sharpenb commited on
Commit
887b335
1 Parent(s): 114d13b

ea559429621e1f6fad2eb6788686670127b701c0143132670c1d8adc6a1860fc

Browse files
README.md ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ thumbnail: "https://assets-global.website-files.com/646b351987a8d8ce158d1940/64ec9e96b4334c0e1ac41504_Logo%20with%20white%20text.svg"
3
+ base_model: McGill-NLP/Llama-3-8B-Web
4
+ metrics:
5
+ - memory_disk
6
+ - memory_inference
7
+ - inference_latency
8
+ - inference_throughput
9
+ - inference_CO2_emissions
10
+ - inference_energy_consumption
11
+ tags:
12
+ - pruna-ai
13
+ ---
14
+ <!-- header start -->
15
+ <!-- 200823 -->
16
+ <div style="width: auto; margin-left: auto; margin-right: auto">
17
+ <a href="https://www.pruna.ai/" target="_blank" rel="noopener noreferrer">
18
+ <img src="https://i.imgur.com/eDAlcgk.png" alt="PrunaAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
19
+ </a>
20
+ </div>
21
+ <!-- header end -->
22
+
23
+ [![Twitter](https://img.shields.io/twitter/follow/PrunaAI?style=social)](https://twitter.com/PrunaAI)
24
+ [![GitHub](https://img.shields.io/github/followers/PrunaAI?label=Follow%20%40PrunaAI&style=social)](https://github.com/PrunaAI)
25
+ [![LinkedIn](https://img.shields.io/badge/LinkedIn-Connect-blue)](https://www.linkedin.com/company/93832878/admin/feed/posts/?feedType=following)
26
+ [![Discord](https://img.shields.io/badge/Discord-Join%20Us-blue?style=social&logo=discord)](https://discord.gg/CP4VSgck)
27
+
28
+ # Simply make AI models cheaper, smaller, faster, and greener!
29
+
30
+ - Give a thumbs up if you like this model!
31
+ - Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact).
32
+ - Request access to easily compress your *own* AI models [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
33
+ - Read the documentations to know more [here](https://pruna-ai-pruna.readthedocs-hosted.com/en/latest/)
34
+ - Join Pruna AI community on Discord [here](https://discord.gg/CP4VSgck) to share feedback/suggestions or get help.
35
+
36
+ ## Results
37
+
38
+ ![image info](./plots.png)
39
+
40
+ **Frequently Asked Questions**
41
+ - ***How does the compression work?*** The model is compressed with awq.
42
+ - ***How does the model quality change?*** The quality of the model output might vary compared to the base model.
43
+ - ***How is the model efficiency evaluated?*** These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in `model/smash_config.json` and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.
44
+ - ***What is the model format?*** We use safetensors.
45
+ - ***What calibration data has been used?*** If needed by the compression method, we used WikiText as the calibration data.
46
+ - ***What is the naming convention for Pruna Huggingface models?*** We take the original model name and append "turbo", "tiny", or "green" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.
47
+ - ***How to compress my own models?*** You can request premium access to more compression methods and tech support for your specific use-cases [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
48
+ - ***What are "first" metrics?*** Results mentioning "first" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.
49
+ - ***What are "Sync" and "Async" metrics?*** "Sync" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. "Async" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.
50
+
51
+ ## Setup
52
+
53
+ You can run the smashed model with these steps:
54
+
55
+ 0. Check requirements from the original repo McGill-NLP/Llama-3-8B-Web installed. In particular, check python, cuda, and transformers versions.
56
+ 1. Make sure that you have installed quantization related packages.
57
+ ```bash
58
+ pip install autoawq
59
+ ```
60
+ 2. Load & run the model.
61
+ ```python
62
+ from transformers import AutoModelForCausalLM, AutoTokenizer
63
+ from awq import AutoAWQForCausalLM
64
+
65
+ model = AutoAWQForCausalLM.from_quantized("PrunaAI/McGill-NLP-Llama-3-8B-Web-AWQ-4bit-smashed", trust_remote_code=True, device_map='auto')
66
+ tokenizer = AutoTokenizer.from_pretrained("McGill-NLP/Llama-3-8B-Web")
67
+
68
+ input_ids = tokenizer("What is the color of prunes?,", return_tensors='pt').to(model.device)["input_ids"]
69
+
70
+ outputs = model.generate(input_ids, max_new_tokens=216)
71
+ tokenizer.decode(outputs[0])
72
+ ```
73
+
74
+ ## Configurations
75
+
76
+ The configuration info are in `smash_config.json`.
77
+
78
+ ## Credits & License
79
+
80
+ The license of the smashed model follows the license of the original model. Please check the license of the original model McGill-NLP/Llama-3-8B-Web before using this model which provided the base model. The license of the `pruna-engine` is [here](https://pypi.org/project/pruna-engine/) on Pypi.
81
+
82
+ ## Want to compress other models?
83
+
84
+ - Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact).
85
+ - Request access to easily compress your own AI models [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/tmp/tmp6tqwsht_",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "quantization_config": {
21
+ "bits": 4,
22
+ "group_size": 128,
23
+ "modules_to_not_convert": null,
24
+ "quant_method": "awq",
25
+ "version": "gemm",
26
+ "zero_point": true
27
+ },
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_scaling": null,
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "float16",
33
+ "transformers_version": "4.40.0",
34
+ "use_cache": false,
35
+ "vocab_size": 128256
36
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 128001,
7
+ 128009
8
+ ],
9
+ "transformers_version": "4.40.0"
10
+ }
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc7f7c99a906f9b3130e120dd1e28803e9337de4aca7bd53a043247264cb32bd
3
+ size 1050673280
model.safetensors.index.json ADDED
@@ -0,0 +1,746 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5727854592
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
21
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
22
+ "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
23
+ "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
24
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
25
+ "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
26
+ "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
27
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
28
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
32
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
33
+ "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
34
+ "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
35
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
36
+ "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
37
+ "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
38
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
39
+ "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
40
+ "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
41
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
42
+ "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
43
+ "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
44
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
45
+ "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
46
+ "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
47
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
48
+ "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
49
+ "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
50
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
51
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
54
+ "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
55
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
56
+ "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
57
+ "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
58
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
59
+ "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
60
+ "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
61
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
62
+ "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
63
+ "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
64
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
65
+ "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
66
+ "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
67
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
68
+ "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
69
+ "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
70
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
71
+ "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
72
+ "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
73
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
74
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
77
+ "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
78
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
79
+ "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
80
+ "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
81
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
82
+ "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
83
+ "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
84
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
85
+ "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
86
+ "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
87
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
88
+ "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
89
+ "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
90
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
91
+ "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
92
+ "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
93
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
94
+ "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
95
+ "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
96
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
97
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
100
+ "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
101
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
102
+ "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
103
+ "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
104
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
105
+ "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
106
+ "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
107
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
108
+ "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
109
+ "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
110
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
111
+ "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
112
+ "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
113
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
114
+ "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
115
+ "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
116
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
117
+ "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
118
+ "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
119
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
120
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
123
+ "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
124
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
125
+ "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
126
+ "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
127
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
128
+ "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
129
+ "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
130
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
131
+ "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
132
+ "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
133
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
134
+ "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
135
+ "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
136
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
137
+ "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
138
+ "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
139
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
140
+ "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
141
+ "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
142
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
143
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
146
+ "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
147
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
148
+ "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
149
+ "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
150
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
151
+ "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
152
+ "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
153
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
154
+ "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
155
+ "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
156
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
157
+ "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
158
+ "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
159
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
160
+ "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
161
+ "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
162
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
163
+ "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
164
+ "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
165
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
166
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
169
+ "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
170
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
171
+ "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
172
+ "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
173
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
174
+ "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
175
+ "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
176
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
177
+ "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
178
+ "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
179
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
180
+ "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
181
+ "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
182
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
183
+ "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
184
+ "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
185
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
186
+ "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
187
+ "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
188
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
189
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
192
+ "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
193
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
194
+ "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
195
+ "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
196
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
197
+ "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
198
+ "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
199
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
200
+ "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
201
+ "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
202
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
203
+ "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
204
+ "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
205
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
206
+ "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
207
+ "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
208
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
209
+ "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
210
+ "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
211
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
212
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
215
+ "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
216
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
217
+ "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
218
+ "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
219
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
220
+ "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
221
+ "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
222
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
223
+ "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
224
+ "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
225
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
226
+ "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
227
+ "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
228
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
229
+ "model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
230
+ "model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
231
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
232
+ "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
233
+ "model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
234
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
235
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
238
+ "model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
239
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
240
+ "model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
241
+ "model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
242
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
243
+ "model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
244
+ "model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
245
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
246
+ "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
247
+ "model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
248
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
249
+ "model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
250
+ "model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
251
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
252
+ "model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
253
+ "model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
254
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
255
+ "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
256
+ "model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
257
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
258
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
261
+ "model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
262
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
263
+ "model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
264
+ "model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
265
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
266
+ "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
267
+ "model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
268
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
269
+ "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
270
+ "model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
271
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
272
+ "model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
273
+ "model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
274
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
275
+ "model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
276
+ "model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
277
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
278
+ "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
279
+ "model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
280
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
281
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
284
+ "model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
285
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
286
+ "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
287
+ "model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
288
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
289
+ "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
290
+ "model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
291
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
292
+ "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
293
+ "model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
294
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
295
+ "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
296
+ "model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
297
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
298
+ "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
299
+ "model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
300
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
301
+ "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
302
+ "model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
303
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
304
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
305
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
306
+ "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
307
+ "model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
308
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
309
+ "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
310
+ "model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
311
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
312
+ "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
313
+ "model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
314
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
315
+ "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
316
+ "model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
317
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
318
+ "model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
319
+ "model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
320
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
321
+ "model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
322
+ "model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
323
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
324
+ "model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
325
+ "model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
326
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
327
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
328
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
329
+ "model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
330
+ "model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
331
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
332
+ "model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
333
+ "model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
334
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
335
+ "model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
336
+ "model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
337
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
338
+ "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
339
+ "model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
340
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
341
+ "model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
342
+ "model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
343
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
344
+ "model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
345
+ "model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
346
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
347
+ "model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
348
+ "model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
349
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
350
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
351
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
352
+ "model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
353
+ "model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
354
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
355
+ "model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
356
+ "model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
357
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
358
+ "model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
359
+ "model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
360
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
361
+ "model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
362
+ "model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
363
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
364
+ "model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
365
+ "model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
366
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
367
+ "model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
368
+ "model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
369
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
370
+ "model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
371
+ "model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
372
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
373
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
374
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
376
+ "model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
377
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
378
+ "model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
379
+ "model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
380
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
381
+ "model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
382
+ "model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
383
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
384
+ "model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
385
+ "model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
386
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
387
+ "model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
388
+ "model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
389
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
390
+ "model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
391
+ "model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
392
+ "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
393
+ "model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
394
+ "model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
395
+ "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
396
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
398
+ "model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
399
+ "model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
400
+ "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
401
+ "model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
402
+ "model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
403
+ "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
404
+ "model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
405
+ "model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
406
+ "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
407
+ "model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
408
+ "model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
409
+ "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
410
+ "model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
411
+ "model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
412
+ "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
413
+ "model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
414
+ "model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
415
+ "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
416
+ "model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
417
+ "model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
418
+ "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
419
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
420
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
422
+ "model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
423
+ "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
424
+ "model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
425
+ "model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
426
+ "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
427
+ "model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
428
+ "model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
429
+ "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
430
+ "model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
431
+ "model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
432
+ "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
433
+ "model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
434
+ "model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
435
+ "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
436
+ "model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
437
+ "model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
438
+ "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
439
+ "model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
440
+ "model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
441
+ "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
442
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
443
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
444
+ "model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
445
+ "model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
446
+ "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
447
+ "model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
448
+ "model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
449
+ "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
450
+ "model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
451
+ "model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
452
+ "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
453
+ "model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
454
+ "model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
455
+ "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
456
+ "model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
457
+ "model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
458
+ "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
459
+ "model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
460
+ "model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
461
+ "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
462
+ "model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
463
+ "model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
464
+ "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
465
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
466
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
467
+ "model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
468
+ "model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
469
+ "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
470
+ "model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
471
+ "model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
472
+ "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
473
+ "model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
474
+ "model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
475
+ "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
476
+ "model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
477
+ "model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
478
+ "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
479
+ "model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
480
+ "model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
481
+ "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
482
+ "model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
483
+ "model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
484
+ "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
485
+ "model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
486
+ "model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
487
+ "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
488
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
489
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
490
+ "model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
491
+ "model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
492
+ "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
493
+ "model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
494
+ "model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
495
+ "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
496
+ "model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
497
+ "model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
498
+ "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
499
+ "model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
500
+ "model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
501
+ "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
502
+ "model.layers.21.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
503
+ "model.layers.21.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
504
+ "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
