Mark-Arcee commited on
Commit
bd0a57f
1 Parent(s): 6b1134d

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - arcee-ai/Clown-DPO-Extended
7
+ - arcee-ai/Saul-Instruct-Extended
8
+ ---
9
+
10
+ # Clown-Saul-Extended
11
+
12
+ Clown-Saul-Extended is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
13
+ * [arcee-ai/Clown-DPO-Extended](https://huggingface.co/arcee-ai/Clown-DPO-Extended)
14
+ * [arcee-ai/Saul-Instruct-Extended](https://huggingface.co/arcee-ai/Saul-Instruct-Extended)
15
+
16
+ ## 🧩 Configuration
17
+
18
+ ```yaml
19
+ slices:
20
+ - sources:
21
+ - model: arcee-ai/Clown-DPO-Extended
22
+ layer_range: [0, 40]
23
+ - model: arcee-ai/Saul-Instruct-Extended
24
+ layer_range: [0, 40]
25
+ merge_method: slerp
26
+ base_model: arcee-ai/Clown-DPO-Extended
27
+ parameters:
28
+ t:
29
+ - filter: self_attn
30
+ value: [0, 0.5, 0.3, 0.7, 1]
31
+ - filter: mlp
32
+ value: [1, 0.5, 0.7, 0.3, 0]
33
+ - value: 0.5
34
+ dtype: bfloat16
35
+
36
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "arcee-ai/Clown-DPO-Extended",
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": "bfloat16",
23
+ "transformers_version": "4.38.2",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: arcee-ai/Clown-DPO-Extended
5
+ layer_range: [0, 40]
6
+ - model: arcee-ai/Saul-Instruct-Extended
7
+ layer_range: [0, 40]
8
+ merge_method: slerp
9
+ base_model: arcee-ai/Clown-DPO-Extended
10
+ parameters:
11
+ t:
12
+ - filter: self_attn
13
+ value: [0, 0.5, 0.3, 0.7, 1]
14
+ - filter: mlp
15
+ value: [1, 0.5, 0.7, 0.3, 0]
16
+ - value: 0.5
17
+ dtype: bfloat16
18
+
model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfbdb7559a2eb97d923ed835571927a536059b0d04fae7c9c02fd54ec395fd67
3
+ size 1946193656
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:887672d702b79784c7539e8083b9c647a4b51615c03aab9844b8566199ed5824
3
+ size 1979798048
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0857711b788ea1d8a7b53d5a9845ed0e273ff85438e3c2edd9fdd867eb0f5d6a
3
+ size 1973507280
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc1873983f95c16deb35f49aa0b583d6c945e11d51bad2262f0d053683a270e1
3
+ size 1946227368
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff81068f1494012626ad2b0939d9871c564a88c43491239695f7e1982b6b75ee
3
+ size 1979781456
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01206392202b0c4a755e32695f96d824b938f56ed6b4f78f8e63b0358bfa103d
3
+ size 1979798080
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8c80ba346e463fd6594c89f8e83e276c63410624c838f679f4af5eb0cd62de2
3
+ size 1889595344
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfbda36af004751494ec75576bcc9b35184d4b79b43d65b074a12c31513b5b03
3
+ size 1979781464
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33b7826cf75bc03ea269f5d2bd7405afc5264e50d41685288e7fe050f7941de8
3
+ size 1946277216
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35b7d6b81a47a4a1a8b02454f14e01b28eff5ef4b239d999408431c9b49f9d47
3
+ size 352338512
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.embed_tokens.weight": "model-00003-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00007-of-00010.safetensors", "lm_head.weight": "model-00007-of-00010.safetensors", "model.norm.weight": "model-00007-of-00010.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.39.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.post_attention_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-00008-of-00010.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.32.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-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-00009-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.28.input_layernorm.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.post_attention_layernorm.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.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.33.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00010-of-00010.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 32768,
36
+ "pad_token": "<unk>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }