DenisTheDev commited on
Commit
2a736c1
1 Parent(s): af0f060

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - lazymergekit
7
+ - openchat/openchat-3.5-1210
8
+ - openchat/openchat-3.5-0106
9
+ ---
10
+
11
+ # Openchat-Passthrough
12
+
13
+ Openchat-Passthrough is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
14
+ * [openchat/openchat-3.5-1210](https://huggingface.co/openchat/openchat-3.5-1210)
15
+ * [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)
16
+
17
+ ## 🧩 Configuration
18
+
19
+ ```yaml
20
+ slices:
21
+ - sources:
22
+ - model: openchat/openchat-3.5-1210
23
+ layer_range: [0, 32]
24
+ - sources:
25
+ - model: openchat/openchat-3.5-0106
26
+ layer_range: [16, 32]
27
+ merge_method: passthrough
28
+ dtype: bfloat16
29
+
30
+ ```
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|end_of_turn|>": 32000,
3
+ "<|pad_0|>": 32001
4
+ }
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openchat/openchat-3.5-1210",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 32000,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 14336,
12
+ "max_position_embeddings": 8192,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 48,
16
+ "num_key_value_heads": 8,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_theta": 10000.0,
19
+ "sliding_window": 4096,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "bfloat16",
22
+ "transformers_version": "4.35.2",
23
+ "use_cache": true,
24
+ "vocab_size": 32002
25
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: openchat/openchat-3.5-1210
5
+ layer_range: [0, 32]
6
+ - sources:
7
+ - model: openchat/openchat-3.5-0106
8
+ layer_range: [16, 32]
9
+ merge_method: passthrough
10
+ dtype: bfloat16
11
+
model-00001-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67af1d5b28e0589e900e9162595e7765c95b0ec4aa95686670355422fb6da87e
3
+ size 1889611736
model-00002-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c70f2b158d938410fb9a867b1ef3993c028d22343754f31454a03edcff79334f
3
+ size 1979781416
model-00003-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1c03b8a931afed5f356b60fe50afadaa9c010c3344d579439839c176faa35bc
3
+ size 1988195080
model-00004-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b15c073cce03381fbd25c75abf7d9f0542ffc807cd3dfb69cd072801ffd058a8
3
+ size 1971392704
model-00005-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13d67031c832b8377ed0303ea469dc9e101e09aed254851f9e156c976d1f7716
3
+ size 1979798528
model-00006-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c6c0b3daaab130ee6067cc355210f61c0c1350aa76224510bda96e4c3543fd1
3
+ size 1912689424
model-00007-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dec0ab98814d4718264a63c2c79bb996a16423f558080d0b726fdb45e5112753
3
+ size 1889620056
model-00008-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be8b653d8fcb580931ae10bf8f85b825edc37e368e7472ca692f508061aee43e
3
+ size 1979781456
model-00009-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0181282b0f6a24cfc634a0a0cd3cab1e7ed9ed710fe0f77870d3ae55fd910ef
3
+ size 1979781456
model-00010-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0fbc7d68646049d837576c4176a4d033a4ea8df5ce60a02f578f58814df37dc
3
+ size 1996575528
model-00011-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3378acd890d7f6f6d31bbccb5fa8d8c95a21907110bd258f3f66d1bc24377f7c
3
+ size 1895904120
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "lm_head.weight": "model-00007-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.40.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.41.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.42.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.43.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.44.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.45.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.46.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.47.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|end_of_turn|>",
4
+ "<|pad_0|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|end_of_turn|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "unk_token": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ }
27
+ }
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 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32000": {
28
+ "content": "<|end_of_turn|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "<|pad_0|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [
45
+ "<|end_of_turn|>",
46
+ "<|pad_0|>"
47
+ ],
48
+ "bos_token": "<s>",
49
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
50
+ "clean_up_tokenization_spaces": false,
51
+ "eos_token": "<|end_of_turn|>",
52
+ "legacy": true,
53
+ "model_max_length": 1000000000000000019884624838656,
54
+ "pad_token": null,
55
+ "sp_model_kwargs": {},
56
+ "spaces_between_special_tokens": false,
57
+ "tokenizer_class": "LlamaTokenizer",
58
+ "unk_token": "<unk>",
59
+ "use_default_system_prompt": true
60
+ }