bigstorm commited on
Commit
fe8c203
1 Parent(s): 4c1bb51

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - code
4
+ license: other
5
+ tags:
6
+ - code
7
+ inference: false
8
+ license_name: mnpl
9
+ license_link: https://mistral.ai/licences/MNPL-0.1.md
10
+ ---
11
+
12
+ # Model Card for Codestral-22B-v0.1
13
+
14
+ Codestral-22B-v0.1 is trained on a diverse dataset of 80+ programming languages, including the most popular ones, such as Python, Java, C, C++, JavaScript, and Bash (more details in the [Blogpost](https://mistral.ai/news/codestral/)). The model can be queried:
15
+ - As instruct, for instance to answer any questions about a code snippet (write documentation, explain, factorize) or to generate code following specific indications
16
+ - As Fill in the Middle (FIM), to predict the middle tokens between a prefix and a suffix (very useful for software development add-ons like in VS Code)
17
+
18
+
19
+ ## Installation
20
+
21
+ It is recommended to use `mistralai/Codestral-22B-v0.1` with [mistral-inference](https://github.com/mistralai/mistral-inference).
22
+
23
+ ```
24
+ pip install mistral_inference
25
+ ```
26
+
27
+ ## Download
28
+
29
+ ```py
30
+ from huggingface_hub import snapshot_download
31
+ from pathlib import Path
32
+
33
+ mistral_models_path = Path.home().joinpath('mistral_models', 'Codestral-22B-v0.1')
34
+ mistral_models_path.mkdir(parents=True, exist_ok=True)
35
+
36
+ snapshot_download(repo_id="mistralai/Codestral-22B-v0.1", allow_patterns=["params.json", "consolidated.safetensors", "tokenizer.model.v3"], local_dir=mistral_models_path)
37
+ ```
38
+
39
+ ### Chat
40
+
41
+ After installing `mistral_inference`, a `mistral-chat` CLI command should be available in your environment.
42
+
43
+ ```
44
+ mistral-chat $HOME/mistral_models/Codestral-22B-v0.1 --instruct --max_tokens 256
45
+ ```
46
+
47
+ Will generate an answer to "Write me a function that computes fibonacci in Rust" and should give something along the following lines:
48
+
49
+ ```
50
+ Sure, here's a simple implementation of a function that computes the Fibonacci sequence in Rust. This function takes an integer `n` as an argument and returns the `n`th Fibonacci number.
51
+
52
+ fn fibonacci(n: u32) -> u32 {
53
+ match n {
54
+ 0 => 0,
55
+ 1 => 1,
56
+ _ => fibonacci(n - 1) + fibonacci(n - 2),
57
+ }
58
+ }
59
+
60
+ fn main() {
61
+ let n = 10;
62
+ println!("The {}th Fibonacci number is: {}", n, fibonacci(n));
63
+ }
64
+
65
+ This function uses recursion to calculate the Fibonacci number. However, it's not the most efficient solution because it performs a lot of redundant calculations. A more efficient solution would use a loop to iteratively calculate the Fibonacci numbers.
66
+ ```
67
+
68
+
69
+ ### Fill-in-the-middle (FIM)
70
+
71
+ After installing `mistral_inference` and running `pip install --upgrade mistral_common` to make sure to have mistral_common>=1.2 installed:
72
+
73
+ ```py
74
+ from mistral_inference.model import Transformer
75
+ from mistral_inference.generate import generate
76
+ from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
77
+ from mistral_common.tokens.instruct.request import FIMRequest
78
+
79
+ tokenizer = MistralTokenizer.v3()
80
+ model = Transformer.from_folder("~/codestral-22B-240529")
81
+
82
+ prefix = """def add("""
83
+ suffix = """ return sum"""
84
+
85
+ request = FIMRequest(prompt=prefix, suffix=suffix)
86
+
87
+ tokens = tokenizer.encode_fim(request).tokens
88
+
89
+ out_tokens, _ = generate([tokens], model, max_tokens=256, temperature=0.0, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)
90
+ result = tokenizer.decode(out_tokens[0])
91
+
92
+ middle = result.split(suffix)[0].strip()
93
+ print(middle)
94
+ ```
95
+
96
+ Should give something along the following lines:
97
+
98
+ ```
99
+ num1, num2):
100
+
101
+ # Add two numbers
102
+ sum = num1 + num2
103
+
104
+ # return the sum
105
+ ```
106
+
107
+ ## Usage with transformers library
108
+
109
+ This model is also compatible with `transformers` library, first run `pip install -U transformers` then use the snippet below to quickly get started:
110
+
111
+ ```python
112
+ from transformers import AutoModelForCausalLM, AutoTokenizer
113
+
114
+ model_id = "mistralai/Codestral-22B-v0.1"
115
+ tokenizer = AutoTokenizer.from_pretrained(model_id)
116
+
117
+ model = AutoModelForCausalLM.from_pretrained(model_id)
118
+
119
+ text = "Hello my name is"
120
+ inputs = tokenizer(text, return_tensors="pt")
121
+
122
+ outputs = model.generate(**inputs, max_new_tokens=20)
123
+ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
124
+ ```
125
+
126
+ By default, transformers will load the model in full precision. Therefore you might be interested to further reduce down the memory requirements to run the model through the optimizations we offer in HF ecosystem.
127
+
128
+ ## Limitations
129
+
130
+ The Codestral-22B-v0.1 does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to
131
+ make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.
132
+
133
+ ## License
134
+
135
+ Codestral-22B-v0.1 is released under the `MNLP-0.1` license.
136
+
137
+ ## The Mistral AI Team
138
+
139
+ Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Antoine Roux, Arthur Mensch, Audrey Herblin-Stoop, Baptiste Bout, Baudouin de Monicault, Blanche Savary, Bam4d, Caroline Feldman, Devendra Singh Chaplot, Diego de las Casas, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Harizo Rajaona, Henri Roussez, Jean-Malo Delignon, Jia Li, Justus Murke, Kartik Khandelwal, Lawrence Stewart, Louis Martin, Louis Ternon, Lucile Saulnier, Lélio Renard Lavaud, Margaret Jennings, Marie Pellat, Marie Torelli, Marie-Anne Lachaux, Marjorie Janiewicz, Mickael Seznec, Nicolas Schuhl, Patrick von Platen, Romain Sauvestre, Pierre Stock, Sandeep Subramanian, Saurabh Garg, Sophia Yang, Szymon Antoniak, Teven Le Scao, Thibaut Lavril, Thibault Schueller, Timothée Lacroix, Théophile Gervet, Thomas Wang, Valera Nemychnikova, Wendy Shang, William El Sayed, William Marshall
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistral-community/Codestral-22B-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": 6144,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 16384,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 48,
16
+ "num_hidden_layers": 56,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 1000000.0,
20
+ "sliding_window": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.42.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 32768,
26
+ "quantization_config": {
27
+ "quant_method": "exl2",
28
+ "version": "0.1.5",
29
+ "bits": 8.0,
30
+ "head_bits": 8,
31
+ "calibration": {
32
+ "rows": 100,
33
+ "length": 2048,
34
+ "dataset": "(default)"
35
+ }
36
+ }
37
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.42.0.dev0"
6
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1,514 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 44494565376
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00009-of-00009.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00009.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00009.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00009.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00009.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00004-of-00009.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00004-of-00009.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00009.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00004-of-00009.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00009.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00005-of-00009.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00005-of-00009.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00005-of-00009.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00005-of-00009.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00005-of-00009.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00005-of-00009.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00005-of-00009.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00006-of-00009.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00006-of-00009.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00006-of-00009.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00006-of-00009.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00006-of-00009.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00006-of-00009.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00007-of-00009.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00007-of-00009.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00007-of-00009.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00009.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
323
+ "model.layers.40.input_layernorm.weight": "model-00007-of-00009.safetensors",
324
+ "model.layers.40.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
325
+ "model.layers.40.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
326
+ "model.layers.40.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
327
+ "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
328
+ "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
329
+ "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
330
+ "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
331
+ "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
332
+ "model.layers.41.input_layernorm.weight": "model-00007-of-00009.safetensors",
333
+ "model.layers.41.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
334
+ "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
335
+ "model.layers.41.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
336
+ "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
337
+ "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
338
+ "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
339
+ "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
340
+ "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
341
+ "model.layers.42.input_layernorm.weight": "model-00007-of-00009.safetensors",
342
+ "model.layers.42.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
343
+ "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
344
+ "model.layers.42.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
345
+ "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
346
+ "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
347
+ "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
348
+ "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
349
+ "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
350
+ "model.layers.43.input_layernorm.weight": "model-00008-of-00009.safetensors",
351
+ "model.layers.43.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
352
+ "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
353
+ "model.layers.43.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
354
+ "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
355
+ "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
356
+ "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
357
+ "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
358
+ "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
359
+ "model.layers.44.input_layernorm.weight": "model-00008-of-00009.safetensors",
360
+ "model.layers.44.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
361
+ "model.layers.44.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
362
+ "model.layers.44.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
363
+ "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
364
+ "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
365
+ "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
366
+ "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
367
+ "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
368
+ "model.layers.45.input_layernorm.weight": "model-00008-of-00009.safetensors",
369
+ "model.layers.45.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
370
+ "model.layers.45.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
371
+ "model.layers.45.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
372
+ "model.layers.45.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
373
+ "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
374
+ "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
375
+ "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
376
+ "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
377
+ "model.layers.46.input_layernorm.weight": "model-00008-of-00009.safetensors",
378
+ "model.layers.46.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
379
+ "model.layers.46.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
380
+ "model.layers.46.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
381
+ "model.layers.46.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
382
+ "model.layers.46.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
383
+ "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
384
+ "model.layers.46.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
385
+ "model.layers.46.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
386
+ "model.layers.47.input_layernorm.weight": "model-00008-of-00009.safetensors",
387
+ "model.layers.47.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
388
+ "model.layers.47.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
389
+ "model.layers.47.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
390
+ "model.layers.47.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
391
+ "model.layers.47.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
392
+ "model.layers.47.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
393
+ "model.layers.47.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
394
+ "model.layers.47.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
395
+ "model.layers.48.input_layernorm.weight": "model-00008-of-00009.safetensors",
396
