nachoaristimuno commited on
Commit
0116c2c
1 Parent(s): a801320

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - merge
4
+ - mergekit
5
+ - lazymergekit
6
+ - WizardLM/WizardMath-7B-V1.1
7
+ - meta-math/MetaMath-Mistral-7B
8
+ base_model:
9
+ - WizardLM/WizardMath-7B-V1.1
10
+ - meta-math/MetaMath-Mistral-7B
11
+ ---
12
+
13
+ # MistralMath-7B-v0.1
14
+
15
+ MistralMath-7B-v0.1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
16
+ * [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1)
17
+ * [meta-math/MetaMath-Mistral-7B](https://huggingface.co/meta-math/MetaMath-Mistral-7B)
18
+
19
+ ## 🧩 Configuration
20
+
21
+ ```yaml
22
+ models:
23
+ - model: mistralai/Mistral-7B-v0.1 # No parameters necessary for base model
24
+ - model: WizardLM/WizardMath-7B-V1.1
25
+ parameters:
26
+ density: 0.65
27
+ weight: 0.4
28
+ - model: meta-math/MetaMath-Mistral-7B
29
+ parameters:
30
+ density: 0.6
31
+ weight: 0.3
32
+ merge_method: dare_ties
33
+ base_model: mistralai/Mistral-7B-v0.1
34
+ parameters:
35
+ int8_mask: true
36
+ dtype: float16
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 = "nachoaristimuno/MistralMath-7B-v0.1"
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 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-v0.1",
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": "float16",
23
+ "transformers_version": "4.38.2",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ models:
3
+ - model: mistralai/Mistral-7B-v0.1 # No parameters necessary for base model
4
+ - model: WizardLM/WizardMath-7B-V1.1
5
+ parameters:
6
+ density: 0.65
7
+ weight: 0.4
8
+ - model: meta-math/MetaMath-Mistral-7B
9
+ parameters:
10
+ density: 0.6
11
+ weight: 0.3
12
+ merge_method: dare_ties
13
+ base_model: mistralai/Mistral-7B-v0.1
14
+ parameters:
15
+ int8_mask: true
16
+ dtype: float16
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:732af4972b676ba8ff0c2304f9945a2d85e20c87e978eb1c7198981fba9d27ce
3
+ size 1946227336
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fef4df4c52931725e5a49d5aa0315cf468344abd87d0541affb226ca73350d6
3
+ size 1979789736
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216268f0d50676c54c2b2f9b128669bfd31b3599bd2f8be11b855f074594d1b7
3
+ size 1946235624
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:470be09b039a6af79cdb81ce1be15e538c96139203d953bbd6200f170ed0da60
3
+ size 1979789696
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbe6293dcf83963458cd646a2d41296ddc3fa1b4a50c26620255e6de1bfd571d
3
+ size 1828794960
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c946c40f762ea680ce8e24bef3b7516003faf897864c29d60e067e2db00aba95
3
+ size 1950412248
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:823de490f66cee51894b93f5f0d32978fdc99b84c5d8f1e68c6a8212da3a15fe
3
+ size 1979789736
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:befb5bf172dc5a6c788603ace740ebfcf05ad857f8cde8015f938a38f781e204
3
+ size 872458376
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 14483464192}, "weight_map": {"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.embed_tokens.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-00007-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-00008-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-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
+ }