ucheog commited on
Commit
3e7d3e1
1 Parent(s): 88f8ba4

Upload folder using huggingface_hub (#1)

Browse files

- 9d9c51889d477c3d1b9b0e7f219f737312d43057c115762530d97115be3b2a72 (384ee09b4d3f4e3feb7f6b7297a412a4063614ad)

README.md ADDED
@@ -0,0 +1,173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ library_name: transformers
5
+ license: apache-2.0
6
+ tags:
7
+ - gpt
8
+ - llm
9
+ - large language model
10
+ - h2o-llmstudio
11
+ thumbnail: >-
12
+ https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
13
+ pipeline_tag: text-generation
14
+ ---
15
+
16
+ # h2o-danube2-1.8b-chat-MLX-4bit
17
+
18
+ Model was converted to MLX format from [`h2oai/h2o-danube2-1.8b-chat`](https://huggingface.co/h2oai/h2o-danube2-1.8b-chat) using mlx-lm version **0.7.0**.
19
+ The original model card is reproduced below, for further details.
20
+
21
+ ## Use with mlx
22
+
23
+ From shell:
24
+
25
+ ```sh
26
+ pip install mlx-lm
27
+ ```
28
+
29
+ Then in Python:
30
+
31
+ ```python
32
+ from mlx_lm import load, generate
33
+
34
+ model, tokenizer = load('ucheog/h2o-danube2-1.8b-chat-MLX-4bit')
35
+ response = generate(model, tokenizer, prompt='Tell me a solar eclipse joke', verbose=True)
36
+ ```
37
+
38
+ # Original Model Card
39
+
40
+ ## Summary
41
+
42
+ h2o-danube2-1.8b-chat is a chat fine-tuned model by H2O.ai with 1.8 billion parameters. We release three versions of this model:
43
+
44
+ | Model Name | Description |
45
+ |:-----------------------------------------------------------------------------------|:----------------|
46
+ | [h2oai/h2o-danube2-1.8b-base](https://huggingface.co/h2oai/h2o-danube2-1.8b-base) | Base model |
47
+ | [h2oai/h2o-danube2-1.8b-sft](https://huggingface.co/h2oai/h2o-danube2-1.8b-sft) | SFT tuned |
48
+ | [h2oai/h2o-danube2-1.8b-chat](https://huggingface.co/h2oai/h2o-danube2-1.8b-chat) | SFT + DPO tuned |
49
+
50
+ This model was trained using [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio).
51
+
52
+ ## Model Architecture
53
+
54
+ We adjust the Llama 2 architecture for a total of around 1.8b parameters. For details, please refer to our [Technical Report](https://arxiv.org/abs/2401.16818). We use the Mistral tokenizer with a vocabulary size of 32,000 and train our model up to a context length of 8,192.
55
+
56
+ The details of the model architecture are:
57
+
58
+ | Hyperparameter | Value |
59
+ |:----------------|:-------|
60
+ | n_layers | 24 |
61
+ | n_heads | 32 |
62
+ | n_query_groups | 8 |
63
+ | n_embd | 2560 |
64
+ | vocab size | 32000 |
65
+ | sequence length | 8192 |
66
+
67
+ ## Usage
68
+
69
+ To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers` library installed.
70
+
71
+ ```bash
72
+ pip install transformers>=4.39.3
73
+ ```
74
+
75
+ ```python
76
+ import torch
77
+ from transformers import pipeline
78
+
79
+ pipe = pipeline(
80
+ "text-generation",
81
+ model="h2oai/h2o-danube2-1.8b-chat",
82
+ torch_dtype=torch.bfloat16,
83
+ device_map="auto",
84
+ )
85
+
86
+ # We use the HF Tokenizer chat template to format each message
87
+ # https://huggingface.co/docs/transformers/main/en/chat_templating
88
+ messages = [
89
+ {"role": "user", "content": "Why is drinking water so healthy?"},
90
+ ]
91
+ prompt = pipe.tokenizer.apply_chat_template(
92
+ messages,
93
+ tokenize=False,
94
+ add_generation_prompt=True,
95
+ )
96
+ res = pipe(
97
+ prompt,
98
+ max_new_tokens=256,
99
+ )
100
+ print(res[0]["generated_text"])
101
+ ```
102
+
103
+ ## Quantization and sharding
104
+
105
+ You can load the models using quantization by specifying ```load_in_8bit=True``` or ```load_in_4bit=True```. Also, sharding on multiple GPUs is possible by setting ```device_map=auto```.
