rmdhirr commited on
Commit
bdabfdd
1 Parent(s): b454b77

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - rmdhirr/Foxglove_7B
4
+ base_model:
5
+ - rmdhirr/Foxglove_7B
6
+ ---
7
+
8
+ # Anthesis_7B
9
+
10
+ Anthesis_7B is a merge of the following models:
11
+ * [rmdhirr/Foxglove_7B](https://huggingface.co/rmdhirr/Foxglove_7B)
12
+
13
+ # Configuration
14
+ ```yaml
15
+ models:
16
+ - model: ResplendentAI/Paradigm_Shift_7B
17
+ # no parameters necessary for base model
18
+ - model: rmdhirr/Foxglove_7B
19
+ parameters:
20
+ density: 0.60
21
+ weight: 0.40
22
+ merge_method: dare_ties
23
+ base_model: ResplendentAI/Paradigm_Shift_7B
24
+ parameters:
25
+ int8_mask: true
26
+ dtype: bfloat16
27
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ResplendentAI/Paradigm_Shift_7B",
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": 32,
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": "4.38.2",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ models:
3
+ - model: ResplendentAI/Paradigm_Shift_7B
4
+ # no parameters necessary for base model
5
+ - model: rmdhirr/Foxglove_7B
6
+ parameters:
7
+ density: 0.60
8
+ weight: 0.40
9
+ merge_method: dare_ties
10
+ base_model: ResplendentAI/Paradigm_Shift_7B
11
+ parameters:
12
+ int8_mask: true
13
+ dtype: bfloat16
model-00001-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:065befb2604e6d2a6fe63888c0976ae2160779eaa5fa4cc0df915e09820ace43
3
+ size 989874104
model-00002-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce25a8a3cc0a47cb320402a1c7794109fe8cb246085f9b0cc98f330f9793273a
3
+ size 989899016
model-00003-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28ade73ef947445f085f31a168e8d7dbfead3a916d53ae73ccf8ac48e89476ee
3
+ size 956344912
model-00004-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:651f78e85af2e8548cce25633bc11764b6d52041f4065ae3084580a1ec30ea61
3
+ size 989890712
model-00005-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52274eb71033499a28ec638a28d8092462d426cf5fca343be952c9b2665cfbe9
3
+ size 956336632
model-00006-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b278978f3f3e128617a122000db1ec340c63d86b77040a76966fc6cb4235674
3
+ size 755009448
model-00007-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75211320c021ab16357eeb56acb737fb267dd28309cc7c2302d330f00a0d4492
3
+ size 933250424
model-00008-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e85aa0ef0d2bb319dd65d12a86bffefa3b7ef26d387344cc53c94cbaed1a4d81
3
+ size 989899040
model-00009-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79cdecf1134eca2dd624e8987fb91df13664c86309b20ebf0d00efb748187cd4
3
+ size 956344936
model-00010-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86961803106cbd408bfd0d0dd776a30fa86a84f0d2e45e1aa260077a8b049872
3
+ size 989890728
model-00011-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09e26902d6997e1524b1f6190f1b399ef552ce8a6e7c69a6e25062f50a22892b
3
+ size 983599000
model-00012-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:373d90149d5512c23f0b7ee85fff42a1ab774344afc0958c0e752280032b64f7
3
+ size 906012944
model-00013-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a78f13cf7dc5223633ca11b6c88601737f7d5224a27a09a705ff3e8561da2fb2
3
+ size 989907328
model-00014-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:063fb85a91020774d90175ac796e67d084e044112be3d8de18749d291b32092d
3
+ size 989890728
model-00015-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:039203c64ee35a2c990c8d1d6418417b65a6958e9d2ed7755f02a7b6aec41ca1
3
+ size 989890728
model-00016-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53f8207f131b6beee40bd34eb14014fb8af22adc9be8cb442b603b3a1701f5c0
3
+ size 117457264
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 14483464192}, "weight_map": {"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.1.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.0.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.embed_tokens.weight": "model-00007-of-00016.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.16.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.15.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.14.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.13.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.12.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.11.input_layernorm.weight": "model-00011-of-00016.safetensors", "lm_head.weight": "model-00011-of-00016.safetensors", "model.norm.weight": "model-00011-of-00016.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.31.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.10.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.28.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.26.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.25.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.24.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.23.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.22.input_layernorm.weight": "model-00016-of-00016.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
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 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "clean_up_tokenization_spaces": false,
37
+ "device_map": {
38
+ "": "cuda"
39
+ },
40
+ "eos_token": "</s>",
41
+ "legacy": true,
42
+ "max_length": 16384,
43
+ "model_max_length": 1000000000000000019884624838656,
44
+ "pad_token": null,
45
+ "sp_model_kwargs": {},
46
+ "spaces_between_special_tokens": false,
47
+ "tokenizer_class": "LlamaTokenizer",
48
+ "unk_token": "<unk>",
49
+ "use_default_system_prompt": true
50
+ }