505
+ "model.layers.21.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
506
+ "model.layers.21.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
507
+ "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
508
+ "model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
509
+ "model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
510
+ "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
511
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
512
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
513
+ "model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
514
+ "model.layers.22.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
515
+ "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
516
+ "model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
517
+ "model.layers.22.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
518
+ "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
519
+ "model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
520
+ "model.layers.22.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
521
+ "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
522
+ "model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
523
+ "model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
524
+ "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
525
+ "model.layers.22.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
526
+ "model.layers.22.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
527
+ "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
528
+ "model.layers.22.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
529
+ "model.layers.22.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
530
+ "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
531
+ "model.layers.22.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
532
+ "model.layers.22.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
533
+ "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
534
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
535
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
536
+ "model.layers.23.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
537
+ "model.layers.23.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
538
+ "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
539
+ "model.layers.23.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
540
+ "model.layers.23.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
541
+ "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
542
+ "model.layers.23.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
543
+ "model.layers.23.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
544
+ "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
545
+ "model.layers.23.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
546
+ "model.layers.23.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
547
+ "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
548
+ "model.layers.23.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
549
+ "model.layers.23.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
550
+ "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
551
+ "model.layers.23.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
552
+ "model.layers.23.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
553
+ "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
554
+ "model.layers.23.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
555
+ "model.layers.23.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
556
+ "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
557
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
558
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
559
+ "model.layers.24.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
560
+ "model.layers.24.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
561
+ "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
562
+ "model.layers.24.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
563
+ "model.layers.24.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
564
+ "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
565
+ "model.layers.24.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
566
+ "model.layers.24.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
567
+ "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
568
+ "model.layers.24.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
569
+ "model.layers.24.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
570
+ "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
571
+ "model.layers.24.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
572
+ "model.layers.24.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
573
+ "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
574
+ "model.layers.24.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
575
+ "model.layers.24.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
576
+ "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
577
+ "model.layers.24.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
578
+ "model.layers.24.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
579
+ "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
580
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
581
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
582
+ "model.layers.25.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
583
+ "model.layers.25.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
584
+ "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
585
+ "model.layers.25.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
586
+ "model.layers.25.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
587
+ "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
588
+ "model.layers.25.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
589
+ "model.layers.25.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
590
+ "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
591
+ "model.layers.25.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
592
+ "model.layers.25.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
593
+ "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
594
+ "model.layers.25.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
595
+ "model.layers.25.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
596
+ "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
597
+ "model.layers.25.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
598
+ "model.layers.25.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
599
+ "model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
600
+ "model.layers.25.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
601
+ "model.layers.25.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
602
+ "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
603
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
604
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
605
+ "model.layers.26.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
606
+ "model.layers.26.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
607
+ "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
608
+ "model.layers.26.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
609
+ "model.layers.26.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
610
+ "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
611
+ "model.layers.26.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
612
+ "model.layers.26.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
613
+ "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
614
+ "model.layers.26.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
615
+ "model.layers.26.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
616
+ "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
617
+ "model.layers.26.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
618
+ "model.layers.26.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
619
+ "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
620
+ "model.layers.26.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
621
+ "model.layers.26.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
622
+ "model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
623
+ "model.layers.26.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
624
+ "model.layers.26.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
625
+ "model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
626
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
627
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
628
+ "model.layers.27.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
629
+ "model.layers.27.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
630
+ "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
631
+ "model.layers.27.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
632
+ "model.layers.27.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
633
+ "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
634
+ "model.layers.27.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
635
+ "model.layers.27.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
636
+ "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
637
+ "model.layers.27.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
638
+ "model.layers.27.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
639
+ "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
640
+ "model.layers.27.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
641
+ "model.layers.27.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
642
+ "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
643
+ "model.layers.27.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
644
+ "model.layers.27.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
645
+ "model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
646
+ "model.layers.27.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
647
+ "model.layers.27.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
648
