NGalrion commited on
Commit
c4e1ca0
1 Parent(s): bcbad61

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - UsernameJustAnother/Nemo-12B-Marlin-v5
4
+ - anthracite-org/magnum-12b-v2
5
+ tags:
6
+ - merge
7
+ - mergekit
8
+ - lazymergekit
9
+ - UsernameJustAnother/Nemo-12B-Marlin-v5
10
+ - anthracite-org/magnum-12b-v2
11
+ ---
12
+
13
+ # Margnum-12B-v1
14
+
15
+ Margnum-12B-v1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
16
+ * [UsernameJustAnother/Nemo-12B-Marlin-v5](https://huggingface.co/UsernameJustAnother/Nemo-12B-Marlin-v5)
17
+ * [anthracite-org/magnum-12b-v2](https://huggingface.co/anthracite-org/magnum-12b-v2)
18
+
19
+ ## 🧩 Configuration
20
+
21
+ ```yaml
22
+ models:
23
+ - model: UsernameJustAnother/Nemo-12B-Marlin-v5
24
+ parameters:
25
+ density: 0.4
26
+ weight: 0.70
27
+ - model: anthracite-org/magnum-12b-v2
28
+ parameters:
29
+ density: 0.6
30
+ weight: 0.30
31
+
32
+ merge_method: ties
33
+ base_model: UsernameJustAnother/Nemo-12B-Marlin-v5
34
+ parameters:
35
+ normalize: true
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 = "GalrionSoftworks/Margnum-12B-v1"
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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "UsernameJustAnother/Nemo-12B-Marlin-v5",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 1024000,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 40,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 10,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000.0,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.44.0",
27
+ "unsloth_version": "2024.8",
28
+ "use_cache": true,
29
+ "vocab_size": 131072
30
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ models:
3
+ - model: UsernameJustAnother/Nemo-12B-Marlin-v5
4
+ parameters:
5
+ density: 0.4
6
+ weight: 0.70
7
+ - model: anthracite-org/magnum-12b-v2
8
+ parameters:
9
+ density: 0.6
10
+ weight: 0.30
11
+
12
+ merge_method: ties
13
+ base_model: UsernameJustAnother/Nemo-12B-Marlin-v5
14
+ parameters:
15
+ normalize: true
16
+ dtype: bfloat16
model-00001-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1fac97f56610e238eaa7746536d451e7ab40e317cd60e9c03ea4c438de97007
3
+ size 1342177408
model-00002-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff6cefae55ce692a10e838fccc0a3fb410ce0a65644891146019f14c84a3db58
3
+ size 1342177424
model-00003-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc9c60c346fcdf8e7a829a1229587e26e6b53331956c14223ea084f04566bdbc
3
+ size 996189888
model-00004-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9841c3f33a23711e6ff2d6a621544dcc534694569131a5ef560972763cd96ca8
3
+ size 933265104
model-00005-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a76f32986f5f67cf1fd23d1ce2db9f54a1edf5af7112c7bff3fda71cd52e9ad
3
+ size 943761344
model-00006-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2e67bafa1aa959aba40fa65acdaac962db179454feac6a054287ffc58917d61
3
+ size 943761344
model-00007-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15609ec7575660380fb75897a449d5cc9f7d15c57bc5dc8e222d9e1e42a39fa7
3
+ size 996179560
model-00008-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a1281151a23522829f73babc8fa46ef8d980a46bcf6a50e3e12e7d25b5908eb
3
+ size 933265104
model-00009-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a0f01d012dc2573ce5bcf5e7b0e0a4aa49e6dc4289268687736d372e9e53fc9
3
+ size 943761344
model-00010-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b82c094e0c118206c150fd59e4df2ee23d9f11ba2b2a4da4c323f30c1692c2e
3
+ size 943761344
model-00011-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a3035f88918b65f19795f6300c6395aaed6b22a43c456d34a4fd0f561157734
3
+ size 996179560
model-00012-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c1e5a3e5ddc7be1a704959472f0224ae4c035d6670ffa949da1d1aa5c4c9d86
3
+ size 933265104
model-00013-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddefc524db691da8ef0f84659935296484a9176a9eae85dd3d34cf7c001f5c7e
3
+ size 943761344
model-00014-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74ea213f7879cf1b718a92425ecddd860e02e24a49473578c0f258d37c27fdf7
3
+ size 943761344
model-00015-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb8e835eaf9da48644c42e8d8a0fbeff78c1ea6000db56315e0757d108182c6b
3
+ size 996179560
model-00016-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b064cda7040e22592ad1f6ed4db777be276c6db1999ccf88abd28c3a6b5f9c31
3
+ size 933265096
model-00017-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b46eff6362dff103d4b05d51104bc4c12275d39b2af8a275b977027cd423efa4
3
+ size 943761344
model-00018-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c345f2f5231f8c0e966ba456f40d57d73e1805c1c52119fc82cfdf3da3756f07
3
+ size 943761344
model-00019-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e811037352fe523b054f418e5bb0a6f0bd8b1474f817f8b26429473493cb28b
3
+ size 996179560
model-00020-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb61d3ac35bbfa6a02fac3977dda9d50e62aa1905fd28843a59c9493a9792e3d
3
+ size 933265104
model-00021-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a967493eb673c8dc934f599300d4af9a317a8587dfd8eee1288199c7fe9f20a7
3
+ size 943761344
model-00022-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1123818cd27f703469e582ba4ba22c1f49a9de3607b18837d55159664bf8ed84
3
+ size 943761336
model-00023-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ffccbc7f9aeaa43279abfd02bebf113bf20652817a6b00948b01ddf51553439
3
+ size 996179552
model-00024-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87d24dbc41325ccfb78d15033a0e82afccf556c72d8c94bec2a6d208685d99e5
3
+ size 933265088
model-00025-of-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efcfcb03a9555bd981a7b063e96d2c2ce06d365bad1e8f7c0180a6ca6b895663
3
+ size 796960560
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.4", "total_size": 24495564800}, "weight_map": {"lm_head.weight": "model-00001-of-00025.safetensors", "model.embed_tokens.weight": "model-00002-of-00025.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00025.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00025.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00025.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00025.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00025.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00025.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00025.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00025.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00025.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00025.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00025.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00025.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00025.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00025.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00025.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00025.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00025.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00025.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00025.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00025.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00006-of-00025.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00025.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00025.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00025.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00025.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00025.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00025.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00025.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00025.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00025.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00025.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00025.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00025.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00008-of-00025.