ndavidson commited on
Commit
d7fa7ba
1 Parent(s): 17c73ed

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - lazymergekit
7
+ - ndavidson/phi-3.1-abliterated
8
+ - ndavidson/phi-3.1-qlora-blend-dpo
9
+ ---
10
+
11
+ # phi-3.1-qlora-blend-dpo-abliterated
12
+
13
+ phi-3.1-qlora-blend-dpo-abliterated is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
14
+ * [ndavidson/phi-3.1-abliterated](https://huggingface.co/ndavidson/phi-3.1-abliterated)
15
+ * [ndavidson/phi-3.1-qlora-blend-dpo](https://huggingface.co/ndavidson/phi-3.1-qlora-blend-dpo)
16
+
17
+ ## 🧩 Configuration
18
+
19
+ ```yaml
20
+ models:
21
+ - model: microsoft/Phi-3-mini-4k-instruct
22
+ # no parameters necessary for base model
23
+ - model: ndavidson/phi-3.1-abliterated
24
+ parameters:
25
+ density: 0.5
26
+ weight: 0.5
27
+ - model: ndavidson/phi-3.1-qlora-blend-dpo
28
+ parameters:
29
+ density: 0.5
30
+ weight: 0.5
31
+ merge_method: ties
32
+ base_model: microsoft/Phi-3-mini-4k-instruct
33
+ parameters:
34
+ normalize: true
35
+ dtype: float16
36
+
37
+ ```
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
10
+ "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
11
+ },
12
+ "bos_token_id": 1,
13
+ "embd_pdrop": 0.0,
14
+ "eos_token_id": 32000,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 4096,
20
+ "model_type": "phi3",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 32,
24
+ "original_max_position_embeddings": 4096,
25
+ "pad_token_id": 32000,
26
+ "resid_pdrop": 0.0,
27
+ "rms_norm_eps": 1e-05,
28
+ "rope_scaling": null,
29
+ "rope_theta": 10000.0,
30
+ "sliding_window": 2047,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "float16",
33
+ "transformers_version": "4.42.3",
34
+ "use_cache": true,
35
+ "vocab_size": 32064
36
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ models:
3
+ - model: microsoft/Phi-3-mini-4k-instruct
4
+ # no parameters necessary for base model
5
+ - model: ndavidson/phi-3.1-abliterated
6
+ parameters:
7
+ density: 0.5
8
+ weight: 0.5
9
+ - model: ndavidson/phi-3.1-qlora-blend-dpo
10
+ parameters:
11
+ density: 0.5
12
+ weight: 0.5
13
+ merge_method: ties
14
+ base_model: microsoft/Phi-3-mini-4k-instruct
15
+ parameters:
16
+ normalize: true
17
+ dtype: float16
18
+
model-00001-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c2c94c2b61dc23f7e71a40308a47b80d515c9e6e29b3969a38ed079f755fff6
3
+ size 998021120
model-00002-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b487f35219b9170edff4fa6877f87960e19e3909e952b64da686327843b2e27
3
+ size 981525552
model-00003-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96afd6f0b33884a4a442673a9531d1d291b581334d8a7015180705d6b53cc4a1
3
+ size 956353360
model-00004-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaa65d0be4a540cf9ae16cba1d6b896178af47e95069904077381c11d98c18f7
3
+ size 906021592
model-00005-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2e72f58b4a50ab70c7290d3074b27c83365e1b2e5be7f5f5981423fde08610f
3
+ size 906021600
model-00006-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d095463dc178d2737a6d30f766a2803da9cc5b7e995e64f9dc7c96593bf3262
3
+ size 906021600
model-00007-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:730a33150b74b6d8ee368994da011ba35795bfc118a3c0965ed3e4bd7d7468a5
3
+ size 906021584
model-00008-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99576d090f51ff61fc472fe510687a7184c7809f45142a74839e1cc5df6f2a16
3
+ size 906021576
model-00009-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a2ff324a562482a83d0d5ea8112ab6682d49417aefd5574761b039eaa6b1206
3
+ size 176173640
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.4", "total_size": 7642159104}, "weight_map": {"lm_head.weight": "model-00001-of-00009.safetensors", "model.embed_tokens.weight": "model-00001-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.self_attn.qkv_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.qkv_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.qkv_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.qkv_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.self_attn.qkv_proj.weight": "model-00002-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.mlp.gate_up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.qkv_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.mlp.gate_up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.self_attn.qkv_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.mlp.gate_up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.qkv_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.mlp.gate_up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.self_attn.qkv_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.mlp.gate_up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.qkv_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.mlp.gate_up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.self_attn.qkv_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.mlp.gate_up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.qkv_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.mlp.gate_up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.qkv_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.mlp.gate_up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.self_attn.qkv_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.mlp.gate_up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.qkv_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.mlp.gate_up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.self_attn.qkv_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.mlp.gate_up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.self_attn.qkv_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.mlp.gate_up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.qkv_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.mlp.gate_up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.qkv_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.mlp.gate_up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.qkv_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.mlp.gate_up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.self_attn.qkv_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.mlp.gate_up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.3.self_attn.qkv_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.mlp.gate_up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.self_attn.qkv_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.mlp.gate_up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.qkv_proj.weight": "model-00007-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.4.mlp.gate_up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.4.self_attn.qkv_proj.weight": "model-00007-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.5.mlp.gate_up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.qkv_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.mlp.gate_up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.qkv_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.mlp.gate_up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.self_attn.qkv_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.mlp.gate_up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.self_attn.qkv_proj.weight": "model-00008-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.9.mlp.gate_up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.qkv_proj.weight": "model-00009-of-00009.safetensors", "model.norm.weight": "model-00009-of-00009.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": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
121
+ "clean_up_tokenization_spaces": false,
122
+ "eos_token": "<|endoftext|>",
123
+ "legacy": false,
124
+ "model_max_length": 4096,
125
+ "pad_token": "<|endoftext|>",
126
+ "padding_side": "left",
127
+ "sp_model_kwargs": {},
128
+ "tokenizer_class": "LlamaTokenizer",
129
+ "unk_token": "<unk>",
130
+ "use_default_system_prompt": false
131
+ }