Kaoeiri commited on
Commit
1d87ed4
1 Parent(s): 78f8d95

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - TheDrummer/Cydonia-22B-v1.1
4
+ - TheDrummer/Cydonia-22B-v1.2
5
+ - anthracite-org/magnum-v4-22b
6
+ - TheDrummer/Cydonia-22B-v1.3
7
+ library_name: transformers
8
+ tags:
9
+ - mergekit
10
+ - merge
11
+
12
+ ---
13
+ # merge
14
+
15
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
16
+
17
+ ## Merge Details
18
+ ### Merge Method
19
+
20
+ This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [anthracite-org/magnum-v4-22b](https://huggingface.co/anthracite-org/magnum-v4-22b) as a base.
21
+
22
+ ### Models Merged
23
+
24
+ The following models were included in the merge:
25
+ * [TheDrummer/Cydonia-22B-v1.1](https://huggingface.co/TheDrummer/Cydonia-22B-v1.1)
26
+ * [TheDrummer/Cydonia-22B-v1.2](https://huggingface.co/TheDrummer/Cydonia-22B-v1.2)
27
+ * [TheDrummer/Cydonia-22B-v1.3](https://huggingface.co/TheDrummer/Cydonia-22B-v1.3)
28
+
29
+ ### Configuration
30
+
31
+ The following YAML configuration was used to produce this model:
32
+
33
+ ```yaml
34
+ models:
35
+ - model: anthracite-org/magnum-v4-22b
36
+ parameters:
37
+ weight: 1.0 # Magnum model to retain style and best writing
38
+ - model: TheDrummer/Cydonia-22B-v1.3
39
+ parameters:
40
+ weight: 0.4 # Cydonia v1.3 for creative/adventurous influence
41
+ density: 0.9 # Retain more creative influence, but balance it
42
+ - model: TheDrummer/Cydonia-22B-v1.2
43
+ parameters:
44
+ weight: 0.3 # Cydonia v1.2 to add more creativity
45
+ density: 0.85 # Slightly less density for extra creativity
46
+ - model: TheDrummer/Cydonia-22B-v1.1
47
+ parameters:
48
+ weight: 0.4 # Cydonia v1.1 for accuracy and evil/trolling thoughts
49
+ density: 0.86 # Higher density for accuracy retention
50
+
51
+ merge_method: dare_ties # Using dare_ties for better handling of interference
52
+ base_model: anthracite-org/magnum-v4-22b
53
+ parameters:
54
+ density: 0.9 # General density for the overall merge
55
+ epsilon: 0.1 # Maximum change in drop probabilities
56
+ lambda: 1.2 # Scaling factor for final merged deltas
57
+ dtype: bfloat16
58
+
59
+ ```
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "anthracite-org/magnum-v4-22b",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 6144,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 16384,
14
+ "max_position_embeddings": 32768,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 48,
17
+ "num_hidden_layers": 56,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.46.2",
25
+ "use_cache": false,
26
+ "vocab_size": 32768
27
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: anthracite-org/magnum-v4-22b
3
+ parameters:
4
+ weight: 1.0 # Magnum model to retain style and best writing
5
+ - model: TheDrummer/Cydonia-22B-v1.3
6
+ parameters:
7
+ weight: 0.4 # Cydonia v1.3 for creative/adventurous influence
8
+ density: 0.9 # Retain more creative influence, but balance it
9
+ - model: TheDrummer/Cydonia-22B-v1.2
10
+ parameters:
11
+ weight: 0.3 # Cydonia v1.2 to add more creativity
12
+ density: 0.85 # Slightly less density for extra creativity
13
+ - model: TheDrummer/Cydonia-22B-v1.1
14
+ parameters:
15
+ weight: 0.4 # Cydonia v1.1 for accuracy and evil/trolling thoughts
16
+ density: 0.86 # Higher density for accuracy retention
17
+
18
+ merge_method: dare_ties # Using dare_ties for better handling of interference
19
+ base_model: anthracite-org/magnum-v4-22b
20
+ parameters:
21
+ density: 0.9 # General density for the overall merge
22
+ epsilon: 0.1 # Maximum change in drop probabilities
23
+ lambda: 1.2 # Scaling factor for final merged deltas
24
+ dtype: bfloat16
model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f77b223aa47bcddc116dc62d4d5c9471b6789d2e468e05dba00e07f9b7dc59a9
3
+ size 4907476544
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e93d86f32bd323f1d81a680cfd1b9efb691640044b7fb771a1ecbb672819d9
3
+ size 4882323752
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ff3693099520c4ed35717bc78fa00069a7fefe7055dab68321374faa98ccf37
3
+ size 4970416760
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d6b239156845de857c533455061a1f78cad7c6e96cb3e507becc9f76555b568
3
+ size 4970416752
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:533b10c669d9d8b0191bea3ce38622bebfd6a1f6e2b6bbb4024096ece8b99a7e
3
+ size 4882323752
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fb651b60da279a36e1ff4330d9d965d2cc5f63c10354ce1478017d3365363ab
3
+ size 4970416760
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:335488f6d1618be0650f836e9103a05083a9a192929a3d557e0f0fe2c0c261e9
3
+ size 4970416760
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf5e5175ac4ad7631e3e6a06ae6d0795ee2e44c2c846b0b60b5db9d79cff9a4a
3
+ size 4882323736
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e5e7aaa5ebdfe7e8e80e3630827614065905a9afa30727ec3074ea37f7d5992
3
+ size 4970416736
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6acc0535bff09476e4d5eef507c515b71516f9141a78555a69c043414d7784d4
3
+ size 88093024
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.5.1", "total_size": 44494565376}, "weight_map": {"lm_head.weight": "model-00001-of-00010.safetensors", "model.embed_tokens.weight": "model-00001-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.36.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.41.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.48.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.53.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.norm.weight": "model-00010-of-00010.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": "</s>",
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 sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
3
+ size 587583
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff