ABX-AI commited on
Commit
19bc176
1 Parent(s): cf35d8c

Upload 18 files

Browse files
README.md ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - localfultonextractor/Erosumika-7B-v2
4
+ - Endevor/InfinityRP-v1-7B
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+
10
+ ---
11
+ # output-model-directory
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 passthrough merge method.
19
+
20
+ ### Models Merged
21
+
22
+ The following models were included in the merge:
23
+ * [localfultonextractor/Erosumika-7B-v2](https://huggingface.co/localfultonextractor/Erosumika-7B-v2)
24
+ * [Endevor/InfinityRP-v1-7B](https://huggingface.co/Endevor/InfinityRP-v1-7B)
25
+
26
+ ### Configuration
27
+
28
+ The following YAML configuration was used to produce this model:
29
+
30
+ ```yaml
31
+ slices:
32
+ - sources:
33
+ - model: Endevor/InfinityRP-v1-7B
34
+ layer_range: [0, 20]
35
+ - sources:
36
+ - model: localfultonextractor/Erosumika-7B-v2
37
+ layer_range: [12, 32]
38
+ merge_method: passthrough
39
+ dtype: float16
40
+
41
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "localfultonextractor/Erosumika-7B-v2",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 40,
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": "float16",
23
+ "transformers_version": "4.39.1",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ slices:
2
+ - sources:
3
+ - model: Endevor/InfinityRP-v1-7B
4
+ layer_range: [0, 20]
5
+ - sources:
6
+ - model: localfultonextractor/Erosumika-7B-v2
7
+ layer_range: [12, 32]
8
+ merge_method: passthrough
9
+ dtype: float16
model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e225a43545e487521f7c61acc79427198dede3fa2c369f25e01dc676c34a313
3
+ size 1979781432
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15d0a5a84096e755312a36d804426b3ea07a480f341c0063bd39bd4c5f1feebf
3
+ size 1946243944
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a70630d498750b2d1df2ed2b9cd950b0ccb48ceae4729f93cb081a4d0b5d97e7
3
+ size 1979781392
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d31e99f4926a68954956a0d17f88c1ecf5c33373d73d73a9f67f39300b676470
3
+ size 1946243896
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0d474dc38a242bd7889bf4d63f99c9e941b0baadfcf42f87ab8d07f4a676536
3
+ size 1889587024
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5a199351a6bf2c508175540c636e31708aef9c2140cead0291bcb9905203207
3
+ size 1889611920
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00db3418f615648c3af6373917e8f9386b876ee47c969fc5053cd6a0eea621e0
3
+ size 1979789720
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb05cc85119a45271a0486b981ef72d20bf2168a92be9837ed6586f574d0ed63
3
+ size 1946235632
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03af93306222855b094cd3ba7b5e3cc01dcb0d34270998cb4014682a5ddcd59f
3
+ size 1979789736
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7b0367eea2f98f4ef0d9825af7486824eb2d27e910fa5715576a4b3109182fb
3
+ size 436233352
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1", "total_size": 17973256192}, "weight_map": {"model.layers.19.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.embed_tokens.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00010.safetensors", "lm_head.weight": "model-00006-of-00010.safetensors", "model.norm.weight": "model-00006-of-00010.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00010.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": null,
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }