sharpenb commited on
Commit
bac6982
·
verified ·
1 Parent(s): f40e60b

Upload folder using huggingface_hub (#1)

Browse files

- 870fdb1ea98dc8ea96a596bc4d8bf687b7571a0bde24aae607d420cada096011 (c80c21cb79358cc51326e6db3b88d42089ed83a6)
- 0f6aedbcb26bff2671b048a7f0f5d9f4bddb08acdaaad5804d5bac55e57bf918 (95892cf24233d1bdc2bdb3b91afe4a560f54cfa9)

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: AI-Sweden-Models/gpt-sw3-6.7b-v2-instruct
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://docs.pruna.ai/en/latest/setup/pip.html" target="_blank" rel="noopener noreferrer">
18
+ <img src="https://imgur.com/rVAgqMY.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/rskEr4BZJx)
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 llm-int8.
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 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 AI-Sweden-Models/gpt-sw3-6.7b-v2-instruct 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 transformers accelerate bitsandbytes>0.37.0
59
+ ```
60
+ 2. Load & run the model.
61
+ ```python
62
+ from transformers import AutoModelForCausalLM, AutoTokenizer
63
+
64
+
65
+ model = AutoModelForCausalLM.from_pretrained("PrunaAI/AI-Sweden-Models-gpt-sw3-6.7b-v2-instruct-bnb-8bit-smashed", trust_remote_code=True, device_map='auto')
66
+ tokenizer = AutoTokenizer.from_pretrained("AI-Sweden-Models/gpt-sw3-6.7b-v2-instruct")
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 AI-Sweden-Models/gpt-sw3-6.7b-v2-instruct 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
+ - Do it by yourself [here](https://docs.pruna.ai/en/latest/setup/pip.html).
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/covalent/.cache/models/tmptkau2ene_8d_qpjv",
3
+ "activation_function": "gelu",
4
+ "apply_query_key_layer_scaling": true,
5
+ "architectures": [
6
+ "GPT2LMHeadModel"
7
+ ],
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 1,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 1,
12
+ "initializer_range": 0.01,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "max_length": null,
15
+ "model_type": "gpt2",
16
+ "n_ctx": 2048,
17
+ "n_embd": 4096,
18
+ "n_head": 32,
19
+ "n_inner": 16384,
20
+ "n_layer": 32,
21
+ "n_positions": 2048,
22
+ "normalize_attention_scores": true,
23
+ "pad_token_id": 0,
24
+ "quantization_config": {
25
+ "_load_in_4bit": false,
26
+ "_load_in_8bit": true,
27
+ "bnb_4bit_compute_dtype": "bfloat16",
28
+ "bnb_4bit_quant_storage": "uint8",
29
+ "bnb_4bit_quant_type": "fp4",
30
+ "bnb_4bit_use_double_quant": false,
31
+ "llm_int8_enable_fp32_cpu_offload": false,
32
+ "llm_int8_has_fp16_weight": false,
33
+ "llm_int8_skip_modules": [
34
+ "lm_head"
35
+ ],
36
+ "llm_int8_threshold": 6.0,
37
+ "load_in_4bit": false,
38
+ "load_in_8bit": true,
39
+ "quant_method": "bitsandbytes"
40
+ },
41
+ "reorder_and_upcast_attn": false,
42
+ "resid_pdrop": 0.1,
43
+ "scale_attn_by_inverse_layer_idx": false,
44
+ "scale_attn_weights": true,
45
+ "summary_activation": null,
46
+ "summary_first_dropout": 0.1,
47
+ "summary_proj_to_labels": true,
48
+ "summary_type": "cls_index",
49
+ "summary_use_proj": true,
50
+ "tokenizer_class": "GPTSw3Tokenizer",
51
+ "torch_dtype": "float16",
52
+ "transformers_version": "4.46.2",
53
+ "use_cache": true,
54
+ "vocab_size": 64000,
55
+ "api_key": null
56
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 1,
5
+ "max_length": 2048,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.46.2"
8
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:376b6f40879e7d4827d723850311a511d125ef6105aa733fa70ef5490c4388ac
3
+ size 4975898920
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c8af103f97fc5c7389933faf2c99c77a5d2d5df0caf205ad9599184966771c0
3
+ size 2015825920
model.safetensors.index.json ADDED
@@ -0,0 +1,651 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6991659136
4
+ },
5
+ "weight_map": {
6
+ "transformer.h.0.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
7
+ "transformer.h.0.attn.c_attn.bias": "model-00001-of-00002.safetensors",
8
+ "transformer.h.0.attn.c_attn.weight": "model-00001-of-00002.safetensors",
9
+ "transformer.h.0.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
10
+ "transformer.h.0.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
11
+ "transformer.h.0.attn.c_proj.bias": "model-00001-of-00002.safetensors",
12
+ "transformer.h.0.attn.c_proj.weight": "model-00001-of-00002.safetensors",
13
+ "transformer.h.0.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
14
+ "transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
15
+ "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
16
+ "transformer.h.0.ln_2.bias": "model-00001-of-00002.safetensors",
17
+ "transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
18
+ "transformer.h.0.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
19
+ "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
20
+ "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
21
+ "transformer.h.0.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
22
+ "transformer.h.0.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
23
+ "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
24
+ "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
25
+ "transformer.h.0.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
26
+ "transformer.h.1.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
27
+ "transformer.h.1.attn.c_attn.bias": "model-00001-of-00002.safetensors",
28
+ "transformer.h.1.attn.c_attn.weight": "model-00001-of-00002.safetensors",
29
+ "transformer.h.1.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
30
+ "transformer.h.1.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
31
+ "transformer.h.1.attn.c_proj.bias": "model-00001-of-00002.safetensors",
32
+ "transformer.h.1.attn.c_proj.weight": "model-00001-of-00002.safetensors",
33
+ "transformer.h.1.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
34
+ "transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
35
+ "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
36
+ "transformer.h.1.ln_2.bias": "model-00001-of-00002.safetensors",
37
+ "transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
38
+ "transformer.h.1.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
39
+ "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
40
+ "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
41
+ "transformer.h.1.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
42
+ "transformer.h.1.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
43
+ "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
44
+ "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
45
+ "transformer.h.1.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
46
+ "transformer.h.10.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
47
+ "transformer.h.10.attn.c_attn.bias": "model-00001-of-00002.safetensors",
48
+ "transformer.h.10.attn.c_attn.weight": "model-00001-of-00002.safetensors",
49
+ "transformer.h.10.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
50
+ "transformer.h.10.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
51
+ "transformer.h.10.attn.c_proj.bias": "model-00001-of-00002.safetensors",
52
+ "transformer.h.10.attn.c_proj.weight": "model-00001-of-00002.safetensors",
53
+ "transformer.h.10.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
54
+ "transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
55
+ "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
56
+ "transformer.h.10.ln_2.bias": "model-00001-of-00002.safetensors",
57
+ "transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
58
+ "transformer.h.10.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
59
+ "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
60
+ "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
61
+ "transformer.h.10.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
62
+ "transformer.h.10.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
63
+ "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
64
+ "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
65
+ "transformer.h.10.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
66
+ "transformer.h.11.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
67
+ "transformer.h.11.attn.c_attn.bias": "model-00001-of-00002.safetensors",
68
+ "transformer.h.11.attn.c_attn.weight": "model-00001-of-00002.safetensors",
69
+ "transformer.h.11.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
70
+ "transformer.h.11.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
71
+ "transformer.h.11.attn.c_proj.bias": "model-00001-of-00002.safetensors",
72
+ "transformer.h.11.attn.c_proj.weight": "model-00001-of-00002.safetensors",
73
+ "transformer.h.11.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
74
+ "transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
75
+ "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
76
+ "transformer.h.11.ln_2.bias": "model-00001-of-00002.safetensors",
77
+ "transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
78
+ "transformer.h.11.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
79
+ "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
80
+ "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
81
+ "transformer.h.11.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
82
+ "transformer.h.11.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
83
+ "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
84
+ "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
85
+ "transformer.h.11.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
86
+ "transformer.h.12.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
87
+ "transformer.h.12.attn.c_attn.bias": "model-00001-of-00002.safetensors",
88
+ "transformer.h.12.attn.c_attn.weight": "model-00001-of-00002.safetensors",
89
+ "transformer.h.12.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
90
+ "transformer.h.12.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
91
+ "transformer.h.12.attn.c_proj.bias": "model-00001-of-00002.safetensors",
92
+ "transformer.h.12.attn.c_proj.weight": "model-00001-of-00002.safetensors",
93
+ "transformer.h.12.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
94
+ "transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
95
+ "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
96
+ "transformer.h.12.ln_2.bias": "model-00001-of-00002.safetensors",
97
+ "transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
98
+ "transformer.h.12.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
99
+ "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
100
+ "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
101
+ "transformer.h.12.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
102
+ "transformer.h.12.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
103
+ "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
104
+ "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
105
+ "transformer.h.12.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
106
+ "transformer.h.13.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
107
+ "transformer.h.13.attn.c_attn.bias": "model-00001-of-00002.safetensors",
108
+ "transformer.h.13.attn.c_attn.weight": "model-00001-of-00002.safetensors",
109
+ "transformer.h.13.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
110
+ "transformer.h.13.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
111
+ "transformer.h.13.attn.c_proj.bias": "model-00001-of-00002.safetensors",
112
+ "transformer.h.13.attn.c_proj.weight": "model-00001-of-00002.safetensors",
113
+ "transformer.h.13.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
114
+ "transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
115
+ "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
116
+ "transformer.h.13.ln_2.bias": "model-00001-of-00002.safetensors",
117
+ "transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
118
+ "transformer.h.13.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
119
+ "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
120
+ "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
121
+ "transformer.h.13.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
122
+ "transformer.h.13.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
123
+ "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
124
+ "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
125
+ "transformer.h.13.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
126
+ "transformer.h.14.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
127
+ "transformer.h.14.attn.c_attn.bias": "model-00001-of-00002.safetensors",
128
+ "transformer.h.14.attn.c_attn.weight": "model-00001-of-00002.safetensors",
129
+ "transformer.h.14.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
130
+ "transformer.h.14.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
131
+ "transformer.h.14.attn.c_proj.bias": "model-00001-of-00002.safetensors",
132
+ "transformer.h.14.attn.c_proj.weight": "model-00001-of-00002.safetensors",
133
+ "transformer.h.14.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
134
+ "transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
135
+ "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
136
+ "transformer.h.14.ln_2.bias": "model-00001-of-00002.safetensors",
137
+ "transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
138
+ "transformer.h.14.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
139
+ "transformer.h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
140
+ "transformer.h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
141
+ "transformer.h.14.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
142
+ "transformer.h.14.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
143
+ "transformer.h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
144
+ "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
145
+ "transformer.h.14.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
146
+ "transformer.h.15.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
147
+ "transformer.h.15.attn.c_attn.bias": "model-00001-of-00002.safetensors",
148
+ "transformer.h.15.attn.c_attn.weight": "model-00001-of-00002.safetensors",
149
+ "transformer.h.15.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
150
+ "transformer.h.15.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
151
+ "transformer.h.15.attn.c_proj.bias": "model-00001-of-00002.safetensors",
152
+ "transformer.h.15.attn.c_proj.weight": "model-00001-of-00002.safetensors",
153
+ "transformer.h.15.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
154
+ "transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
155
+ "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
156
+ "transformer.h.15.ln_2.bias": "model-00001-of-00002.safetensors",
157
+ "transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
158
+ "transformer.h.15.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
159
+ "transformer.h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
160
+ "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
161
+ "transformer.h.15.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
162
+ "transformer.h.15.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
163
+ "transformer.h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
164
+ "transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
165
+ "transformer.h.15.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
166
+ "transformer.h.16.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
167
+ "transformer.h.16.attn.c_attn.bias": "model-00001-of-00002.safetensors",
168
+ "transformer.h.16.attn.c_attn.weight": "model-00001-of-00002.safetensors",
169
+ "transformer.h.16.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
170
+ "transformer.h.16.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
171
+ "transformer.h.16.attn.c_proj.bias": "model-00001-of-00002.safetensors",
172
+ "transformer.h.16.attn.c_proj.weight": "model-00001-of-00002.safetensors",
173
+ "transformer.h.16.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
174
+ "transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
175
+ "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
176
+ "transformer.h.16.ln_2.bias": "model-00001-of-00002.safetensors",
177
+ "transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
178
+ "transformer.h.16.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
179
+ "transformer.h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
180
+ "transformer.h.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
181
+ "transformer.h.16.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
182
+ "transformer.h.16.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
183
+ "transformer.h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
184
+ "transformer.h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
185
+ "transformer.h.16.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
186
+ "transformer.h.17.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
187
+ "transformer.h.17.attn.c_attn.bias": "model-00001-of-00002.safetensors",
188
+ "transformer.h.17.attn.c_attn.weight": "model-00001-of-00002.safetensors",
189
+ "transformer.h.17.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
190
+ "transformer.h.17.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
191
+ "transformer.h.17.attn.c_proj.bias": "model-00001-of-00002.safetensors",
192
+ "transformer.h.17.attn.c_proj.weight": "model-00001-of-00002.safetensors",
193
+ "transformer.h.17.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
194
+ "transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
195
+ "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
196
+ "transformer.h.17.ln_2.bias": "model-00001-of-00002.safetensors",
197
+ "transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
198
+ "transformer.h.17.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
199
+ "transformer.h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
200
+ "transformer.h.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
201
+ "transformer.h.17.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
202
+ "transformer.h.17.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
203
+ "transformer.h.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
204
+ "transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
205
+ "transformer.h.17.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
206
+ "transformer.h.18.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
207
+ "transformer.h.18.attn.c_attn.bias": "model-00001-of-00002.safetensors",
208
+ "transformer.h.18.attn.c_attn.weight": "model-00001-of-00002.safetensors",
209
+ "transformer.h.18.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
210
+ "transformer.h.18.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
211
+ "transformer.h.18.attn.c_proj.bias": "model-00001-of-00002.safetensors",
212
+ "transformer.h.18.attn.c_proj.weight": "model-00001-of-00002.safetensors",
213
+ "transformer.h.18.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
214
+ "transformer.h.18.ln_1.bias": "model-00001-of-00002.safetensors",
215
+ "transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
216
+ "transformer.h.18.ln_2.bias": "model-00001-of-00002.safetensors",
217
+ "transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
218
+ "transformer.h.18.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
219
+ "transformer.h.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
220
+ "transformer.h.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
221
+ "transformer.h.18.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
222
+ "transformer.h.18.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
223
+ "transformer.h.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
224
+ "transformer.h.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
225
+ "transformer.h.18.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
226
+ "transformer.h.19.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
227
+ "transformer.h.19.attn.c_attn.bias": "model-00001-of-00002.safetensors",
228
+ "transformer.h.19.attn.c_attn.weight": "model-00001-of-00002.safetensors",
229
+ "transformer.h.19.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
230
+ "transformer.h.19.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
231
+ "transformer.h.19.attn.c_proj.bias": "model-00001-of-00002.safetensors",
232
+ "transformer.h.19.attn.c_proj.weight": "model-00001-of-00002.safetensors",
233
+ "transformer.h.19.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
234
+ "transformer.h.19.ln_1.bias": "model-00001-of-00002.safetensors",
235
+ "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
236
+ "transformer.h.19.ln_2.bias": "model-00001-of-00002.safetensors",
237
+ "transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
238
+ "transformer.h.19.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
239
+ "transformer.h.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
240
+ "transformer.h.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
241
+ "transformer.h.19.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
242
+ "transformer.h.19.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
243
+ "transformer.h.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
244
+ "transformer.h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
245
+ "transformer.h.19.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
246
+ "transformer.h.2.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
247
+ "transformer.h.2.attn.c_attn.bias": "model-00001-of-00002.safetensors",
248
+ "transformer.h.2.attn.c_attn.weight": "model-00001-of-00002.safetensors",
249
+ "transformer.h.2.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
250
+ "transformer.h.2.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
251
+ "transformer.h.2.attn.c_proj.bias": "model-00001-of-00002.safetensors",
252
+ "transformer.h.2.attn.c_proj.weight": "model-00001-of-00002.safetensors",
253
+ "transformer.h.2.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
254
+ "transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
255
+ "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
256
+ "transformer.h.2.ln_2.bias": "model-00001-of-00002.safetensors",
257
+ "transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
258
+ "transformer.h.2.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
259
+ "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
260
+ "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
261
+ "transformer.h.2.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
262
+ "transformer.h.2.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
263
+ "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
264
+ "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
265
+ "transformer.h.2.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
266
+ "transformer.h.20.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
267
+ "transformer.h.20.attn.c_attn.bias": "model-00001-of-00002.safetensors",
268
+ "transformer.h.20.attn.c_attn.weight": "model-00001-of-00002.safetensors",
269
+ "transformer.h.20.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
270
+ "transformer.h.20.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
271
+ "transformer.h.20.attn.c_proj.bias": "model-00001-of-00002.safetensors",
272
+ "transformer.h.20.attn.c_proj.weight": "model-00001-of-00002.safetensors",
273
+ "transformer.h.20.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
274
+ "transformer.h.20.ln_1.bias": "model-00001-of-00002.safetensors",
275
+ "transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
276
+ "transformer.h.20.ln_2.bias": "model-00001-of-00002.safetensors",
277
+ "transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
278
+ "transformer.h.20.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
279
+ "transformer.h.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
280
+ "transformer.h.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
281
+ "transformer.h.20.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
282
+ "transformer.h.20.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
283
+ "transformer.h.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
284
+ "transformer.h.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
285
+ "transformer.h.20.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
286
+ "transformer.h.21.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
287
+ "transformer.h.21.attn.c_attn.bias": "model-00001-of-00002.safetensors",
288
+ "transformer.h.21.attn.c_attn.weight": "model-00001-of-00002.safetensors",
289
+ "transformer.h.21.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
290
+ "transformer.h.21.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
291
+ "transformer.h.21.attn.c_proj.bias": "model-00001-of-00002.safetensors",
292
+ "transformer.h.21.attn.c_proj.weight": "model-00001-of-00002.safetensors",
293
+ "transformer.h.21.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
294
+ "transformer.h.21.ln_1.bias": "model-00001-of-00002.safetensors",
295
+ "transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
296
+ "transformer.h.21.ln_2.bias": "model-00001-of-00002.safetensors",
297
+ "transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
298
+ "transformer.h.21.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
299
+ "transformer.h.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
300
+ "transformer.h.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
301
+ "transformer.h.21.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
302
+ "transformer.h.21.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
303
+ "transformer.h.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
304
+ "transformer.h.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
305
+ "transformer.h.21.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
306
+ "transformer.h.22.attn.c_attn.SCB": "model-00002-of-00002.safetensors",
307
+ "transformer.h.22.attn.c_attn.bias": "model-00002-of-00002.safetensors",
308
+ "transformer.h.22.attn.c_attn.weight": "model-00002-of-00002.safetensors",
309
+ "transformer.h.22.attn.c_attn.weight_format": "model-00002-of-00002.safetensors",
310
+ "transformer.h.22.attn.c_proj.SCB": "model-00002-of-00002.safetensors",
311
+ "transformer.h.22.attn.c_proj.bias": "model-00002-of-00002.safetensors",
312
+ "transformer.h.22.attn.c_proj.weight": "model-00002-of-00002.safetensors",
313
+ "transformer.h.22.attn.c_proj.weight_format": "model-00002-of-00002.safetensors",
314
+ "transformer.h.22.ln_1.bias": "model-00001-of-00002.safetensors",
315
+ "transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
316
+ "transformer.h.22.ln_2.bias": "model-00002-of-00002.safetensors",
317
+ "transformer.h.22.ln_2.weight": "model-00002-of-00002.safetensors",
318
+ "transformer.h.22.mlp.c_fc.SCB": "model-00002-of-00002.safetensors",
319
+ "transformer.h.22.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
320
+ "transformer.h.22.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
321
+ "transformer.h.22.mlp.c_fc.weight_format": "model-00002-of-00002.safetensors",
322
+ "transformer.h.22.mlp.c_proj.SCB": "model-00002-of-00002.safetensors",
323
+ "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
324
+ "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
325
+ "transformer.h.22.mlp.c_proj.weight_format": "model-00002-of-00002.safetensors",
326
+ "transformer.h.23.attn.c_attn.SCB": "model-00002-of-00002.safetensors",
327
+ "transformer.h.23.attn.c_attn.bias": "model-00002-of-00002.safetensors",
328
+ "transformer.h.23.attn.c_attn.weight": "model-00002-of-00002.safetensors",
329
+ "transformer.h.23.attn.c_attn.weight_format": "model-00002-of-00002.safetensors",
330
+ "transformer.h.23.attn.c_proj.SCB": "model-00002-of-00002.safetensors",
331
+ "transformer.h.23.attn.c_proj.bias": "model-00002-of-00002.safetensors",
332
+ "transformer.h.23.attn.c_proj.weight": "model-00002-of-00002.safetensors",
333
+ "transformer.h.23.attn.c_proj.weight_format": "model-00002-of-00002.safetensors",
334
+ "transformer.h.23.ln_1.bias": "model-00002-of-00002.safetensors",
335
+ "transformer.h.23.ln_1.weight": "model-00002-of-00002.safetensors",
336
+ "transformer.h.23.ln_2.bias": "model-00002-of-00002.safetensors",
337
+ "transformer.h.23.ln_2.weight": "model-00002-of-00002.safetensors",
338
+ "transformer.h.23.mlp.c_fc.SCB": "model-00002-of-00002.safetensors",
339
+ "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
340
+ "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
341
+ "transformer.h.23.mlp.c_fc.weight_format": "model-00002-of-00002.safetensors",
342
+ "transformer.h.23.mlp.c_proj.SCB": "model-00002-of-00002.safetensors",
343
+ "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
344
+ "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
345
+ "transformer.h.23.mlp.c_proj.weight_format": "model-00002-of-00002.safetensors",
346
+ "transformer.h.24.attn.c_attn.SCB": "model-00002-of-00002.safetensors",
347
+ "transformer.h.24.attn.c_attn.bias": "model-00002-of-00002.safetensors",
348
+ "transformer.h.24.attn.c_attn.weight": "model-00002-of-00002.safetensors",
349
+ "transformer.h.24.attn.c_attn.weight_format": "model-00002-of-00002.safetensors",
350
+ "transformer.h.24.attn.c_proj.SCB": "model-00002-of-00002.safetensors",
351
+ "transformer.h.24.attn.c_proj.bias": "model-00002-of-00002.safetensors",
352
+ "transformer.h.24.attn.c_proj.weight": "model-00002-of-00002.safetensors",
353
+ "transformer.h.24.attn.c_proj.weight_format": "model-00002-of-00002.safetensors",
354
+ "transformer.h.24.ln_1.bias": "model-00002-of-00002.safetensors",
355
+ "transformer.h.24.ln_1.weight": "model-00002-of-00002.safetensors",
356
+ "transformer.h.24.ln_2.bias": "model-00002-of-00002.safetensors",
357
+ "transformer.h.24.ln_2.weight": "model-00002-of-00002.safetensors",
358
+ "transformer.h.24.mlp.c_fc.SCB": "model-00002-of-00002.safetensors",
359
+ "transformer.h.24.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
360
+ "transformer.h.24.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
361
+ "transformer.h.24.mlp.c_fc.weight_format": "model-00002-of-00002.safetensors",
362
+ "transformer.h.24.mlp.c_proj.SCB": "model-00002-of-00002.safetensors",
363
+ "transformer.h.24.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
364
+ "transformer.h.24.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
365
+ "transformer.h.24.mlp.c_proj.weight_format": "model-00002-of-00002.safetensors",
366
+ "transformer.h.25.attn.c_attn.SCB": "model-00002-of-00002.safetensors",
367
+ "transformer.h.25.attn.c_attn.bias": "model-00002-of-00002.safetensors",
368
+ "transformer.h.25.attn.c_attn.weight": "model-00002-of-00002.safetensors",
369
+ "transformer.h.25.attn.c_attn.weight_format": "model-00002-of-00002.safetensors",
370
+ "transformer.h.25.attn.c_proj.SCB": "model-00002-of-00002.safetensors",
371
+ "transformer.h.25.attn.c_proj.bias": "model-00002-of-00002.safetensors",
372
+ "transformer.h.25.attn.c_proj.weight": "model-00002-of-00002.safetensors",
373
+ "transformer.h.25.attn.c_proj.weight_format": "model-00002-of-00002.safetensors",
374
+ "transformer.h.25.ln_1.bias": "model-00002-of-00002.safetensors",
375
+ "transformer.h.25.ln_1.weight": "model-00002-of-00002.safetensors",
376
+ "transformer.h.25.ln_2.bias": "model-00002-of-00002.safetensors",
377
+ "transformer.h.25.ln_2.weight": "model-00002-of-00002.safetensors",
378
+ "transformer.h.25.mlp.c_fc.SCB": "model-00002-of-00002.safetensors",
379
+ "transformer.h.25.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
380
+ "transformer.h.25.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
381
+ "transformer.h.25.mlp.c_fc.weight_format": "model-00002-of-00002.safetensors",
382
+ "transformer.h.25.mlp.c_proj.SCB": "model-00002-of-00002.safetensors",
383
+ "transformer.h.25.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
384
+ "transformer.h.25.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
385
+ "transformer.h.25.mlp.c_proj.weight_format": "model-00002-of-00002.safetensors",
386
+ "transformer.h.26.attn.c_attn.SCB": "model-00002-of-00002.safetensors",
387
+ "transformer.h.26.attn.c_attn.bias": "model-00002-of-00002.safetensors",
388
+ "transformer.h.26.attn.c_attn.weight": "model-00002-of-00002.safetensors",
389
+ "transformer.h.26.attn.c_attn.weight_format": "model-00002-of-00002.safetensors",
390
+ "transformer.h.26.attn.c_proj.SCB": "model-00002-of-00002.safetensors",
391
+ "transformer.h.26.attn.c_proj.bias": "model-00002-of-00002.safetensors",
392
+ "transformer.h.26.attn.c_proj.weight": "model-00002-of-00002.safetensors",
393
+ "transformer.h.26.attn.c_proj.weight_format": "model-00002-of-00002.safetensors",
394
+ "transformer.h.26.ln_1.bias": "model-00002-of-00002.safetensors",
395
+ "transformer.h.26.ln_1.weight": "model-00002-of-00002.safetensors",
396
+ "transformer.h.26.ln_2.bias": "model-00002-of-00002.safetensors",
397
+ "transformer.h.26.ln_2.weight": "model-00002-of-00002.safetensors",
398
+ "transformer.h.26.mlp.c_fc.SCB": "model-00002-of-00002.safetensors",
399
+ "transformer.h.26.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
400
+ "transformer.h.26.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
401
+ "transformer.h.26.mlp.c_fc.weight_format": "model-00002-of-00002.safetensors",
402
+ "transformer.h.26.mlp.c_proj.SCB": "model-00002-of-00002.safetensors",
403
+ "transformer.h.26.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
404
+ "transformer.h.26.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
405
+ "transformer.h.26.mlp.c_proj.weight_format": "model-00002-of-00002.safetensors",
406
+ "transformer.h.27.attn.c_attn.SCB": "model-00002-of-00002.safetensors",
407
+ "transformer.h.27.attn.c_attn.bias": "model-00002-of-00002.safetensors",
408
+ "transformer.h.27.attn.c_attn.weight": "model-00002-of-00002.safetensors",
409
+ "transformer.h.27.attn.c_attn.weight_format": "model-00002-of-00002.safetensors",
410
+ "transformer.h.27.attn.c_proj.SCB": "model-00002-of-00002.safetensors",
411
+ "transformer.h.27.attn.c_proj.bias": "model-00002-of-00002.safetensors",
412
+ "transformer.h.27.attn.c_proj.weight": "model-00002-of-00002.safetensors",
413
+ "transformer.h.27.attn.c_proj.weight_format": "model-00002-of-00002.safetensors",
414
+ "transformer.h.27.ln_1.bias": "model-00002-of-00002.safetensors",
415
+ "transformer.h.27.ln_1.weight": "model-00002-of-00002.safetensors",
416
+ "transformer.h.27.ln_2.bias": "model-00002-of-00002.safetensors",
417
+ "transformer.h.27.ln_2.weight": "model-00002-of-00002.safetensors",
418
+ "transformer.h.27.mlp.c_fc.SCB": "model-00002-of-00002.safetensors",
419
+ "transformer.h.27.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
420
+ "transformer.h.27.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
421
+ "transformer.h.27.mlp.c_fc.weight_format": "model-00002-of-00002.safetensors",
422
+ "transformer.h.27.mlp.c_proj.SCB": "model-00002-of-00002.safetensors",
423
+ "transformer.h.27.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
424
+ "transformer.h.27.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
425
+ "transformer.h.27.mlp.c_proj.weight_format": "model-00002-of-00002.safetensors",
426
+ "transformer.h.28.attn.c_attn.SCB": "model-00002-of-00002.safetensors",
427
+ "transformer.h.28.attn.c_attn.bias": "model-00002-of-00002.safetensors",
428
+ "transformer.h.28.attn.c_attn.weight": "model-00002-of-00002.safetensors",
429
+ "transformer.h.28.attn.c_attn.weight_format": "model-00002-of-00002.safetensors",
430
+ "transformer.h.28.attn.c_proj.SCB": "model-00002-of-00002.safetensors",
431
+ "transformer.h.28.attn.c_proj.bias": "model-00002-of-00002.safetensors",
432
+ "transformer.h.28.attn.c_proj.weight": "model-00002-of-00002.safetensors",
433
+ "transformer.h.28.attn.c_proj.weight_format": "model-00002-of-00002.safetensors",
434
+ "transformer.h.28.ln_1.bias": "model-00002-of-00002.safetensors",
435
+ "transformer.h.28.ln_1.weight": "model-00002-of-00002.safetensors",
436
+ "transformer.h.28.ln_2.bias": "model-00002-of-00002.safetensors",
437
+ "transformer.h.28.ln_2.weight": "model-00002-of-00002.safetensors",
438
+ "transformer.h.28.mlp.c_fc.SCB": "model-00002-of-00002.safetensors",
439
+ "transformer.h.28.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
440
+ "transformer.h.28.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
441
+ "transformer.h.28.mlp.c_fc.weight_format": "model-00002-of-00002.safetensors",
442
+ "transformer.h.28.mlp.c_proj.SCB": "model-00002-of-00002.safetensors",
443
+ "transformer.h.28.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
444
+ "transformer.h.28.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
445
+ "transformer.h.28.mlp.c_proj.weight_format": "model-00002-of-00002.safetensors",
446
+ "transformer.h.29.attn.c_attn.SCB": "model-00002-of-00002.safetensors",
447
+ "transformer.h.29.attn.c_attn.bias": "model-00002-of-00002.safetensors",
448
+ "transformer.h.29.attn.c_attn.weight": "model-00002-of-00002.safetensors",
449
+ "transformer.h.29.attn.c_attn.weight_format": "model-00002-of-00002.safetensors",
450
+ "transformer.h.29.attn.c_proj.SCB": "model-00002-of-00002.safetensors",
451
+ "transformer.h.29.attn.c_proj.bias": "model-00002-of-00002.safetensors",
452
+ "transformer.h.29.attn.c_proj.weight": "model-00002-of-00002.safetensors",
453
+ "transformer.h.29.attn.c_proj.weight_format": "model-00002-of-00002.safetensors",
454
+ "transformer.h.29.ln_1.bias": "model-00002-of-00002.safetensors",
455
+ "transformer.h.29.ln_1.weight": "model-00002-of-00002.safetensors",
456
+ "transformer.h.29.ln_2.bias": "model-00002-of-00002.safetensors",
457
+ "transformer.h.29.ln_2.weight": "model-00002-of-00002.safetensors",
458
+ "transformer.h.29.mlp.c_fc.SCB": "model-00002-of-00002.safetensors",
459
+ "transformer.h.29.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
460
+ "transformer.h.29.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
461
+ "transformer.h.29.mlp.c_fc.weight_format": "model-00002-of-00002.safetensors",
462
+ "transformer.h.29.mlp.c_proj.SCB": "model-00002-of-00002.safetensors",
463
+ "transformer.h.29.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
464
+ "transformer.h.29.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
465
+ "transformer.h.29.mlp.c_proj.weight_format": "model-00002-of-00002.safetensors",
466
+ "transformer.h.3.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
467
+ "transformer.h.3.attn.c_attn.bias": "model-00001-of-00002.safetensors",
468
+ "transformer.h.3.attn.c_attn.weight": "model-00001-of-00002.safetensors",
469
+ "transformer.h.3.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
470
+ "transformer.h.3.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
471
+ "transformer.h.3.attn.c_proj.bias": "model-00001-of-00002.safetensors",
472
+ "transformer.h.3.attn.c_proj.weight": "model-00001-of-00002.safetensors",
473
+ "transformer.h.3.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
474
+ "transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
475
+ "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
476
+ "transformer.h.3.ln_2.bias": "model-00001-of-00002.safetensors",
477
+ "transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
478
+ "transformer.h.3.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
479
+ "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
480
+ "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
481
+ "transformer.h.3.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
482
+ "transformer.h.3.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
483
+ "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
484
+ "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
485
+ "transformer.h.3.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
486
+ "transformer.h.30.attn.c_attn.SCB": "model-00002-of-00002.safetensors",
487
+ "transformer.h.30.attn.c_attn.bias": "model-00002-of-00002.safetensors",
488
+ "transformer.h.30.attn.c_attn.weight": "model-00002-of-00002.safetensors",
489
+ "transformer.h.30.attn.c_attn.weight_format": "model-00002-of-00002.safetensors",
490
+ "transformer.h.30.attn.c_proj.SCB": "model-00002-of-00002.safetensors",
491
+ "transformer.h.30.attn.c_proj.bias": "model-00002-of-00002.safetensors",
492
+ "transformer.h.30.attn.c_proj.weight": "model-00002-of-00002.safetensors",
493
+ "transformer.h.30.attn.c_proj.weight_format": "model-00002-of-00002.safetensors",
494
+ "transformer.h.30.ln_1.bias": "model-00002-of-00002.safetensors",
495
+ "transformer.h.30.ln_1.weight": "model-00002-of-00002.safetensors",
496
+ "transformer.h.30.ln_2.bias": "model-00002-of-00002.safetensors",
497
+ "transformer.h.30.ln_2.weight": "model-00002-of-00002.safetensors",
498
+ "transformer.h.30.mlp.c_fc.SCB": "model-00002-of-00002.safetensors",
499
+ "transformer.h.30.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
500
+ "transformer.h.30.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
501
+ "transformer.h.30.mlp.c_fc.weight_format": "model-00002-of-00002.safetensors",
502
+ "transformer.h.30.mlp.c_proj.SCB": "model-00002-of-00002.safetensors",
503
+ "transformer.h.30.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
504
+ "transformer.h.30.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
505
+ "transformer.h.30.mlp.c_proj.weight_format": "model-00002-of-00002.safetensors",
506
+ "transformer.h.31.attn.c_attn.SCB": "model-00002-of-00002.safetensors",
507
+ "transformer.h.31.attn.c_attn.bias": "model-00002-of-00002.safetensors",
508
+ "transformer.h.31.attn.c_attn.weight": "model-00002-of-00002.safetensors",
509
+ "transformer.h.31.attn.c_attn.weight_format": "model-00002-of-00002.safetensors",
510
+ "transformer.h.31.attn.c_proj.SCB": "model-00002-of-00002.safetensors",
511
+ "transformer.h.31.attn.c_proj.bias": "model-00002-of-00002.safetensors",
512
+ "transformer.h.31.attn.c_proj.weight": "model-00002-of-00002.safetensors",
513
+ "transformer.h.31.attn.c_proj.weight_format": "model-00002-of-00002.safetensors",
514
+ "transformer.h.31.ln_1.bias": "model-00002-of-00002.safetensors",
515
+ "transformer.h.31.ln_1.weight": "model-00002-of-00002.safetensors",
516
+ "transformer.h.31.ln_2.bias": "model-00002-of-00002.safetensors",
517
+ "transformer.h.31.ln_2.weight": "model-00002-of-00002.safetensors",
518
+ "transformer.h.31.mlp.c_fc.SCB": "model-00002-of-00002.safetensors",
519
+ "transformer.h.31.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
520
+ "transformer.h.31.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
521
+ "transformer.h.31.mlp.c_fc.weight_format": "model-00002-of-00002.safetensors",
522
+ "transformer.h.31.mlp.c_proj.SCB": "model-00002-of-00002.safetensors",
523
+ "transformer.h.31.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
524
+ "transformer.h.31.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
525
+ "transformer.h.31.mlp.c_proj.weight_format": "model-00002-of-00002.safetensors",
526
+ "transformer.h.4.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
527
+ "transformer.h.4.attn.c_attn.bias": "model-00001-of-00002.safetensors",
528
+ "transformer.h.4.attn.c_attn.weight": "model-00001-of-00002.safetensors",
529
+ "transformer.h.4.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
530
+ "transformer.h.4.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
531
+ "transformer.h.4.attn.c_proj.bias": "model-00001-of-00002.safetensors",
532
+ "transformer.h.4.attn.c_proj.weight": "model-00001-of-00002.safetensors",
533
+ "transformer.h.4.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
534
+ "transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
535
+ "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
536
+ "transformer.h.4.ln_2.bias": "model-00001-of-00002.safetensors",
537
+ "transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
538
+ "transformer.h.4.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
539
+ "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
540
+ "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
541
+ "transformer.h.4.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
542
+ "transformer.h.4.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
543
+ "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
544
+ "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
545
+ "transformer.h.4.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
546
+ "transformer.h.5.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
547
+ "transformer.h.5.attn.c_attn.bias": "model-00001-of-00002.safetensors",
548
+ "transformer.h.5.attn.c_attn.weight": "model-00001-of-00002.safetensors",
549
+ "transformer.h.5.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
550
+ "transformer.h.5.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
551
+ "transformer.h.5.attn.c_proj.bias": "model-00001-of-00002.safetensors",
552
+ "transformer.h.5.attn.c_proj.weight": "model-00001-of-00002.safetensors",
553
+ "transformer.h.5.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
554
+ "transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
555
+ "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
556
+ "transformer.h.5.ln_2.bias": "model-00001-of-00002.safetensors",
557
+ "transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
558
+ "transformer.h.5.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
559
+ "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
560
+ "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
561
+ "transformer.h.5.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
562
+ "transformer.h.5.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
563
+ "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
564
+ "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
565
+ "transformer.h.5.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
566
+ "transformer.h.6.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
567
+ "transformer.h.6.attn.c_attn.bias": "model-00001-of-00002.safetensors",
568
+ "transformer.h.6.attn.c_attn.weight": "model-00001-of-00002.safetensors",
569
+ "transformer.h.6.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
570
+ "transformer.h.6.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
571
+ "transformer.h.6.attn.c_proj.bias": "model-00001-of-00002.safetensors",
572
+ "transformer.h.6.attn.c_proj.weight": "model-00001-of-00002.safetensors",
573
+ "transformer.h.6.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
574
+ "transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
575
+ "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
576
+ "transformer.h.6.ln_2.bias": "model-00001-of-00002.safetensors",
577
+ "transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
578
+ "transformer.h.6.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
579
+ "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
580
+ "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
581
+ "transformer.h.6.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
582
+ "transformer.h.6.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
583
+ "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
584
+ "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
585
+ "transformer.h.6.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
586
+ "transformer.h.7.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
587
+ "transformer.h.7.attn.c_attn.bias": "model-00001-of-00002.safetensors",
588
+ "transformer.h.7.attn.c_attn.weight": "model-00001-of-00002.safetensors",
589
+ "transformer.h.7.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
590
+ "transformer.h.7.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
591
+ "transformer.h.7.attn.c_proj.bias": "model-00001-of-00002.safetensors",
592
+ "transformer.h.7.attn.c_proj.weight": "model-00001-of-00002.safetensors",
593
+ "transformer.h.7.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
594
+ "transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
595
+ "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
596
+ "transformer.h.7.ln_2.bias": "model-00001-of-00002.safetensors",
597
+ "transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
598
+ "transformer.h.7.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
599
+ "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
600
+ "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
601
+ "transformer.h.7.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
602
+ "transformer.h.7.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
603
+ "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
604
+ "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
605
+ "transformer.h.7.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
606
+ "transformer.h.8.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
607
+ "transformer.h.8.attn.c_attn.bias": "model-00001-of-00002.safetensors",
608
+ "transformer.h.8.attn.c_attn.weight": "model-00001-of-00002.safetensors",
609
+ "transformer.h.8.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
610
+ "transformer.h.8.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
611
+ "transformer.h.8.attn.c_proj.bias": "model-00001-of-00002.safetensors",
612
+ "transformer.h.8.attn.c_proj.weight": "model-00001-of-00002.safetensors",
613
+ "transformer.h.8.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
614
+ "transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
615
+ "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
616
+ "transformer.h.8.ln_2.bias": "model-00001-of-00002.safetensors",
617
+ "transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
618
+ "transformer.h.8.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
619
+ "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
620
+ "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
621
+ "transformer.h.8.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
622
+ "transformer.h.8.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
623
+ "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
624
+ "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
625
+ "transformer.h.8.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
626
+ "transformer.h.9.attn.c_attn.SCB": "model-00001-of-00002.safetensors",
627
+ "transformer.h.9.attn.c_attn.bias": "model-00001-of-00002.safetensors",
628
+ "transformer.h.9.attn.c_attn.weight": "model-00001-of-00002.safetensors",
629
+ "transformer.h.9.attn.c_attn.weight_format": "model-00001-of-00002.safetensors",
630
+ "transformer.h.9.attn.c_proj.SCB": "model-00001-of-00002.safetensors",
631
+ "transformer.h.9.attn.c_proj.bias": "model-00001-of-00002.safetensors",
632
+ "transformer.h.9.attn.c_proj.weight": "model-00001-of-00002.safetensors",
633
+ "transformer.h.9.attn.c_proj.weight_format": "model-00001-of-00002.safetensors",
634
+ "transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
635
+ "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
636
+ "transformer.h.9.ln_2.bias": "model-00001-of-00002.safetensors",
637
+ "transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
638
+ "transformer.h.9.mlp.c_fc.SCB": "model-00001-of-00002.safetensors",
639
+ "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
640
+ "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
641
+ "transformer.h.9.mlp.c_fc.weight_format": "model-00001-of-00002.safetensors",
642
+ "transformer.h.9.mlp.c_proj.SCB": "model-00001-of-00002.safetensors",
643
+ "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
644
+ "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
645
+ "transformer.h.9.mlp.c_proj.weight_format": "model-00001-of-00002.safetensors",
646
+ "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
647
+ "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
648
+ "transformer.wpe.weight": "model-00001-of-00002.safetensors",
649
+ "transformer.wte.weight": "model-00001-of-00002.safetensors"
650
+ }
651
+ }
smash_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "comp_cgenerate_active": false,
3
+ "comp_ctranslate_active": false,
4
+ "comp_cwhisper_active": false,
5
+ "comp_diffusers2_active": false,
6
+ "comp_ifw_active": false,
7
+ "comp_onediff_active": false,
8
+ "comp_step_caching_active": false,
9
+ "comp_torch_compile_active": false,
10
+ "comp_ws2t_active": false,
11
+ "comp_x-fast_active": false,
12
+ "prune_torch-structured_active": false,
13
+ "quant_aqlm_active": false,
14
+ "quant_awq_active": false,
15
+ "quant_gptq_active": false,
16
+ "quant_half_active": false,
17
+ "quant_hqq_active": false,
18
+ "quant_llm-int8_active": true,
19
+ "quant_quanto_active": false,
20
+ "quant_torch_dynamic_active": false,
21
+ "quant_torch_static_active": false,
22
+ "quant_llm-int8_compute_dtype": "bfloat16",
23
+ "quant_llm-int8_double_quant": false,
24
+ "quant_llm-int8_enable_fp32_cpu_offload": false,
25
+ "quant_llm-int8_has_fp16_weight": false,
26
+ "quant_llm-int8_quant_type": "fp4",
27
+ "quant_llm-int8_threshold": 6.0,
28
+ "quant_llm-int8_weight_bits": 8,
29
+ "max_batch_size": 1,
30
+ "device": "cuda",
31
+ "cache_dir": "/covalent/.cache/models/tmptkau2ene",
32
+ "task": "",
33
+ "save_load_fn": "bitsandbytes",
34
+ "save_load_fn_args": {}
35
+ }