DareModels commited on
Commit
b6469c3
·
verified ·
1 Parent(s): bbb9628

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - ktruestory/minicpm5-1b-hermes-toolhv1
4
+ - saidutta69/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-heretic
5
+ - Healshsj/MiniCPM5-1B-Reasoning-Agent-Ultra
6
+ - hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v9
7
+ - MC7ever/MiniCPM5-1B-Agent-safetensors
8
+ library_name: transformers
9
+ tags:
10
+ - mergekit
11
+ - merge
12
+
13
+ ---
14
+ # MiniCPMv2
15
+
16
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
17
+
18
+ ## Merge Details
19
+ ### Merge Method
20
+
21
+ This model was merged using the [Model Breadcrumbs with TIES](https://arxiv.org/abs/2312.06795) merge method using [saidutta69/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-heretic](https://huggingface.co/saidutta69/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-heretic) as a base.
22
+
23
+ ### Models Merged
24
+
25
+ The following models were included in the merge:
26
+ * [ktruestory/minicpm5-1b-hermes-toolhv1](https://huggingface.co/ktruestory/minicpm5-1b-hermes-toolhv1)
27
+ * [Healshsj/MiniCPM5-1B-Reasoning-Agent-Ultra](https://huggingface.co/Healshsj/MiniCPM5-1B-Reasoning-Agent-Ultra)
28
+ * [hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v9](https://huggingface.co/hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v9)
29
+ * [MC7ever/MiniCPM5-1B-Agent-safetensors](https://huggingface.co/MC7ever/MiniCPM5-1B-Agent-safetensors)
30
+
31
+ ### Configuration
32
+
33
+ The following YAML configuration was used to produce this model:
34
+
35
+ ```yaml
36
+ merge_method: breadcrumbs_ties
37
+ base_model: saidutta69/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-heretic
38
+ models:
39
+ - model: saidutta69/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-heretic
40
+ - model: ktruestory/minicpm5-1b-hermes-toolhv1
41
+ parameters:
42
+ weight: 1
43
+ density: 0.01
44
+ - model: MC7ever/MiniCPM5-1B-Agent-safetensors
45
+ parameters:
46
+ weight: 0.45
47
+ density: 0.01
48
+ - model: hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v9
49
+ parameters:
50
+ weight: 0.35
51
+ density: 0.01
52
+ - model: Healshsj/MiniCPM5-1B-Reasoning-Agent-Ultra
53
+ parameters:
54
+ weight: 0.2
55
+ density: 0.01
56
+ dtype: bfloat16
57
+
58
+ ```
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": [
10
+ 1,
11
+ 130073
12
+ ],
13
+ "head_dim": 128,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 1536,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 4608,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 16,
22
+ "num_hidden_layers": 24,
23
+ "num_key_value_heads": 2,
24
+ "pad_token_id": 1,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-06,
27
+ "rope_parameters": {
28
+ "rope_theta": 5000000,
29
+ "rope_type": "default"
30
+ },
31
+ "tie_word_embeddings": false,
32
+ "transformers_version": "5.12.1",
33
+ "use_cache": true,
34
+ "vocab_size": 130560
35
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 130073
8
+ ],
9
+ "pad_token_id": 1,
10
+ "temperature": 0.9,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.13.1"
13
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ merge_method: breadcrumbs_ties
2
+ base_model: saidutta69/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-heretic
3
+ models:
4
+ - model: saidutta69/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-heretic
5
+ - model: ktruestory/minicpm5-1b-hermes-toolhv1
6
+ parameters:
7
+ weight: 1
8
+ density: 0.01
9
+ - model: MC7ever/MiniCPM5-1B-Agent-safetensors
10
+ parameters:
11
+ weight: 0.45
12
+ density: 0.01
13
+ - model: hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v9
14
+ parameters:
15
+ weight: 0.35
16
+ density: 0.01
17
+ - model: Healshsj/MiniCPM5-1B-Reasoning-Agent-Ultra
18
+ parameters:
19
+ weight: 0.2
20
+ density: 0.01
21
+ dtype: bfloat16
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:424a4757012f29324d00a441fc74eb0b1ce7fb023ecf2d2028b109afbf580708
3
+ size 2161290944
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "</s>",
7
+ "is_local": false,
8
+ "legacy": true,
9
+ "local_files_only": false,
10
+ "model_max_length": 1000000000000000019884624838656,
11
+ "pad_token": "</s>",
12
+ "sp_model_kwargs": {},
13
+ "spaces_between_special_tokens": false,
14
+ "tokenizer_class": "TokenizersBackend",
15
+ "unk_token": "<unk>",
16
+ "use_default_system_prompt": false
17
+ }