106
+
107
+ ## Model Architecture
108
+
109
+ ```
110
+ MistralForCausalLM(
111
+ (model): MistralModel(
112
+ (embed_tokens): Embedding(32000, 2560, padding_idx=0)
113
+ (layers): ModuleList(
114
+ (0-23): 24 x MistralDecoderLayer(
115
+ (self_attn): MistralAttention(
116
+ (q_proj): Linear(in_features=2560, out_features=2560, bias=False)
117
+ (k_proj): Linear(in_features=2560, out_features=640, bias=False)
118
+ (v_proj): Linear(in_features=2560, out_features=640, bias=False)
119
+ (o_proj): Linear(in_features=2560, out_features=2560, bias=False)
120
+ (rotary_emb): MistralRotaryEmbedding()
121
+ )
122
+ (mlp): MistralMLP(
123
+ (gate_proj): Linear(in_features=2560, out_features=6912, bias=False)
124
+ (up_proj): Linear(in_features=2560, out_features=6912, bias=False)
125
+ (down_proj): Linear(in_features=6912, out_features=2560, bias=False)
126
+ (act_fn): SiLU()
127
+ )
128
+ (input_layernorm): MistralRMSNorm()
129
+ (post_attention_layernorm): MistralRMSNorm()
130
+ )
131
+ )
132
+ (norm): MistralRMSNorm()
133
+ )
134
+ (lm_head): Linear(in_features=2560, out_features=32000, bias=False)
135
+ )
136
+ ```
137
+
138
+ ## Benchmarks
139
+
140
+ ### 🤗 Open LLM Leaderboard
141
+
142
+ | Benchmark | acc_n |
143
+ |:--------------|:--------:|
144
+ | Average | 48.44 |
145
+ | ARC-challenge | 43.43 |
146
+ | Hellaswag | 73.54 |
147
+ | MMLU | 37.77 |
148
+ | TruthfulQA | 39.96 |
149
+ | Winogrande | 69.77 |
150
+ | GSM8K | 26.16 |
151
+
152
+ ### MT-Bench
153
+
154
+ ```
155
+ First Turn: 6.23
156
+ Second Turn: 5.34
157
+ Average: 5.79
158
+ ```
159
+
160
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/636d18755aaed143cd6698ef/s0wBOV7Nh1C4ODQGxiGJU.png)
161
+
162
+ ## Disclaimer
163
+
164
+ Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions.
165
+
166
+ - Biases and Offensiveness: The large language model is trained on a diverse range of internet text data, which may contain biased, racist, offensive, or otherwise inappropriate content. By using this model, you acknowledge and accept that the generated content may sometimes exhibit biases or produce content that is offensive or inappropriate. The developers of this repository do not endorse, support, or promote any such content or viewpoints.
167
+ - Limitations: The large language model is an AI-based tool and not a human. It may produce incorrect, nonsensical, or irrelevant responses. It is the user's responsibility to critically evaluate the generated content and use it at their discretion.
168
+ - Use at Your Own Risk: Users of this large language model must assume full responsibility for any consequences that may arise from their use of the tool. The developers and contributors of this repository shall not be held liable for any damages, losses, or harm resulting from the use or misuse of the provided model.
169
+ - Ethical Considerations: Users are encouraged to use the large language model responsibly and ethically. By using this model, you agree not to use it for purposes that promote hate speech, discrimination, harassment, or any form of illegal or harmful activities.
170
+ - Reporting Issues: If you encounter any biased, offensive, or otherwise inappropriate content generated by the large language model, please report it to the repository maintainers through the provided channels. Your feedback will help improve the model and mitigate potential issues.
171
+ - Changes to this Disclaimer: The developers of this repository reserve the right to modify or update this disclaimer at any time without prior notice. It is the user's responsibility to periodically review the disclaimer to stay informed about any changes.
172
+
173
+ By using the large language model provided in this repository, you agree to accept and comply with the terms and conditions outlined in this disclaimer. If you do not agree with any part of this disclaimer, you should refrain from using the model and any content generated by it.
config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bad_words_ids": null,
8
+ "begin_suppress_tokens": null,
9
+ "bos_token_id": 1,
10
+ "chunk_size_feed_forward": 0,
11
+ "cross_attention_hidden_size": null,
12
+ "decoder_start_token_id": null,
13
+ "diversity_penalty": 0.0,
14
+ "do_sample": false,
15
+ "early_stopping": false,
16
+ "encoder_no_repeat_ngram_size": 0,
17
+ "eos_token_id": 2,
18
+ "exponential_decay_length_penalty": null,
19
+ "finetuning_task": null,
20
+ "forced_bos_token_id": null,
21
+ "forced_eos_token_id": null,
22
+ "hidden_act": "silu",
23
+ "hidden_size": 2560,
24
+ "id2label": {
25
+ "0": "LABEL_0",
26
+ "1": "LABEL_1"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 6912,
30
+ "is_decoder": false,
31
+ "is_encoder_decoder": false,
32
+ "label2id": {
33
+ "LABEL_0": 0,
34
+ "LABEL_1": 1
35
+ },
36
+ "length_penalty": 1.0,
37
+ "max_length": 20,
38
+ "max_position_embeddings": 8192,
39
+ "min_length": 0,
40
+ "model_type": "mistral",
41
+ "no_repeat_ngram_size": 0,
42
+ "num_attention_heads": 32,
43
+ "num_beam_groups": 1,
44
+ "num_beams": 1,
45
+ "num_hidden_layers": 24,
46
+ "num_key_value_heads": 8,
47
+ "num_return_sequences": 1,
48
+ "output_attentions": false,
49
+ "output_hidden_states": false,
50
+ "output_scores": false,
51
+ "pad_token_id": 0,
52
+ "prefix": null,
53
+ "problem_type": null,
54
+ "pruned_heads": {},
55
+ "quantization": {
56
+ "group_size": 64,
57
+ "bits": 4
58
+ },
59
+ "remove_invalid_values": false,
60
+ "repetition_penalty": 1.0,
61
+ "return_dict": true,
62
+ "return_dict_in_generate": false,
63
+ "rms_norm_eps": 1e-05,
64
+ "rope_theta": 10000,
65
+ "sep_token_id": null,
66
+ "sliding_window": null,
67
+ "suppress_tokens": null,
68
+ "task_specific_params": null,
69
+ "temperature": 1.0,
70
+ "tf_legacy_loss": false,
71
+ "tie_encoder_decoder": false,
72
+ "tie_word_embeddings": false,
73
+ "tokenizer_class": null,
74
+ "top_k": 50,
75
+ "top_p": 1.0,
76
+ "torch_dtype": "bfloat16",
77
+ "torchscript": false,
78
+ "transformers_version": "4.38.2",
79
+ "typical_p": 1.0,
80
+ "use_bfloat16": false,
81
+ "use_cache": true,
82
+ "vocab_size": 32000
83
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:208e3c7bfb4a7209a4ddcb61ebfec971c6b9f739d00ea3feecdf0c40bcef5118
3
+ size 1148052922
model.safetensors.index.json ADDED
@@ -0,0 +1,564 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 1147991040
4
+ },
5
+ "weight_map": {
6
+ "lm_head.biases": "model.safetensors",
7
+ "lm_head.scales": "model.safetensors",
8
+ "lm_head.weight": "model.safetensors",
9
+ "model.embed_tokens.weight": "model.safetensors",
10
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
11
+ "model.layers.0.mlp.down_proj.biases": "model.safetensors",
12
+ "model.layers.0.mlp.down_proj.scales": "model.safetensors",
13
+ "model.layers.0.mlp.down_proj.weight": "model.safetensors",
14
+ "model.layers.0.mlp.gate_proj.biases": "model.safetensors",
15
+ "model.layers.0.mlp.gate_proj.scales": "model.safetensors",
16
+ "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
17
+ "model.layers.0.mlp.up_proj.biases": "model.safetensors",
18
+ "model.layers.0.mlp.up_proj.scales": "model.safetensors",
19
+ "model.layers.0.mlp.up_proj.weight": "model.safetensors",
20
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
21
+ "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
22
+ "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
23
+ "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
24
+ "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
25
+ "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
26
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
27
+ "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
28
+ "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
29
+ "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
30
+ "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
31
+ "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
32
+ "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
33
+ "model.layers.1.input_layernorm.weight": "model.safetensors",
34
+ "model.layers.1.mlp.down_proj.biases": "model.safetensors",
35
+ "model.layers.1.mlp.down_proj.scales": "model.safetensors",
36
+ "model.layers.1.mlp.down_proj.weight": "model.safetensors",
37
+ "model.layers.1.mlp.gate_proj.biases": "model.safetensors",
38
+ "model.layers.1.mlp.gate_proj.scales": "model.safetensors",
39
+ "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
40
+ "model.layers.1.mlp.up_proj.biases": "model.safetensors",
41
+ "model.layers.1.mlp.up_proj.scales": "model.safetensors",
42
+ "model.layers.1.mlp.up_proj.weight": "model.safetensors",
43
+ "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
44
+ "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
45
+ "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
46
+ "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
47
+ "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
48
+ "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
49
+ "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
50
+ "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
51
+ "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
52
+ "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
53
+ "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
54
+ "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
55
+ "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
56
+ "model.layers.10.input_layernorm.weight": "model.safetensors",
57
+ "model.layers.10.mlp.down_proj.biases": "model.safetensors",
58
+ "model.layers.10.mlp.down_proj.scales": "model.safetensors",
59
+ "model.layers.10.mlp.down_proj.weight": "model.safetensors",
60
+ "model.layers.10.mlp.gate_proj.biases": "model.safetensors",
61
+ "model.layers.10.mlp.gate_proj.scales": "model.safetensors",
62
+ "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
63
+ "model.layers.10.mlp.up_proj.biases": "model.safetensors",
64
+ "model.layers.10.mlp.up_proj.scales": "model.safetensors",
65
+ "model.layers.10.mlp.up_proj.weight": "model.safetensors",
66
+ "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
67
+ "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
68
+ "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
69
+ "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
70
+ "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
71
+ "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
72
+ "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
73
+ "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
74
+ "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
75
+ "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
76
+ "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
77
+ "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
78
+ "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
79
+ "model.layers.11.input_layernorm.weight": "model.safetensors",
80
+ "model.layers.11.mlp.down_proj.biases": "model.safetensors",
81
+ "model.layers.11.mlp.down_proj.scales": "model.safetensors",
82
+ "model.layers.11.mlp.down_proj.weight": "model.safetensors",
83
+ "model.layers.11.mlp.gate_proj.biases": "model.safetensors",
84
+ "model.layers.11.mlp.gate_proj.scales": "model.safetensors",
85
+ "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
86
+ "model.layers.11.mlp.up_proj.biases": "model.safetensors",
87
+ "model.layers.11.mlp.up_proj.scales": "model.safetensors",
88
+ "model.layers.11.mlp.up_proj.weight": "model.safetensors",
89
+ "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
90
+ "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
91
+ "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
92
+ "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
93
+ "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
94
+ "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
95
+ "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
96
+ "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
97
+ "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
98
+ "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
99
+ "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
100
+ "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
101
+ "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
102
+ "model.layers.12.input_layernorm.weight": "model.safetensors",
103
+ "model.layers.12.mlp.down_proj.biases": "model.safetensors",
104
+ "model.layers.12.mlp.down_proj.scales": "model.safetensors",
105
+ "model.layers.12.mlp.down_proj.weight": "model.safetensors",
106
+ "model.layers.12.mlp.gate_proj.biases": "model.safetensors",
107
+ "model.layers.12.mlp.gate_proj.scales": "model.safetensors",
108
+ "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
109
+ "model.layers.12.mlp.up_proj.biases": "model.safetensors",
110
+ "model.layers.12.mlp.up_proj.scales": "model.safetensors",
111
+ "model.layers.12.mlp.up_proj.weight": "model.safetensors",
112
+ "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
113
+ "model.layers.12.self_attn.k_proj.biases": "model.safetensors",
114
+ "model.layers.12.self_attn.k_proj.scales": "model.safetensors",
115
+ "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
116
+ "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
117
+ "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
118
+ "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
119
+ "model.layers.12.self_attn.q_proj.biases": "model.safetensors",
120
+ "model.layers.12.self_attn.q_proj.scales": "model.safetensors",
121
+ "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
122
+ "model.layers.12.self_attn.v_proj.biases": "model.safetensors",
123
+ "model.layers.12.self_attn.v_proj.scales": "model.safetensors",
124
+ "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
125
+ "model.layers.13.input_layernorm.weight": "model.safetensors",
126
+ "model.layers.13.mlp.down_proj.biases": "model.safetensors",
127
+ "model.layers.13.mlp.down_proj.scales": "model.safetensors",
128
+ "model.layers.13.mlp.down_proj.weight": "model.safetensors",
129
+ "model.layers.13.mlp.gate_proj.biases": "model.safetensors",
130
+ "model.layers.13.mlp.gate_proj.scales": "model.safetensors",
131
+ "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
132
+ "model.layers.13.mlp.up_proj.biases": "model.safetensors",
133
+ "model.layers.13.mlp.up_proj.scales": "model.safetensors",
134
+ "model.layers.13.mlp.up_proj.weight": "model.safetensors",
135
+ "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
136
+ "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
137
+ "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
138
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
139
+ "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
140
+ "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
141
+ "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
142
+ "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
143
+ "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
144
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
145
+ "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
146
+ "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
147
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
148
+ "model.layers.14.input_layernorm.weight": "model.safetensors",
149
+ "model.layers.14.mlp.down_proj.biases": "model.safetensors",
150
+ "model.layers.14.mlp.down_proj.scales": "model.safetensors",
151
+ "model.layers.14.mlp.down_proj.weight": "model.safetensors",
152
+ "model.layers.14.mlp.gate_proj.biases": "model.safetensors",
153
+ "model.layers.14.mlp.gate_proj.scales": "model.safetensors",
154
+ "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
155
+ "model.layers.14.mlp.up_proj.biases": "model.safetensors",
156
+ "model.layers.14.mlp.up_proj.scales": "model.safetensors",
157
+ "model.layers.14.mlp.up_proj.weight": "model.safetensors",
158
+ "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
159
+ "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
160
+ "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
161
+ "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
162
+ "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
163
+ "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
164
+ "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
165
+ "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
166
+ "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
167
+ "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
168
+ "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
169
+ "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
170
+ "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
171
+ "model.layers.15.input_layernorm.weight": "model.safetensors",
172
+ "model.layers.15.mlp.down_proj.biases": "model.safetensors",
173
+ "model.layers.15.mlp.down_proj.scales": "model.safetensors",
174
+ "model.layers.15.mlp.down_proj.weight": "model.safetensors",
175
+ "model.layers.15.mlp.gate_proj.biases": "model.safetensors",
176
+ "model.layers.15.mlp.gate_proj.scales": "model.safetensors",
177
+ "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
178
+ "model.layers.15.mlp.up_proj.biases": "model.safetensors",
179
+ "model.layers.15.mlp.up_proj.scales": "model.safetensors",
180
+ "model.layers.15.mlp.up_proj.weight": "model.safetensors",
181
+ "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
182
+ "model.layers.15.self_attn.k_proj.biases": "model.safetensors",
183
+ "model.layers.15.self_attn.k_proj.scales": "model.safetensors",
184
+ "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
185
+ "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
186
+ "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
187
+ "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
188
+ "model.layers.15.self_attn.q_proj.biases": "model.safetensors",
189
+ "model.layers.15.self_attn.q_proj.scales": "model.safetensors",
190
+ "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
191
+ "model.layers.15.self_attn.v_proj.biases": "model.safetensors",
192
+ "model.layers.15.self_attn.v_proj.scales": "model.safetensors",
193
+ "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
194
+ "model.layers.16.input_layernorm.weight": "model.safetensors",
195
+ "model.layers.16.mlp.down_proj.biases": "model.safetensors",
196
+ "model.layers.16.mlp.down_proj.scales": "model.safetensors",
197
+ "model.layers.16.mlp.down_proj.weight": "model.safetensors",
198
+ "model.layers.16.mlp.gate_proj.biases": "model.safetensors",
199
+ "model.layers.16.mlp.gate_proj.scales": "model.safetensors",
200
+ "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
201
+ "model.layers.16.mlp.up_proj.biases": "model.safetensors",
202
+ "model.layers.16.mlp.up_proj.scales": "model.safetensors",
203
+ "model.layers.16.mlp.up_proj.weight": "model.safetensors",
204
+ "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
205
+ "model.layers.16.self_attn.k_proj.biases": "model.safetensors",
206
+ "model.layers.16.self_attn.k_proj.scales": "model.safetensors",
207
+ "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
208
+ "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
209
+ "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
210
+ "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
211
+ "model.layers.16.self_attn.q_proj.biases": "model.safetensors",
212
+ "model.layers.16.self_attn.q_proj.scales": "model.safetensors",
213
+ "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
214
+ "model.layers.16.self_attn.v_proj.biases": "model.safetensors",
215
+ "model.layers.16.self_attn.v_proj.scales": "model.safetensors",
216
+ "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
217
+ "model.layers.17.input_layernorm.weight": "model.safetensors",
218
+ "model.layers.17.mlp.down_proj.biases": "model.safetensors",
219
+ "model.layers.17.mlp.down_proj.scales": "model.safetensors",
220
+ "model.layers.17.mlp.down_proj.weight": "model.safetensors",
221
+ "model.layers.17.mlp.gate_proj.biases": "model.safetensors",
222
+ "model.layers.17.mlp.gate_proj.scales": "model.safetensors",
223
+ "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
224
+ "model.layers.17.mlp.up_proj.biases": "model.safetensors",
225
+ "model.layers.17.mlp.up_proj.scales": "model.safetensors",
226
+ "model.layers.17.mlp.up_proj.weight": "model.safetensors",
227
+ "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
228
+ "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
229
+ "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
230
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
231
+ "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
232
+ "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
233
+ "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
234
+ "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
235
+ "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
236
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
237
+ "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
238
+ "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
239
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
240
+ "model.layers.18.input_layernorm.weight": "model.safetensors",
241
+ "model.layers.18.mlp.down_proj.biases": "model.safetensors",
242
+ "model.layers.18.mlp.down_proj.scales": "model.safetensors",
243
+ "model.layers.18.mlp.down_proj.weight": "model.safetensors",
244
+ "model.layers.18.mlp.gate_proj.biases": "model.safetensors",
245
+ "model.layers.18.mlp.gate_proj.scales": "model.safetensors",
246
+ "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
247
+ "model.layers.18.mlp.up_proj.biases": "model.safetensors",
248
+ "model.layers.18.mlp.up_proj.scales": "model.safetensors",
249
+ "model.layers.18.mlp.up_proj.weight": "model.safetensors",
250
+ "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
251
+ "model.layers.18.self_attn.k_proj.biases": "model.safetensors",
252
+ "model.layers.18.self_attn.k_proj.scales": "model.safetensors",
253
+ "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
254
+ "model.layers.18.self_attn.o_proj.biases": "model.safetensors",
255
+ "model.layers.18.self_attn.o_proj.scales": "model.safetensors",
256
+ "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
257
+ "model.layers.18.self_attn.q_proj.biases": "model.safetensors",
258
+ "model.layers.18.self_attn.q_proj.scales": "model.safetensors",
259
+ "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
260
+ "model.layers.18.self_attn.v_proj.biases": "model.safetensors",
261
+ "model.layers.18.self_attn.v_proj.scales": "model.safetensors",
262
+ "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
263
+ "model.layers.19.input_layernorm.weight": "model.safetensors",
264
+ "model.layers.19.mlp.down_proj.biases": "model.safetensors",
265
+ "model.layers.19.mlp.down_proj.scales": "model.safetensors",
266
+ "model.layers.19.mlp.down_proj.weight": "model.safetensors",
267
+ "model.layers.19.mlp.gate_proj.biases": "model.safetensors",
268
+ "model.layers.19.mlp.gate_proj.scales": "model.safetensors",
269
+ "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
270
+ "model.layers.19.mlp.up_proj.biases": "model.safetensors",
271
+ "model.layers.19.mlp.up_proj.scales": "model.safetensors",
272
+ "model.layers.19.mlp.up_proj.weight": "model.safetensors",
273
+ "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
274
+ "model.layers.19.self_attn.k_proj.biases": "model.safetensors",
275
+ "model.layers.19.self_attn.k_proj.scales": "model.safetensors",
276
+ "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
277
+ "model.layers.19.self_attn.o_proj.biases": "model.safetensors",
278
+ "model.layers.19.self_attn.o_proj.scales": "model.safetensors",
279
+ "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
280
+ "model.layers.19.self_attn.q_proj.biases": "model.safetensors",
281
+ "model.layers.19.self_attn.q_proj.scales": "model.safetensors",
282
+ "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
283
+ "model.layers.19.self_attn.v_proj.biases": "model.safetensors",
284
+ "model.layers.19.self_attn.v_proj.scales": "model.safetensors",
285
+ "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
286
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
287
+ "model.layers.2.mlp.down_proj.biases": "model.safetensors",
288
+ "model.layers.2.mlp.down_proj.scales": "model.safetensors",
289
+ "model.layers.2.mlp.down_proj.weight": "model.safetensors",
290
+ "model.layers.2.mlp.gate_proj.biases": "model.safetensors",
291
+ "model.layers.2.mlp.gate_proj.scales": "model.safetensors",
292
+ "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
293
+ "model.layers.2.mlp.up_proj.biases": "model.safetensors",
294
+ "model.layers.2.mlp.up_proj.scales": "model.safetensors",
295
+ "model.layers.2.mlp.up_proj.weight": "model.safetensors",
296
+ "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
297
+ "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
298
+ "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
299
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
300
+ "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
301
+ "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
302
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
303
+ "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
304
+ "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
305
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
306
+ "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
307
+ "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
308
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
309
+ "model.layers.20.input_layernorm.weight": "model.safetensors",
310
+ "model.layers.20.mlp.down_proj.biases": "model.safetensors",
311
+ "model.layers.20.mlp.down_proj.scales": "model.safetensors",
312
+ "model.layers.20.mlp.down_proj.weight": "model.safetensors",
313
+ "model.layers.20.mlp.gate_proj.biases": "model.safetensors",
314
+ "model.layers.20.mlp.gate_proj.scales": "model.safetensors",
315
+ "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
316
+ "model.layers.20.mlp.up_proj.biases": "model.safetensors",
317
+ "model.layers.20.mlp.up_proj.scales": "model.safetensors",
318
+ "model.layers.20.mlp.up_proj.weight": "model.safetensors",
319
+ "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
320
+ "model.layers.20.self_attn.k_proj.biases": "model.safetensors",
321
+ "model.layers.20.self_attn.k_proj.scales": "model.safetensors",
322
+ "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
323
+ "model.layers.20.self_attn.o_proj.biases": "model.safetensors",
324
+ "model.layers.20.self_attn.o_proj.scales": "model.safetensors",
325
+ "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
326
+ "model.layers.20.self_attn.q_proj.biases": "model.safetensors",
327
+ "model.layers.20.self_attn.q_proj.scales": "model.safetensors",
328
+ "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
329
+ "model.layers.20.self_attn.v_proj.biases": "model.safetensors",
330
+ "model.layers.20.self_attn.v_proj.scales": "model.safetensors",
331
+ "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
332
+ "model.layers.21.input_layernorm.weight": "model.safetensors",
333
+ "model.layers.21.mlp.down_proj.biases": "model.safetensors",
334
+ "model.layers.21.mlp.down_proj.scales": "model.safetensors",
335
+ "model.layers.21.mlp.down_proj.weight": "model.safetensors",
336
+ "model.layers.21.mlp.gate_proj.biases": "model.safetensors",
337
+ "model.layers.21.mlp.gate_proj.scales": "model.safetensors",
338
+ "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
339
+ "model.layers.21.mlp.up_proj.biases": "model.safetensors",
340
+ "model.layers.21.mlp.up_proj.scales": "model.safetensors",
341
+ "model.layers.21.mlp.up_proj.weight": "model.safetensors",
342
+ "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
343
+ "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
344
+ "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
345
+ "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
346
+ "model.layers.21.self_attn.o_proj.biases": "model.safetensors",
347
+ "model.layers.21.self_attn.o_proj.scales": "model.safetensors",
348
+ "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
349
+ "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
350
+ "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
351
+ "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
352
+ "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
353
+ "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
354
+ "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
355
+ "model.layers.22.input_layernorm.weight": "model.safetensors",
356
+ "model.layers.22.mlp.down_proj.biases": "model.safetensors",
357
+ "model.layers.22.mlp.down_proj.scales": "model.safetensors",
358
+ "model.layers.22.mlp.down_proj.weight": "model.safetensors",
359
+ "model.layers.22.mlp.gate_proj.biases": "model.safetensors",
360
+ "model.layers.22.mlp.gate_proj.scales": "model.safetensors",
361
+ "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
362
+ "model.layers.22.mlp.up_proj.biases": "model.safetensors",
363
+ "model.layers.22.mlp.up_proj.scales": "model.safetensors",
364
+ "model.layers.22.mlp.up_proj.weight": "model.safetensors",
365
+ "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
366
+ "model.layers.22.self_attn.k_proj.biases": "model.safetensors",
367
+ "model.layers.22.self_attn.k_proj.scales": "model.safetensors",
368
+ "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
369
+ "model.layers.22.self_attn.o_proj.biases": "model.safetensors",
370
+ "model.layers.22.self_attn.o_proj.scales": "model.safetensors",
371
+ "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
372
+ "model.layers.22.self_attn.q_proj.biases": "model.safetensors",
373
+ "model.layers.22.self_attn.q_proj.scales": "model.safetensors",
374
+ "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
375
+ "model.layers.22.self_attn.v_proj.biases": "model.safetensors",
376
+ "model.layers.22.self_attn.v_proj.scales": "model.safetensors",
377
+ "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
378
+ "model.layers.23.input_layernorm.weight": "model.safetensors",
379
+ "model.layers.23.mlp.down_proj.biases": "model.safetensors",
380
+ "model.layers.23.mlp.down_proj.scales": "model.safetensors",
381
+ "model.layers.23.mlp.down_proj.weight": "model.safetensors",
382
+ "model.layers.23.mlp.gate_proj.biases": "model.safetensors",
383
+ "model.layers.23.mlp.gate_proj.scales": "model.safetensors",
384
+ "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
385
+ "model.layers.23.mlp.up_proj.biases": "model.safetensors",
386
+ "model.layers.23.mlp.up_proj.scales": "model.safetensors",
387
+ "model.layers.23.mlp.up_proj.weight": "model.safetensors",
388
+ "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
389
+ "model.layers.23.self_attn.k_proj.biases": "model.safetensors",
390
+ "model.layers.23.self_attn.k_proj.scales": "model.safetensors",
391
+ "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
392
+ "model.layers.23.self_attn.o_proj.biases": "model.safetensors",
393
+ "model.layers.23.self_attn.o_proj.scales": "model.safetensors",
394
+ "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
395
+ "model.layers.23.self_attn.q_proj.biases": "model.safetensors",
396
+ "model.layers.23.self_attn.q_proj.scales": "model.safetensors",
397
+ "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
398
+ "model.layers.23.self_attn.v_proj.biases": "model.safetensors",
399
+ "model.layers.23.self_attn.v_proj.scales": "model.safetensors",
400
+ "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
401
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
402
+ "model.layers.3.mlp.down_proj.biases": "model.safetensors",
403
+ "model.layers.3.mlp.down_proj.scales": "model.safetensors",
404
+ "model.layers.3.mlp.down_proj.weight": "model.safetensors",
405
+ "model.layers.3.mlp.gate_proj.biases": "model.safetensors",
406
+ "model.layers.3.mlp.gate_proj.scales": "model.safetensors",
407
+ "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
408
+ "model.layers.3.mlp.up_proj.biases": "model.safetensors",
409
+ "model.layers.3.mlp.up_proj.scales": "model.safetensors",
410
+ "model.layers.3.mlp.up_proj.weight": "model.safetensors",
411
+ "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
412
+ "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
413
+ "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
414
+ "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
415
+ "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
416
+ "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
417
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
418
+ "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
419
+ "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
420
+ "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
421
+ "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
422
+ "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
423
+ "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
424
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
425
+ "model.layers.4.mlp.down_proj.biases": "model.safetensors",
426
+ "model.layers.4.mlp.down_proj.scales": "model.safetensors",
427
+ "model.layers.4.mlp.down_proj.weight": "model.safetensors",
428
+ "model.layers.4.mlp.gate_proj.biases": "model.safetensors",
429
+ "model.layers.4.mlp.gate_proj.scales": "model.safetensors",
430
+ "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
431
+ "model.layers.4.mlp.up_proj.biases": "model.safetensors",
432
+ "model.layers.4.mlp.up_proj.scales": "model.safetensors",
433
+ "model.layers.4.mlp.up_proj.weight": "model.safetensors",
434
+ "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
435
+ "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
436
+ "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
437
+ "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
438
+ "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
439
+ "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
440
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
441
+ "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
442
+ "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
443
+ "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
444
+ "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
445
+ "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
446
+ "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
447
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
448
+ "model.layers.5.mlp.down_proj.biases": "model.safetensors",
449
+ "model.layers.5.mlp.down_proj.scales": "model.safetensors",
450
+ "model.layers.5.mlp.down_proj.weight": "model.safetensors",
451
+ "model.layers.5.mlp.gate_proj.biases": "model.safetensors",
452
+ "model.layers.5.mlp.gate_proj.scales": "model.safetensors",
453
+ "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
454
+ "model.layers.5.mlp.up_proj.biases": "model.safetensors",
455
+ "model.layers.5.mlp.up_proj.scales": "model.safetensors",
456
+ "model.layers.5.mlp.up_proj.weight": "model.safetensors",
457
+ "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
458
+ "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
459
+ "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
460
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
461
+ "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
462
+ "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
463
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
464
+ "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
465
+ "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
466
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
467
+ "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
468
+ "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
469
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
470
+ "model.layers.6.input_layernorm.weight": "model.safetensors",
471
+ "model.layers.6.mlp.down_proj.biases": "model.safetensors",
472
+ "model.layers.6.mlp.down_proj.scales": "model.safetensors",
473
+ "model.layers.6.mlp.down_proj.weight": "model.safetensors",
474
+ "model.layers.6.mlp.gate_proj.biases": "model.safetensors",
475
+ "model.layers.6.mlp.gate_proj.scales": "model.safetensors",
476
+ "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
477
+ "model.layers.6.mlp.up_proj.biases": "model.safetensors",
478
+ "model.layers.6.mlp.up_proj.scales": "model.safetensors",
479
+ "model.layers.6.mlp.up_proj.weight": "model.safetensors",
480
+ "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
481
+ "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
482
+ "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
