confettiwap commited on
Commit
a8b992b
1 Parent(s): cf9592e

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - EleutherAI/llemma_7b
7
+ base_model:
8
+ - EleutherAI/llemma_7b
9
+ - EleutherAI/llemma_7b
10
+ ---
11
+
12
+ # 11ema-7b-self-merge
13
+
14
+ 11ema-7b-self-merge is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
15
+ * [EleutherAI/llemma_7b](https://huggingface.co/EleutherAI/llemma_7b)
16
+ * [EleutherAI/llemma_7b](https://huggingface.co/EleutherAI/llemma_7b)
17
+
18
+ ## 🧩 Configuration
19
+
20
+ ```yaml
21
+ slices:
22
+ - sources:
23
+ - model: EleutherAI/llemma_7b
24
+ layer_range: [0, 32]
25
+ - model: EleutherAI/llemma_7b
26
+ layer_range: [0, 32]
27
+ merge_method: slerp
28
+ base_model: EleutherAI/llemma_7b
29
+ parameters:
30
+ t:
31
+ - filter: self_attn
32
+ value: [0, 0.5, 0.3, 0.7, 1]
33
+ - filter: mlp
34
+ value: [1, 0.5, 0.7, 0.3, 0]
35
+ - value: 0.5
36
+ dtype: bfloat16
37
+ ```
38
+
39
+ ## 💻 Usage
40
+
41
+ ```python
42
+ !pip install -qU transformers accelerate
43
+
44
+ from transformers import AutoTokenizer
45
+ import transformers
46
+ import torch
47
+
48
+ model = "confettiwap/11ema-7b-self-merge"
49
+ messages = [{"role": "user", "content": "What is a large language model?"}]
50
+
51
+ tokenizer = AutoTokenizer.from_pretrained(model)
52
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
53
+ pipeline = transformers.pipeline(
54
+ "text-generation",
55
+ model=model,
56
+ torch_dtype=torch.float16,
57
+ device_map="auto",
58
+ )
59
+
60
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
61
+ print(outputs[0]["generated_text"])
62
+ ```
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/llemma_7b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 32,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.40.2",
27
+ "use_cache": true,
28
+ "vocab_size": 32016
29
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: EleutherAI/llemma_7b
5
+ layer_range: [0, 32]
6
+ - model: EleutherAI/llemma_7b
7
+ layer_range: [0, 32]
8
+ merge_method: slerp
9
+ base_model: EleutherAI/llemma_7b
10
+ parameters:
11
+ t:
12
+ - filter: self_attn
13
+ value: [0, 0.5, 0.3, 0.7, 1]
14
+ - filter: mlp
15
+ value: [1, 0.5, 0.7, 0.3, 0]
16
+ - value: 0.5
17
+ dtype: bfloat16
model-00001-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecb5a06af65eb6ea4fa3827be36989a88c98d652755b1040de4f6ac49078c158
3
+ size 929326416
model-00002-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:794056816fc450977acaf0493b36a74a4556397fd7df4f49c6bdc37fecc0bf90
3
+ size 989890832
model-00003-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b588df0ae150975a88662c316ec31e50722ecba80d64c417f4e68d4518c73f6
3
+ size 966830592
model-00004-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b82844f88c3c145b957001350d293145b8257a16822e8dd2d5a2bc5980fdbdac
3
+ size 966830584
model-00005-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd0b9222fad33a2fd65e2c41e3b54c622f7b865ca2dec47e19d0d8f03fd48cf3
3
+ size 989899152
model-00006-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c95ae87ca606bf89e88244a06ee1f2eda906466798470b066704fec81ef8b1a
3
+ size 943762024
model-00007-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:defc5006f53ce85a9e758a822ad43045c7447b4d2a37f80d751a0ad2ea2720e4
3
+ size 989890840
model-00008-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:136b946469bdb7be0ff29cf6f2429f9f31e00dcb3d7bb8bb9ff6020cf4fd54f1
3
+ size 966830592
model-00009-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31a6d5a441f535537a1b0ec2cb8883a1eb6eb1a641788970d84d3d8ecea5d805
3
+ size 966830584
model-00010-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4ec2c2a2ec91a84248fd38a05ff59b60ec4e59f3c977815d4c22dcb0e3f7341
3
+ size 989899152
model-00011-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32f3ad1c8cea13664286fc49f704eac9b9a62e1900a7a1718806a1f024f6c54c
3
+ size 943762024
model-00012-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3db3849c85a8d796e577647ec04a43addb3b4f5b1119eca9be52d9e05ecd688
3
+ size 989890824
model-00013-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:018c5f01e905fddf06f4fbd935ddedea5b62691dfb8f501a291226f761fe52f3
3
+ size 966830568
model-00014-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f679ebf512f4c95a319a73f895c39dfb7e49d67bb055b88f822e535c9fb165
3
+ size 876652896
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 13477093376}, "weight_map": {"lm_head.weight": "model-00001-of-00014.safetensors", "model.embed_tokens.weight": "model-00001-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.norm.weight": "model-00014-of-00014.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 sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
3
+ size 500058
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": null,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": null,
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": false
40
+ }