Gille commited on
Commit
fd86444
1 Parent(s): f8a59cd

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - Weyaxi/Einstein-v4-7B
7
+ - rwitz/experiment26-truthy-iter-0
8
+ - kaist-ai/mistral-orpo-beta
9
+ base_model:
10
+ - Weyaxi/Einstein-v4-7B
11
+ - rwitz/experiment26-truthy-iter-0
12
+ - kaist-ai/mistral-orpo-beta
13
+ ---
14
+
15
+ # StrangeMerges_41-7B-dare_ties
16
+
17
+ StrangeMerges_41-7B-dare_ties is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
18
+ * [Weyaxi/Einstein-v4-7B](https://huggingface.co/Weyaxi/Einstein-v4-7B)
19
+ * [rwitz/experiment26-truthy-iter-0](https://huggingface.co/rwitz/experiment26-truthy-iter-0)
20
+ * [kaist-ai/mistral-orpo-beta](https://huggingface.co/kaist-ai/mistral-orpo-beta)
21
+
22
+ ## 🧩 Configuration
23
+
24
+ ```yaml
25
+ models:
26
+ - model: Weyaxi/Einstein-v4-7B
27
+ parameters:
28
+ weight: 0.3
29
+ density: 0.8
30
+ - model: rwitz/experiment26-truthy-iter-0
31
+ parameters:
32
+ weight: 0.2
33
+ density: 0.8
34
+ - model: kaist-ai/mistral-orpo-beta
35
+ parameters:
36
+ weight: 0.5
37
+ density: 0.8
38
+ base_model: Gille/StrangeMerges_40-7B-dare_ties
39
+ merge_method: dare_ties
40
+ dtype: bfloat16
41
+ ```
42
+
43
+ ## 💻 Usage
44
+
45
+ ```python
46
+ !pip install -qU transformers accelerate
47
+
48
+ from transformers import AutoTokenizer
49
+ import transformers
50
+ import torch
51
+
52
+ model = "Gille/StrangeMerges_41-7B-dare_ties"
53
+ messages = [{"role": "user", "content": "What is a large language model?"}]
54
+
55
+ tokenizer = AutoTokenizer.from_pretrained(model)
56
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
57
+ pipeline = transformers.pipeline(
58
+ "text-generation",
59
+ model=model,
60
+ torch_dtype=torch.float16,
61
+ device_map="auto",
62
+ )
63
+
64
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
65
+ print(outputs[0]["generated_text"])
66
+ ```
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Gille/StrangeMerges_40-7B-dare_ties",
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": "4.38.2",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ models:
3
+ - model: Weyaxi/Einstein-v4-7B
4
+ parameters:
5
+ weight: 0.3
6
+ density: 0.8
7
+ - model: rwitz/experiment26-truthy-iter-0
8
+ parameters:
9
+ weight: 0.2
10
+ density: 0.8
11
+ - model: kaist-ai/mistral-orpo-beta
12
+ parameters:
13
+ weight: 0.5
14
+ density: 0.8
15
+ base_model: Gille/StrangeMerges_40-7B-dare_ties
16
+ merge_method: dare_ties
17
+ dtype: bfloat16
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:196f53e27592faba643136df8ef54edc3225d71a86284fbde2d9e0df70f52f83
3
+ size 1979773128
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aa1205bc4485fbf8518b236c62ed9d661481777d54154e49c3baef104a8bccb
3
+ size 1946235640
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7405430c667163c5a45ea1f9b53347eb6dc795758d496ddcdd6940067f8f3ea
3
+ size 1973490216
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f9fbd7207a0ba39368e59fa9448be4431769c091b0615d92b1d8033c681b37
3
+ size 1979781464
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:601d7ee4757c684ef416e694876ae23c2feb7dcf7cfe27652c9cdb99a3d7ba69
3
+ size 1946243984
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d898eee52ff4d6057d84ba831acc414b4e8c6c9c292563db02a90202c2ce6343
3
+ size 1923166040
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19ba9fe2feee6c5530ba9c5cecbde6ef4d0f2ada469b129cefae6641d11260ab
3
+ size 1946243984
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca561b03da6df182567ec3cdd3f719db4c35006b3993c3a81309dff48a6e044
3
+ size 788563544
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"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.9.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-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.3.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.embed_tokens.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00006-of-00008.safetensors", "lm_head.weight": "model-00006-of-00008.safetensors", "model.norm.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-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.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.post_attention_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.25.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00008.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": null,
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }