2b76cba2a5e2668c97f33bfb8a54cf55
3
+ size 4806840640
model-00004-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8a76e5304fea2478901c237a11a1b6258fb542b4a947e850414e34ef2bef1ad
3
+ size 4915895368
model-00005-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04e7edc21f2f5b4bbe76bfca9d78898999f2d279e50fb14598ea79f5c38b9b56
3
+ size 4882323752
model-00006-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70f5c77be2f2c25af0e5d2ea3400ba7c6ada5e99803d4d77b22673bae3eb376c
3
+ size 4915895368
model-00007-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18be8715adfc51f218eebf3a3e11c52f08714a36993efd4a8aab2b77f76ef501
3
+ size 4882323752
model-00008-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e188ac92f2d84bddd5ad2efd2b2eb498dd40ba7f46b0ee1e6ab083397c66374f
3
+ size 4924289096
model-00009-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a60aab108eb6134065726552ad2648413130ccd8d2b19832359f8d9511485f24
3
+ size 318788512
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 39589261312}, "weight_map": {"lm_head.weight": "model-00001-of-00009.safetensors", "model.embed_tokens.weight": "model-00001-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.34.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.35.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.37.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.38.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.39.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.40.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.41.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.42.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.43.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.44.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.45.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.46.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.47.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.48.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.49.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.50.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.51.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.52.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.53.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.54.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.55.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.56.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.57.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.58.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.59.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.60.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.61.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.62.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.63.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.norm.weight": "model-00009-of-00009.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": null,
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }