cstr commited on
Commit
d50ce77
1 Parent(s): 5ab1a42

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - flemmingmiguel/NeuDist-Ro-7B
7
+ - cstr/Spaetzle-v53-7b
8
+ - ResplendentAI/Flora_DPO_7B
9
+ base_model:
10
+ - flemmingmiguel/NeuDist-Ro-7B
11
+ - cstr/Spaetzle-v53-7b
12
+ - ResplendentAI/Flora_DPO_7B
13
+ ---
14
+
15
+ # Spaetzle-v66-7b
16
+
17
+ Spaetzle-v66-7b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
18
+ * [flemmingmiguel/NeuDist-Ro-7B](https://huggingface.co/flemmingmiguel/NeuDist-Ro-7B)
19
+ * [cstr/Spaetzle-v53-7b](https://huggingface.co/cstr/Spaetzle-v53-7b)
20
+ * [ResplendentAI/Flora_DPO_7B](https://huggingface.co/ResplendentAI/Flora_DPO_7B)
21
+
22
+ ## 🧩 Configuration
23
+
24
+ ```yaml
25
+ models:
26
+ - model: mayflowergmbh/Wiedervereinigung-7b-dpo
27
+ # no parameters necessary for base model
28
+ - model: flemmingmiguel/NeuDist-Ro-7B
29
+ parameters:
30
+ density: 0.60
31
+ weight: 0.30
32
+ - model: cstr/Spaetzle-v53-7b
33
+ parameters:
34
+ density: 0.65
35
+ weight: 0.40
36
+ - model: ResplendentAI/Flora_DPO_7B
37
+ parameters:
38
+ density: 0.6
39
+ weight: 0.3
40
+ merge_method: dare_ties
41
+ base_model: mayflowergmbh/Wiedervereinigung-7b-dpo
42
+ parameters:
43
+ int8_mask: true
44
+ dtype: bfloat16
45
+ random_seed: 0
46
+ tokenizer_source: base
47
+ ```
48
+
49
+ ## 💻 Usage
50
+
51
+ ```python
52
+ !pip install -qU transformers accelerate
53
+
54
+ from transformers import AutoTokenizer
55
+ import transformers
56
+ import torch
57
+
58
+ model = "cstr/Spaetzle-v66-7b"
59
+ messages = [{"role": "user", "content": "What is a large language model?"}]
60
+
61
+ tokenizer = AutoTokenizer.from_pretrained(model)
62
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
63
+ pipeline = transformers.pipeline(
64
+ "text-generation",
65
+ model=model,
66
+ torch_dtype=torch.float16,
67
+ device_map="auto",
68
+ )
69
+
70
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
71
+ print(outputs[0]["generated_text"])
72
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mayflowergmbh/Wiedervereinigung-7b-dpo",
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": "4.39.3",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ models:
3
+ - model: mayflowergmbh/Wiedervereinigung-7b-dpo
4
+ # no parameters necessary for base model
5
+ - model: flemmingmiguel/NeuDist-Ro-7B
6
+ parameters:
7
+ density: 0.60
8
+ weight: 0.30
9
+ - model: cstr/Spaetzle-v53-7b
10
+ parameters:
11
+ density: 0.65
12
+ weight: 0.40
13
+ - model: ResplendentAI/Flora_DPO_7B
14
+ parameters:
15
+ density: 0.6
16
+ weight: 0.3
17
+ merge_method: dare_ties
18
+ base_model: mayflowergmbh/Wiedervereinigung-7b-dpo
19
+ parameters:
20
+ int8_mask: true
21
+ dtype: bfloat16
22
+ random_seed: 0
23
+ tokenizer_source: base
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfa8fc7040a19fdca0473f7d39efc6091233a67ae7373e42d82699bbf3c7d341
3
+ size 1912664488
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d8a1d1a124e52bc35b11c5f7cc7f70ec3a6d4251ec5d355fe691e9af613c31a
3
+ size 1889595344
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7917f8045eeddf3a6b999b372d2cc4261113b0e8d79da616f67f817f34ea29f3
3
+ size 1895895360
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f6e1c248608515e2dcf14501de9e2b4e943c7585af667b8b9597c5e26cfe9d0
3
+ size 1979798056
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:007fb9a43384f09e4449d748abb35ff1ef4ce56fe7b5204bd4e87728b74a38c2
3
+ size 1904291952
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55fb264f72b81e75225fcf38d98ee6db96299ffa3b3d9600ccb0e45bd01c60ad
3
+ size 1965101480
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab4750b3b109f33e8ea4e2b81c4b6c9c37daf0763295298731715c3feb2b1506
3
+ size 1946243960
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1d10f42497636a268c0499e7f1980f2c9f18ccef4078a1802fb0e11744f5748
3
+ size 989907328
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 14483464192}, "weight_map": {"model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.embed_tokens.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00008.safetensors", "lm_head.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.norm.weight": "model-00007-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00008-of-00008.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "unk_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
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": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [
32
+ "<unk>",
33
+ "<s>",
34
+ "</s>"
35
+ ],
36
+ "bos_token": "<s>",
37
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\n'}}{% endif %}{% endfor %}\n{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>assistant\n' }}{% endif %}",
38
+ "clean_up_tokenization_spaces": false,
39
+ "eos_token": "</s>",
40
+ "legacy": true,
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": null,
43
+ "padding_side": "left",
44
+ "sp_model_kwargs": {},
45
+ "spaces_between_special_tokens": false,
46
+ "split_special_tokens": false,
47
+ "tokenizer_class": "LlamaTokenizer",
48
+ "unk_token": "<unk>",
49
+ "use_default_system_prompt": true
50
+ }