JoPmt commited on
Commit
504b559
1 Parent(s): f82e374

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - BEE-spoke-data/smol_llama-220M-openhermes
7
+ - BEE-spoke-data/smol_llama-220M-GQA
8
+ base_model:
9
+ - BEE-spoke-data/smol_llama-220M-openhermes
10
+ - BEE-spoke-data/smol_llama-220M-GQA
11
+ ---
12
+
13
+ # Hermetic-Llama-Ties
14
+
15
+ Hermetic-Llama-Ties is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
16
+ * [BEE-spoke-data/smol_llama-220M-openhermes](https://huggingface.co/BEE-spoke-data/smol_llama-220M-openhermes)
17
+ * [BEE-spoke-data/smol_llama-220M-GQA](https://huggingface.co/BEE-spoke-data/smol_llama-220M-GQA)
18
+
19
+ ## 🧩 Configuration
20
+
21
+ ```yaml
22
+ models:
23
+ - model: BEE-spoke-data/smol_llama-220M-openhermes
24
+ parameters:
25
+ density: 0.5
26
+ weight: 0.5
27
+ - model: BEE-spoke-data/smol_llama-220M-GQA
28
+ parameters:
29
+ density: 0.5
30
+ weight: 0.5
31
+
32
+ merge_method: ties
33
+ base_model: BEE-spoke-data/smol_llama-220M-openhermes
34
+ parameters:
35
+ normalize: false
36
+ int8_mask: true
37
+ dtype: bfloat16
38
+ ```
39
+
40
+ ## 💻 Usage
41
+
42
+ ```python
43
+ !pip install -qU transformers accelerate
44
+
45
+ from transformers import AutoTokenizer
46
+ import transformers
47
+ import torch
48
+
49
+ model = "JoPmt/Hermetic-Llama-Ties"
50
+ messages = [{"role": "user", "content": "What is a large language model?"}]
51
+
52
+ tokenizer = AutoTokenizer.from_pretrained(model)
53
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
54
+ pipeline = transformers.pipeline(
55
+ "text-generation",
56
+ model=model,
57
+ torch_dtype=torch.float16,
58
+ device_map="auto",
59
+ )
60
+
61
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
62
+ print(outputs[0]["generated_text"])
63
+ ```
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "BEE-spoke-data/smol_llama-220M-openhermes",
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": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 10,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.38.2",
26
+ "use_cache": false,
27
+ "vocab_size": 32128
28
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ models:
3
+ - model: BEE-spoke-data/smol_llama-220M-openhermes
4
+ parameters:
5
+ density: 0.5
6
+ weight: 0.5
7
+ - model: BEE-spoke-data/smol_llama-220M-GQA
8
+ parameters:
9
+ density: 0.5
10
+ weight: 0.5
11
+
12
+ merge_method: ties
13
+ base_model: BEE-spoke-data/smol_llama-220M-openhermes
14
+ parameters:
15
+ normalize: false
16
+ int8_mask: true
17
+ dtype: bfloat16
model-00001-of-00001.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2438b9285edf9dfe12e223a3805618df0ab5ec37c4ad122de876e114f3cd433f
3
+ size 435736840
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 435726336}, "weight_map": {"lm_head.weight": "model-00001-of-00001.safetensors", "model.norm.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.embed_tokens.weight": "model-00001-of-00001.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": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
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.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "trust_remote_code": false,
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": true,
44
+ "use_fast": true
45
+ }