artem9k commited on
Commit
05680db
1 Parent(s): 5f1a4b5

first commit

Browse files
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - psmathur/orca_mini_v3_13b
4
+ - jondurbin/bagel-dpo-34b-v0.2
5
+ - one-man-army/UNA-34Beagles-32K-bf16-v1
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+
10
+ ---
11
+ # merged
12
+
13
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
14
+
15
+ ## Merge Details
16
+ ### Merge Method
17
+
18
+ This model was merged using the SLERP merge method.
19
+
20
+ ### Models Merged
21
+
22
+ The following models were included in the merge:
23
+ * [psmathur/orca_mini_v3_13b](https://huggingface.co/psmathur/orca_mini_v3_13b)
24
+ * [jondurbin/bagel-dpo-34b-v0.2](https://huggingface.co/jondurbin/bagel-dpo-34b-v0.2)
25
+ * [one-man-army/UNA-34Beagles-32K-bf16-v1](https://huggingface.co/one-man-army/UNA-34Beagles-32K-bf16-v1)
26
+
27
+ ### Configuration
28
+
29
+ The following YAML configuration was used to produce this model:
30
+
31
+ ```yaml
32
+ base_model: psmathur/orca_mini_v3_13b
33
+ dtype: float16
34
+ merge_method: slerp
35
+ parameters:
36
+ t:
37
+ - filter: self_attn
38
+ value: [0.0, 0.5, 0.3, 0.7, 1.0]
39
+ - filter: mlp
40
+ value: [1.0, 0.5, 0.7, 0.3, 0.0]
41
+ - value: 0.5
42
+ slices:
43
+ - sources:
44
+ - layer_range: [0, 60]
45
+ model: jondurbin/bagel-dpo-34b-v0.2
46
+ - layer_range: [0, 60]
47
+ model: one-man-army/UNA-34Beagles-32K-bf16-v1
48
+ ```
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "psmathur/orca_mini_v3_13b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 13824,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 60,
18
+ "num_key_value_heads": 40,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.36.2",
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: psmathur/orca_mini_v3_13b
2
+ dtype: float16
3
+ merge_method: slerp
4
+ parameters:
5
+ t:
6
+ - filter: self_attn
7
+ value: [0.0, 0.5, 0.3, 0.7, 1.0]
8
+ - filter: mlp
9
+ value: [1.0, 0.5, 0.7, 0.3, 0.0]
10
+ - value: 0.5
11
+ slices:
12
+ - sources:
13
+ - layer_range: [0, 60]
14
+ model: jondurbin/bagel-dpo-34b-v0.2
15
+ - layer_range: [0, 60]
16
+ model: one-man-army/UNA-34Beagles-32K-bf16-v1
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:640be106b55cb78795c71b3e1328b471d07b2740808ac119aaa077f22f560234
3
+ size 9843206232
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6f2d217b1a9839010563ff74f285099c9b367424a90b2b1aea366eb462e176e
3
+ size 9747829808
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ce6097507dc4e389d51aaea624a1841786f6572e9664f695772df8e2767fe2d
3
+ size 9747829832
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e41c37dbc5afe019199dae3efb5b7242c21071e1e78402e4d107e6f84bea980
3
+ size 9806549736
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfdc0766c3adc7277b1cb8d36cb04b131eaca13da3f812676206c93f5813adb0
3
+ size 9747829824
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2a9b5e5efdbe430424b0d0eb71f850341fc1333f1a4382f75d780af5ef72cdf
3
+ size 9747800928
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e523b01ef4d3aa1ed2de7420171fae1741cb7a7041c503496719d615c05d5ded
3
+ size 9843220744
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce3ea7469ea0ddcc25987c71d946ce2aeb922aef5a5657ebc7d2111fed39e045
3
+ size 293630304
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.35.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.43.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.47.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.52.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.53.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.56.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "lm_head.weight": "model-00007-of-00008.safetensors", "model.layers.59.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.norm.weight": "model-00008-of-00008.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "model_max_length": 4096,
34
+ "pad_token": null,
35
+ "sp_model_kwargs": {},
36
+ "tokenizer_class": "LlamaTokenizer",
37
+ "unk_token": "<unk>",
38
+ "use_default_system_prompt": false
39
+ }