483
+ "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
484
+ "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
485
+ "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
486
+ "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
487
+ "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
488
+ "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
489
+ "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
490
+ "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
491
+ "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
492
+ "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
493
+ "model.layers.7.input_layernorm.weight": "model.safetensors",
494
+ "model.layers.7.mlp.down_proj.biases": "model.safetensors",
495
+ "model.layers.7.mlp.down_proj.scales": "model.safetensors",
496
+ "model.layers.7.mlp.down_proj.weight": "model.safetensors",
497
+ "model.layers.7.mlp.gate_proj.biases": "model.safetensors",
498
+ "model.layers.7.mlp.gate_proj.scales": "model.safetensors",
499
+ "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
500
+ "model.layers.7.mlp.up_proj.biases": "model.safetensors",
501
+ "model.layers.7.mlp.up_proj.scales": "model.safetensors",
502
+ "model.layers.7.mlp.up_proj.weight": "model.safetensors",
503
+ "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
504
+ "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
505
+ "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
506
+ "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
507
+ "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
508
+ "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
509
+ "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
510
+ "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
511
+ "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
512
+ "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
513
+ "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
514
+ "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
515
+ "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
516
+ "model.layers.8.input_layernorm.weight": "model.safetensors",
517
+ "model.layers.8.mlp.down_proj.biases": "model.safetensors",
518
+ "model.layers.8.mlp.down_proj.scales": "model.safetensors",
519
+ "model.layers.8.mlp.down_proj.weight": "model.safetensors",
520
+ "model.layers.8.mlp.gate_proj.biases": "model.safetensors",
521
+ "model.layers.8.mlp.gate_proj.scales": "model.safetensors",
522
+ "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
523
+ "model.layers.8.mlp.up_proj.biases": "model.safetensors",
524
+ "model.layers.8.mlp.up_proj.scales": "model.safetensors",
525
+ "model.layers.8.mlp.up_proj.weight": "model.safetensors",
526
+ "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
527
+ "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
528
+ "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
529
+ "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
530
+ "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
531
+ "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
532
+ "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
533
+ "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
534
+ "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
535
+ "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
536
+ "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
537
+ "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
538
+ "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
539
+ "model.layers.9.input_layernorm.weight": "model.safetensors",
540
+ "model.layers.9.mlp.down_proj.biases": "model.safetensors",
541
+ "model.layers.9.mlp.down_proj.scales": "model.safetensors",
542
+ "model.layers.9.mlp.down_proj.weight": "model.safetensors",
543
+ "model.layers.9.mlp.gate_proj.biases": "model.safetensors",
544
+ "model.layers.9.mlp.gate_proj.scales": "model.safetensors",
545
+ "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
546
+ "model.layers.9.mlp.up_proj.biases": "model.safetensors",
547
+ "model.layers.9.mlp.up_proj.scales": "model.safetensors",
548
+ "model.layers.9.mlp.up_proj.weight": "model.safetensors",
549
+ "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
550
+ "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
551
+ "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
552
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
553
+ "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
554
+ "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
555
+ "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
556
+ "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
557
+ "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
558
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
559
+ "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
560
+ "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
561
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
562
+ "model.norm.weight": "model.safetensors"
563
+ }
564
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "sep_token": {
31
+ "content": "</s>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "unk_token": {
38
+ "content": "<unk>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
+ }
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 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
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
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|prompt|>' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% elif message['role'] == 'assistant' %}{{ '<|answer|>' + message['content'] + eos_token }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|answer|>' }}{% endif %}{% endfor %}",
34
+ "clean_up_tokenization_spaces": false,
35
+ "cls_token": "</s>",
36
+ "eos_token": "</s>",
37
+ "legacy": true,
38
+ "model_max_length": 1000000000000000019884624838656,
39
+ "pad_token": "<unk>",
40
+ "sep_token": "</s>",
41
+ "sp_model_kwargs": {},
42
+ "spaces_between_special_tokens": false,
43
+ "tokenizer_class": "LlamaTokenizer",
44
+ "unk_token": "<unk>",
45
+ "use_default_system_prompt": false
46
+ }