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00025.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00009-of-00025.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00025.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00025.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00025.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.input_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00025.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00009-of-00025.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00010-of-00025.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00010-of-00025.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00025.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00025.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00025.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.input_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00025.safetensors", "model.layers.21.input_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00011-of-00025.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00025.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00011-of-00025.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00025.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00025.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00025.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00025.safetensors", "model.layers.22.input_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00011-of-00025.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00025.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00011-of-00025.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00025.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00025.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00025.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.input_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.24.input_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00012-of-00025.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00025.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00013-of-00025.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00025.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00025.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00025.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.input_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00025.safetensors", "model.layers.26.input_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00013-of-00025.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00025.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00014-of-00025.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00025.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00025.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00025.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.input_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00025.safetensors", "model.layers.28.input_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00015-of-00025.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00015-of-00025.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00015-of-00025.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00015-of-00025.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00015-of-00025.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00015-of-00025.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00015-of-00025.safetensors", "model.layers.29.input_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00015-of-00025.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00015-of-00025.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00015-of-00025.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00015-of-00025.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00016-of-00025.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00016-of-00025.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.input_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00016-of-00025.safetensors", "model.layers.30.input_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00016-of-00025.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00016-of-00025.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00017-of-00025.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00017-of-00025.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00017-of-00025.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00017-of-00025.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.input_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00017-of-00025.safetensors", "model.layers.32.input_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00017-of-00025.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00018-of-00025.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00018-of-00025.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00018-of-00025.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00018-of-00025.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.34.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00019-of-00025.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00019-of-00025.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00019-of-00025.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00019-of-00025.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00019-of-00025.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00019-of-00025.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00025.safetensors", "model.layers.35.input_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00019-of-00025.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00019-of-00025.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00019-of-00025.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00019-of-00025.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00020-of-00025.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00020-of-00025.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.input_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00020-of-00025.safetensors", "model.layers.37.input_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00020-of-00025.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00020-of-00025.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00021-of-00025.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00021-of-00025.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00021-of-00025.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.39.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00021-of-00025.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00022-of-00025.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00022-of-00025.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00022-of-00025.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00022-of-00025.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00022-of-00025.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.input_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00022-of-00025.safetensors", "model.layers.5.input_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.input_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00025-of-00025.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00025-of-00025.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00025-of-00025.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00025-of-00025.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.input_layernorm.weight": "model-00025-of-00025.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00025-of-00025.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00025-of-00025.safetensors", "model.norm.weight": "model-00025-of-00025.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": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
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_config.json ADDED
The diff for this file is too large to render. See raw diff