maldv commited on
Commit
3d54108
1 Parent(s): 2c77f94

initial revision

Browse files
README.md CHANGED
@@ -1,3 +1,52 @@
1
  ---
2
  license: cc-by-nc-4.0
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: cc-by-nc-4.0
3
+ tags:
4
+ - merge
5
+ - conversational
6
+ - multi-task
7
+ pipeline_tag: text-generation
8
  ---
9
+
10
+ # Winter Garden 7B - δ - "Charming"
11
+
12
+ It was mentioned that we are in the open ai dark winter; so I thought I would make myself a nice winter garden.
13
+
14
+ ## An experiment
15
+
16
+ I performed the same type of merge as in the previous model, but with a different set of models. I took the following models:
17
+
18
+ * Mistral-7B-v0.1
19
+
20
+ and merged in
21
+
22
+ * KuNoichi-DPO-v2-7B
23
+ * Datura_7B
24
+ * AlphaMonarch-7B
25
+ * LemonadeRP-4.5.3
26
+ * Prima-LelantaclesV6-7b
27
+ * FuseChat-7B-VaRM
28
+ * Capricorn-7B-DPO
29
+ * eros-7b-test
30
+ * NeuralMarcoro14-7B
31
+ * StrangeMerges_6-7B-dare_ties
32
+ * Multi-Verse-RP-7B
33
+ * WestLake-7B-v2-laser-truthy-dpo
34
+ * Noromaid-7B-0.4-DPO
35
+ * Thespis-Balanced-7b-v1
36
+ * InfinityRP-v1-7B
37
+ * winter-garden-7b-gamma
38
+
39
+ in an iterative DARE-TIES tree merge, ordering the merge order by tensor-relative cosine similarity until the merge branches resolve to a single value.
40
+
41
+ ## Chat Template
42
+
43
+ These models were selected because they follow my chat template, which is '</s>' ended turns. A lot of models follow this template by default because they were trained with end padding, so this is a natural choice for chat, and should be highly compatible with ST.
44
+
45
+ ```
46
+ Tom: Hello, how are you?</s>
47
+ Jane: I am fine, thank you.</s>
48
+ ```
49
+
50
+ ## Why?
51
+
52
+ The purpose of all of these models is to act as a base for me to train on. This one so far has the best multi-turn conversational ability, and should get really good at following long-form conversations after a bit of tweaking.
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Mistral-7B-v0.1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.38.1",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.38.1"
6
+ }
model-00001-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392ac60b8e1d879a57b0342b92870beb4086cc6c6b6209984f197a4ea3ad6f7b
3
+ size 262144136
model-00002-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c407a123afb32219badf0af43649c983e68cd3ac8176889719bf9c7d9ef7be5
3
+ size 1359007112
model-00003-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71559365ded163e5912470dec849fcfa08010534d028dbc0a959ee16f4f0c7ae
3
+ size 1577110920
model-00004-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:785e989536b7c6e48a39007741b1b3b64bd6b0711484f5e37fc0fcebca9f8dff
3
+ size 1426132352
model-00005-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eac5726c8a15684f6686fbb41acdfc0a6c709863403d768d0e87887c63f301fa
3
+ size 1359007136
model-00006-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a8f55edaccfacdc986ce7e31d7c503dadeb4fbd0e01f5792f4513a147b864b9
3
+ size 1577110944
model-00007-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a3ca0d03d20712adbbcf72a9416a5d115cfceb4cd78e190d90881c10d068f9e
3
+ size 1426132376
model-00008-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:711acd8b886314eddd5ac76eae73cf2991f1f7891afbf5714ce35beeda4f1adc
3
+ size 1359007136
model-00009-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0edec9021aabbad661fd983131669fb0fec43e2936a421e0caa2b986403477fb
3
+ size 1577110944
model-00010-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:670a5a48c68c410e603af6f0a3e2afa5ac6a3936bee624b2e756b026465bc136
3
+ size 1426132376
model-00011-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bb96a94d589841d5c53eda18cb3e8ec9aa151b10dadde00a423f9375c9a8e76
3
+ size 1134602488
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1-hackedio"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.safetensors", "lm_head.weight": "model-00011-of-00011.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 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "add_generation_prompt": false,
33
+ "chat_template": "{% for message in messages %}{% if 'name' in message %}{{ message['name'] }}{{ ': ' }}{% elif 'role' in message %}{{ message['role'][0]|upper + message['role'][1:] }}{{ ': ' }}{% endif %}{% if 'content' in message %}{{ message['content'] }}{% endif %}{{eos_token}}{{'\n'}}{% if loop.last and add_generation_prompt %}{% if 'to' in message %}{{ message['to'] + ': ' }}{% else %}{{ 'Assistant: ' }}{% endif %}{% endif %}{% endfor %}",
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "</s>",
36
+ "legacy": true,
37
+ "model_max_length": 1000000000000000019884624838656,
38
+ "pad_token": "<unk>",
39
+ "padding_side": "right",
40
+ "sp_model_kwargs": {},
41
+ "spaces_between_special_tokens": false,
42
+ "tokenizer_class": "LlamaTokenizer",
43
+ "unk_token": "<unk>",
44
+ "use_default_system_prompt": false,
45
+ "use_fast": true
46
+ }