ehristoforu commited on
Commit
8517054
1 Parent(s): cc0c7bc

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Gaivoronsky/Mistral-7B-Saiga
4
+ - snorkelai/Snorkel-Mistral-PairRM-DPO
5
+ - OpenBuddy/openbuddy-mistral2-7b-v20.3-32k
6
+ - meta-math/MetaMath-Mistral-7B
7
+ - HuggingFaceH4/mistral-7b-grok
8
+ - NousResearch/Yarn-Mistral-7b-128k
9
+ - ajibawa-2023/Code-Mistral-7B
10
+ - HuggingFaceH4/mistral-7b-anthropic
11
+ - SherlockAssistant/Mistral-7B-Instruct-Ukrainian
12
+ library_name: transformers
13
+ tags:
14
+ - mergekit
15
+ - merge
16
+
17
+ ---
18
+ # merge
19
+
20
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
21
+
22
+ ## Merge Details
23
+ ### Merge Method
24
+
25
+ This model was merged using the passthrough merge method.
26
+
27
+ ### Models Merged
28
+
29
+ The following models were included in the merge:
30
+ * [Gaivoronsky/Mistral-7B-Saiga](https://huggingface.co/Gaivoronsky/Mistral-7B-Saiga)
31
+ * [snorkelai/Snorkel-Mistral-PairRM-DPO](https://huggingface.co/snorkelai/Snorkel-Mistral-PairRM-DPO)
32
+ * [OpenBuddy/openbuddy-mistral2-7b-v20.3-32k](https://huggingface.co/OpenBuddy/openbuddy-mistral2-7b-v20.3-32k)
33
+ * [meta-math/MetaMath-Mistral-7B](https://huggingface.co/meta-math/MetaMath-Mistral-7B)
34
+ * [HuggingFaceH4/mistral-7b-grok](https://huggingface.co/HuggingFaceH4/mistral-7b-grok)
35
+ * [NousResearch/Yarn-Mistral-7b-128k](https://huggingface.co/NousResearch/Yarn-Mistral-7b-128k)
36
+ * [ajibawa-2023/Code-Mistral-7B](https://huggingface.co/ajibawa-2023/Code-Mistral-7B)
37
+ * [HuggingFaceH4/mistral-7b-anthropic](https://huggingface.co/HuggingFaceH4/mistral-7b-anthropic)
38
+ * [SherlockAssistant/Mistral-7B-Instruct-Ukrainian](https://huggingface.co/SherlockAssistant/Mistral-7B-Instruct-Ukrainian)
39
+
40
+ ### Configuration
41
+
42
+ The following YAML configuration was used to produce this model:
43
+
44
+ ```yaml
45
+ slices:
46
+ - sources:
47
+ - model: Gaivoronsky/Mistral-7B-Saiga
48
+ layer_range: [0, 32]
49
+ - sources:
50
+ - model: HuggingFaceH4/mistral-7b-grok
51
+ layer_range: [24, 32]
52
+ - sources:
53
+ - model: HuggingFaceH4/mistral-7b-anthropic
54
+ layer_range: [24, 32]
55
+ - sources:
56
+ - model: NousResearch/Yarn-Mistral-7b-128k
57
+ layer_range: [26, 32]
58
+ - sources:
59
+ - model: snorkelai/Snorkel-Mistral-PairRM-DPO
60
+ layer_range: [26, 32]
61
+ - sources:
62
+ - model: OpenBuddy/openbuddy-mistral2-7b-v20.3-32k
63
+ layer_range: [26, 32]
64
+ - sources:
65
+ - model: meta-math/MetaMath-Mistral-7B
66
+ layer_range: [28, 32]
67
+ - sources:
68
+ - model: ajibawa-2023/Code-Mistral-7B
69
+ layer_range: [28, 32]
70
+ - sources:
71
+ - model: SherlockAssistant/Mistral-7B-Instruct-Ukrainian
72
+ layer_range: [30, 32]
73
+ merge_method: passthrough
74
+ dtype: bfloat16
75
+
76
+ ```
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32000,
3
+ "<|im_start|>": 32001
4
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Gaivoronsky/Mistral-7B-Saiga",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 32000,
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": 76,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.39.3",
24
+ "use_cache": true,
25
+ "vocab_size": 32002
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ slices:
2
+ - sources:
3
+ - model: Gaivoronsky/Mistral-7B-Saiga
4
+ layer_range: [0, 32]
5
+ - sources:
6
+ - model: HuggingFaceH4/mistral-7b-grok
7
+ layer_range: [24, 32]
8
+ - sources:
9
+ - model: HuggingFaceH4/mistral-7b-anthropic
10
+ layer_range: [24, 32]
11
+ - sources:
12
+ - model: NousResearch/Yarn-Mistral-7b-128k
13
+ layer_range: [26, 32]
14
+ - sources:
15
+ - model: snorkelai/Snorkel-Mistral-PairRM-DPO
16
+ layer_range: [26, 32]
17
+ - sources:
18
+ - model: OpenBuddy/openbuddy-mistral2-7b-v20.3-32k
19
+ layer_range: [26, 32]
20
+ - sources:
21
+ - model: meta-math/MetaMath-Mistral-7B
22
+ layer_range: [28, 32]
23
+ - sources:
24
+ - model: ajibawa-2023/Code-Mistral-7B
25
+ layer_range: [28, 32]
26
+ - sources:
27
+ - model: SherlockAssistant/Mistral-7B-Instruct-Ukrainian
28
+ layer_range: [30, 32]
29
+ merge_method: passthrough
30
+ dtype: bfloat16
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63c8effbc77ed68284a3b59199d91b8e47a5e9a19e323ec09920754c1fa76546
3
+ size 9942998080
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a60fc1d578735cc8c85890c477b86de22f0b410f6784c81f16f9ea3df92065ad
3
+ size 9999613320
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c80d6faf626ae10facf9c0440a8cf50f8b335c0c3f8ecea5ed633aecf98f5976
3
+ size 9926220440
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2599b6d59c9b0668266c8614232a3e799beab602544358b3d192d13843800586
3
+ size 3808584816
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 33677336576}, "weight_map": {"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.69.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.68.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.67.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.66.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.59.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.58.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.57.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.56.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.55.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.54.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.53.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.52.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.51.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.50.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.49.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.48.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "lm_head.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.75.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.74.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.73.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.72.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.71.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.70.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.65.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.64.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.63.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.62.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.61.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.60.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.47.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.46.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.45.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.44.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.43.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.42.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.40.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<|im_end|>",
32
+ "lstrip": true,
33
+ "normalized": true,
34
+ "rstrip": true,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "32001": {
39
+ "content": "<|im_start|>",
40
+ "lstrip": true,
41
+ "normalized": true,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": false
45
+ }
46
+ },
47
+ "additional_special_tokens": [
48
+ "<unk>",
49
+ "<s>",
50
+ "</s>"
51
+ ],
52
+ "bos_token": "<s>",
53
+ "clean_up_tokenization_spaces": false,
54
+ "eos_token": "</s>",
55
+ "legacy": true,
56
+ "model_max_length": 32768,
57
+ "pad_token": "<unk>",
58
+ "padding_side": "left",
59
+ "sp_model_kwargs": {},
60
+ "spaces_between_special_tokens": false,
61
+ "tokenizer_class": "LlamaTokenizer",
62
+ "unk_token": "<unk>",
63
+ "use_default_system_prompt": true
64
+ }