+ "model.layers.48.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
397
+ "model.layers.48.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
398
+ "model.layers.48.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
399
+ "model.layers.48.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
400
+ "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
401
+ "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
402
+ "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
403
+ "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
404
+ "model.layers.49.input_layernorm.weight": "model-00008-of-00009.safetensors",
405
+ "model.layers.49.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
406
+ "model.layers.49.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
407
+ "model.layers.49.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
408
+ "model.layers.49.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
409
+ "model.layers.49.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
410
+ "model.layers.49.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
411
+ "model.layers.49.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
412
+ "model.layers.49.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
413
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
414
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
415
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
416
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
417
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
418
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
419
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
420
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
421
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
422
+ "model.layers.50.input_layernorm.weight": "model-00009-of-00009.safetensors",
423
+ "model.layers.50.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
424
+ "model.layers.50.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
425
+ "model.layers.50.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
426
+ "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
427
+ "model.layers.50.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
428
+ "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
429
+ "model.layers.50.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
430
+ "model.layers.50.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
431
+ "model.layers.51.input_layernorm.weight": "model-00009-of-00009.safetensors",
432
+ "model.layers.51.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
433
+ "model.layers.51.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
434
+ "model.layers.51.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
435
+ "model.layers.51.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
436
+ "model.layers.51.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
437
+ "model.layers.51.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
438
+ "model.layers.51.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
439
+ "model.layers.51.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
440
+ "model.layers.52.input_layernorm.weight": "model-00009-of-00009.safetensors",
441
+ "model.layers.52.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
442
+ "model.layers.52.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
443
+ "model.layers.52.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
444
+ "model.layers.52.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
445
+ "model.layers.52.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
446
+ "model.layers.52.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
447
+ "model.layers.52.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
448
+ "model.layers.52.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
449
+ "model.layers.53.input_layernorm.weight": "model-00009-of-00009.safetensors",
450
+ "model.layers.53.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
451
+ "model.layers.53.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
452
+ "model.layers.53.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
453
+ "model.layers.53.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
454
+ "model.layers.53.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
455
+ "model.layers.53.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
456
+ "model.layers.53.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
457
+ "model.layers.53.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
458
+ "model.layers.54.input_layernorm.weight": "model-00009-of-00009.safetensors",
459
+ "model.layers.54.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
460
+ "model.layers.54.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
461
+ "model.layers.54.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
462
+ "model.layers.54.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
463
+ "model.layers.54.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
464
+ "model.layers.54.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
465
+ "model.layers.54.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
466
+ "model.layers.54.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
467
+ "model.layers.55.input_layernorm.weight": "model-00009-of-00009.safetensors",
468
+ "model.layers.55.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
469
+ "model.layers.55.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
470
+ "model.layers.55.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
471
+ "model.layers.55.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
472
+ "model.layers.55.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
473
+ "model.layers.55.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
474
+ "model.layers.55.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
475
+ "model.layers.55.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
476
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors",
477
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
478
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
479
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
480
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
481
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
482
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
483
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
484
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
485
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors",
486
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
487
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
488
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
489
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
490
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
491
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
492
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
493
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
494
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors",
495
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
496
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
497
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
498
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
499
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
500
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
501
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
502
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
503
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00009.safetensors",
504
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
505
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
506
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
507
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
508
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
509
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
510
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
511
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
512
+ "model.norm.weight": "model-00009-of-00009.safetensors"
513
+ }
514
+ }
output-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1744dfc84732d46aa840857e25c292057962adf08ddd4706d4c0ba25014b807
3
+ size 8544626336
output-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a54a66bc539b96890f1c8cc5e9ea4a6cc4e53b0cc8c2ac98f5470e656c88e8de
3
+ size 8489596576
output-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c198ba6bdd6481a80d0a6f8db03a183cc5787d652e18f82078aff8af640309e
3
+ size 4092196000
params.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dim": 6144,
3
+ "n_layers": 56,
4
+ "head_dim": 128,
5
+ "hidden_dim": 16384,
6
+ "n_heads": 48,
7
+ "n_kv_heads": 8,
8
+ "norm_eps": 1e-05,
9
+ "vocab_size": 32768,
10
+ "rope_theta": 1000000.0
11
+ }
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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
tokenizer.model.v3 ADDED
Binary file (588 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 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
+ }