+ "model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
649
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
650
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
651
+ "model.layers.28.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
652
+ "model.layers.28.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
653
+ "model.layers.28.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
654
+ "model.layers.28.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
655
+ "model.layers.28.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
656
+ "model.layers.28.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
657
+ "model.layers.28.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
658
+ "model.layers.28.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
659
+ "model.layers.28.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
660
+ "model.layers.28.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
661
+ "model.layers.28.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
662
+ "model.layers.28.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
663
+ "model.layers.28.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
664
+ "model.layers.28.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
665
+ "model.layers.28.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
666
+ "model.layers.28.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
667
+ "model.layers.28.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
668
+ "model.layers.28.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
669
+ "model.layers.28.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
670
+ "model.layers.28.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
671
+ "model.layers.28.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
672
+ "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
673
+ "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
674
+ "model.layers.29.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
675
+ "model.layers.29.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
676
+ "model.layers.29.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
677
+ "model.layers.29.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
678
+ "model.layers.29.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
679
+ "model.layers.29.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
680
+ "model.layers.29.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
681
+ "model.layers.29.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
682
+ "model.layers.29.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
683
+ "model.layers.29.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
684
+ "model.layers.29.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
685
+ "model.layers.29.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
686
+ "model.layers.29.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
687
+ "model.layers.29.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
688
+ "model.layers.29.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
689
+ "model.layers.29.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
690
+ "model.layers.29.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
691
+ "model.layers.29.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
692
+ "model.layers.29.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
693
+ "model.layers.29.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
694
+ "model.layers.29.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
695
+ "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
696
+ "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
697
+ "model.layers.30.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
698
+ "model.layers.30.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
699
+ "model.layers.30.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
700
+ "model.layers.30.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
701
+ "model.layers.30.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
702
+ "model.layers.30.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
703
+ "model.layers.30.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
704
+ "model.layers.30.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
705
+ "model.layers.30.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
706
+ "model.layers.30.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
707
+ "model.layers.30.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
708
+ "model.layers.30.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
709
+ "model.layers.30.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
710
+ "model.layers.30.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
711
+ "model.layers.30.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
712
+ "model.layers.30.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
713
+ "model.layers.30.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
714
+ "model.layers.30.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
715
+ "model.layers.30.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
716
+ "model.layers.30.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
717
+ "model.layers.30.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
718
+ "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
719
+ "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
720
+ "model.layers.31.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
721
+ "model.layers.31.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
722
+ "model.layers.31.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
723
+ "model.layers.31.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
724
+ "model.layers.31.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
725
+ "model.layers.31.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
726
+ "model.layers.31.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
727
+ "model.layers.31.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
728
+ "model.layers.31.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
729
+ "model.layers.31.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
730
+ "model.layers.31.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
731
+ "model.layers.31.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
732
+ "model.layers.31.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
733
+ "model.layers.31.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
734
+ "model.layers.31.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
735
+ "model.layers.31.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
736
+ "model.layers.31.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
737
+ "model.layers.31.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
738
+ "model.layers.31.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
739
+ "model.layers.31.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
740
+ "model.layers.31.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
741
+ "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
742
+ "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
743
+ "model.norm.weight": "model-00001-of-00002.safetensors",
744
+ "lm_head.weight": "model-00002-of-00002.safetensors"
745
+ }
746
+ }
plots.png ADDED
results.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_current_gpu_type": "NVIDIA A100-PCIE-40GB",
3
+ "base_current_gpu_total_memory": 40339.3125,
4
+ "base_token_generation_latency_sync": 76.91910247802734,
5
+ "base_token_generation_latency_async": 76.82386375963688,
6
+ "base_token_generation_throughput_sync": 0.013000671715919452,
7
+ "base_token_generation_throughput_async": 0.013016788678173697,
8
+ "base_token_generation_CO2_emissions": 3.9930267542867864e-05,
9
+ "base_token_generation_energy_consumption": 0.013695786831045186,
10
+ "base_inference_latency_sync": 75.31489334106445,
11
+ "base_inference_latency_async": 74.6358871459961,
12
+ "base_inference_throughput_sync": 0.013277586352960592,
13
+ "base_inference_throughput_async": 0.013398380299866857,
14
+ "base_inference_CO2_emissions": 4.072261623993283e-05,
15
+ "base_inference_energy_consumption": 0.00011265253741674144,
16
+ "smashed_current_gpu_type": "NVIDIA A100-PCIE-40GB",
17
+ "smashed_current_gpu_total_memory": 40339.3125,
18
+ "smashed_token_generation_latency_sync": 49.13712501525879,
19
+ "smashed_token_generation_latency_async": 48.9015968516469,
20
+ "smashed_token_generation_throughput_sync": 0.02035121101793125,
21
+ "smashed_token_generation_throughput_async": 0.02044922997164503,
22
+ "smashed_token_generation_CO2_emissions": 3.524599859739772e-05,
23
+ "smashed_token_generation_energy_consumption": 0.009180102018160505,
24
+ "smashed_inference_latency_sync": 52.06343727111816,
25
+ "smashed_inference_latency_async": 49.8340368270874,
26
+ "smashed_inference_throughput_sync": 0.019207337287250974,
27
+ "smashed_inference_throughput_async": 0.0200666063531993,
28
+ "smashed_inference_CO2_emissions": 3.379301910600281e-05,
29
+ "smashed_inference_energy_consumption": 9.774841757057516e-05
30
+ }
smash_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "api_key": null,
3
+ "verify_url": "http://johnrachwan.pythonanywhere.com",
4
+ "smash_config": {
5
+ "pruners": "[]",
6
+ "pruning_ratio": 0.0,
7
+ "factorizers": "[]",
8
+ "quantizers": "['awq']",
9
+ "weight_quantization_bits": 4,
10
+ "output_deviation": 0.01,
11
+ "compilers": "[]",
12
+ "static_batch": true,
13
+ "static_shape": true,
14
+ "controlnet": "None",
15
+ "unet_dim": 4,
16
+ "device": "cuda",
17
+ "cache_dir": "/ceph/hdd/staff/charpent/.cache/models8o3cnft5",
18
+ "batch_size": 1,
19
+ "model_name": "McGill-NLP/Llama-3-8B-Web",
20
+ "task": "text_text_generation",
21
+ "max_batch_size": 1,
22
+ "qtype_weight": "torch.qint8",
23
+ "qtype_activation": "torch.quint8",
24
+ "qobserver": "<class 'torch.ao.quantization.observer.MinMaxObserver'>",
25
+ "qscheme": "torch.per_tensor_symmetric",
26
+ "qconfig": "x86",
27
+ "group_size": 128,
28
+ "damp_percent": 0.1,
29
+ "save_load_fn": "hf-awq"
30
+ }
31
+ }