upload weights
Browse files- README.md +199 -0
- config.json +152 -0
- configuration.py +62 -0
- generation_config.json +4 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +897 -0
README.md
ADDED
|
@@ -0,0 +1,199 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags: []
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
config.json
ADDED
|
@@ -0,0 +1,152 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MoLM"
|
| 4 |
+
],
|
| 5 |
+
"auto_map": {
|
| 6 |
+
"AutoConfig": "configuration.MoLMConfig",
|
| 7 |
+
"AutoModelForCausalLM": "robinfaro/molm_log_prob_router--modeling.MoLM",
|
| 8 |
+
"AutoTokenizer": "robinfaro/molm_log_prob_router--GPT2TokenizerFast"
|
| 9 |
+
},
|
| 10 |
+
"bias": false,
|
| 11 |
+
"dropout": 0.0,
|
| 12 |
+
"expert_configs": [
|
| 13 |
+
{
|
| 14 |
+
"bias": false,
|
| 15 |
+
"dropout": 0.0,
|
| 16 |
+
"dtype": "torch.bfloat16",
|
| 17 |
+
"mlp_dim_exp_factor": 1,
|
| 18 |
+
"moe": false,
|
| 19 |
+
"moe_aux_loss_factor": 0.01,
|
| 20 |
+
"moe_num_experts": 1,
|
| 21 |
+
"moe_num_experts_per_tok": 2,
|
| 22 |
+
"moe_router_loss": "load_balancing_z_loss",
|
| 23 |
+
"moe_routing": null,
|
| 24 |
+
"moe_softmax_order": "softmax_topk",
|
| 25 |
+
"moe_z_loss_factor": 1,
|
| 26 |
+
"n_embd": 1152,
|
| 27 |
+
"n_head": 16,
|
| 28 |
+
"n_layer": 24,
|
| 29 |
+
"routing": null,
|
| 30 |
+
"sequence_length": 1024,
|
| 31 |
+
"shared_attention": true,
|
| 32 |
+
"vocab_size": 50304
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"bias": false,
|
| 36 |
+
"dropout": 0.0,
|
| 37 |
+
"dtype": "torch.bfloat16",
|
| 38 |
+
"mlp_dim_exp_factor": 1,
|
| 39 |
+
"moe": false,
|
| 40 |
+
"moe_aux_loss_factor": 0.01,
|
| 41 |
+
"moe_num_experts": 1,
|
| 42 |
+
"moe_num_experts_per_tok": 2,
|
| 43 |
+
"moe_router_loss": "load_balancing_z_loss",
|
| 44 |
+
"moe_routing": null,
|
| 45 |
+
"moe_softmax_order": "softmax_topk",
|
| 46 |
+
"moe_z_loss_factor": 1,
|
| 47 |
+
"n_embd": 1152,
|
| 48 |
+
"n_head": 16,
|
| 49 |
+
"n_layer": 24,
|
| 50 |
+
"routing": null,
|
| 51 |
+
"sequence_length": 1024,
|
| 52 |
+
"shared_attention": true,
|
| 53 |
+
"vocab_size": 50304
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"bias": false,
|
| 57 |
+
"dropout": 0.0,
|
| 58 |
+
"dtype": "torch.bfloat16",
|
| 59 |
+
"mlp_dim_exp_factor": 1,
|
| 60 |
+
"moe": false,
|
| 61 |
+
"moe_aux_loss_factor": 0.01,
|
| 62 |
+
"moe_num_experts": 1,
|
| 63 |
+
"moe_num_experts_per_tok": 2,
|
| 64 |
+
"moe_router_loss": "load_balancing_z_loss",
|
| 65 |
+
"moe_routing": null,
|
| 66 |
+
"moe_softmax_order": "softmax_topk",
|
| 67 |
+
"moe_z_loss_factor": 1,
|
| 68 |
+
"n_embd": 1152,
|
| 69 |
+
"n_head": 16,
|
| 70 |
+
"n_layer": 24,
|
| 71 |
+
"routing": null,
|
| 72 |
+
"sequence_length": 1024,
|
| 73 |
+
"shared_attention": true,
|
| 74 |
+
"vocab_size": 50304
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"bias": false,
|
| 78 |
+
"dropout": 0.0,
|
| 79 |
+
"dtype": "torch.bfloat16",
|
| 80 |
+
"mlp_dim_exp_factor": 1,
|
| 81 |
+
"moe": false,
|
| 82 |
+
"moe_aux_loss_factor": 0.01,
|
| 83 |
+
"moe_num_experts": 1,
|
| 84 |
+
"moe_num_experts_per_tok": 2,
|
| 85 |
+
"moe_router_loss": "load_balancing_z_loss",
|
| 86 |
+
"moe_routing": null,
|
| 87 |
+
"moe_softmax_order": "softmax_topk",
|
| 88 |
+
"moe_z_loss_factor": 1,
|
| 89 |
+
"n_embd": 1152,
|
| 90 |
+
"n_head": 16,
|
| 91 |
+
"n_layer": 24,
|
| 92 |
+
"routing": null,
|
| 93 |
+
"sequence_length": 1024,
|
| 94 |
+
"shared_attention": true,
|
| 95 |
+
"vocab_size": 50304
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"bias": false,
|
| 99 |
+
"dropout": 0.0,
|
| 100 |
+
"dtype": "torch.bfloat16",
|
| 101 |
+
"mlp_dim_exp_factor": 1,
|
| 102 |
+
"moe": false,
|
| 103 |
+
"moe_aux_loss_factor": 0.01,
|
| 104 |
+
"moe_num_experts": 1,
|
| 105 |
+
"moe_num_experts_per_tok": 2,
|
| 106 |
+
"moe_router_loss": "load_balancing_z_loss",
|
| 107 |
+
"moe_routing": null,
|
| 108 |
+
"moe_softmax_order": "softmax_topk",
|
| 109 |
+
"moe_z_loss_factor": 1,
|
| 110 |
+
"n_embd": 1152,
|
| 111 |
+
"n_head": 16,
|
| 112 |
+
"n_layer": 24,
|
| 113 |
+
"routing": null,
|
| 114 |
+
"sequence_length": 1024,
|
| 115 |
+
"shared_attention": true,
|
| 116 |
+
"vocab_size": 50304
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"bias": false,
|
| 120 |
+
"dropout": 0.0,
|
| 121 |
+
"dtype": "torch.bfloat16",
|
| 122 |
+
"mlp_dim_exp_factor": 1,
|
| 123 |
+
"moe": false,
|
| 124 |
+
"moe_aux_loss_factor": 0.01,
|
| 125 |
+
"moe_num_experts": 1,
|
| 126 |
+
"moe_num_experts_per_tok": 2,
|
| 127 |
+
"moe_router_loss": "load_balancing_z_loss",
|
| 128 |
+
"moe_routing": null,
|
| 129 |
+
"moe_softmax_order": "softmax_topk",
|
| 130 |
+
"moe_z_loss_factor": 1,
|
| 131 |
+
"n_embd": 1152,
|
| 132 |
+
"n_head": 16,
|
| 133 |
+
"n_layer": 24,
|
| 134 |
+
"routing": null,
|
| 135 |
+
"sequence_length": 1024,
|
| 136 |
+
"shared_attention": true,
|
| 137 |
+
"vocab_size": 50304
|
| 138 |
+
}
|
| 139 |
+
],
|
| 140 |
+
"mlp_dim_exp_factor": 1.0,
|
| 141 |
+
"model_type": "MoLM",
|
| 142 |
+
"n_embd": 1152,
|
| 143 |
+
"n_head": 16,
|
| 144 |
+
"n_layer": 24,
|
| 145 |
+
"num_experts": 6,
|
| 146 |
+
"sequence_length": 1024,
|
| 147 |
+
"top_k_experts": 6,
|
| 148 |
+
"torch_dtype": "float32",
|
| 149 |
+
"transformers_version": "4.51.0",
|
| 150 |
+
"use_router": true,
|
| 151 |
+
"vocab_size": 50304
|
| 152 |
+
}
|
configuration.py
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from transformers import PretrainedConfig
|
| 2 |
+
|
| 3 |
+
class MoLMConfig(PretrainedConfig):
|
| 4 |
+
model_type = "MoLM"
|
| 5 |
+
|
| 6 |
+
def __init__(
|
| 7 |
+
self,
|
| 8 |
+
vocab_size=50304,
|
| 9 |
+
n_embd=768,
|
| 10 |
+
n_layer=12,
|
| 11 |
+
n_head=12,
|
| 12 |
+
sequence_length=1024,
|
| 13 |
+
mlp_dim_exp_factor=1.0,
|
| 14 |
+
dropout=0.0,
|
| 15 |
+
bias=False,
|
| 16 |
+
num_experts=6,
|
| 17 |
+
expert_configs=None,
|
| 18 |
+
use_router=False,
|
| 19 |
+
top_k_experts=6,
|
| 20 |
+
architectures=["MoLM"],
|
| 21 |
+
auto_map={
|
| 22 |
+
"AutoConfig": "configuration.MoLMConfig",
|
| 23 |
+
"AutoModelForCausalLM": "modeling.MoLM",
|
| 24 |
+
"AutoTokenizer": "GPT2TokenizerFast"
|
| 25 |
+
},
|
| 26 |
+
**kwargs,
|
| 27 |
+
):
|
| 28 |
+
super().__init__(**kwargs)
|
| 29 |
+
self.vocab_size = vocab_size
|
| 30 |
+
self.n_embd = n_embd
|
| 31 |
+
self.n_layer = n_layer
|
| 32 |
+
self.n_head = n_head
|
| 33 |
+
self.sequence_length = sequence_length
|
| 34 |
+
self.mlp_dim_exp_factor = mlp_dim_exp_factor
|
| 35 |
+
self.dropout = dropout
|
| 36 |
+
self.bias = bias
|
| 37 |
+
self.num_experts = num_experts
|
| 38 |
+
self.expert_configs = expert_configs
|
| 39 |
+
self.use_router = use_router
|
| 40 |
+
self.architectures = architectures
|
| 41 |
+
self.auto_map = auto_map
|
| 42 |
+
self.top_k_experts = top_k_experts
|
| 43 |
+
def to_dict(self):
|
| 44 |
+
config_dict = super().to_dict()
|
| 45 |
+
config_dict.update({
|
| 46 |
+
"vocab_size": self.vocab_size,
|
| 47 |
+
"n_embd": self.n_embd,
|
| 48 |
+
"n_layer": self.n_layer,
|
| 49 |
+
"n_head": self.n_head,
|
| 50 |
+
"sequence_length": self.sequence_length,
|
| 51 |
+
"mlp_dim_exp_factor": self.mlp_dim_exp_factor,
|
| 52 |
+
"dropout": self.dropout,
|
| 53 |
+
"bias": self.bias,
|
| 54 |
+
"num_experts": self.num_experts,
|
| 55 |
+
"expert_configs": [
|
| 56 |
+
expert_config.to_dict() if not isinstance(expert_config, dict) else expert_config
|
| 57 |
+
for expert_config in self.expert_configs
|
| 58 |
+
] if self.expert_configs else None,
|
| 59 |
+
"use_router": self.use_router,
|
| 60 |
+
"top_k_experts": self.top_k_experts,
|
| 61 |
+
})
|
| 62 |
+
return config_dict
|
generation_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"transformers_version": "4.51.0"
|
| 4 |
+
}
|
model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52d8fd07180a3ce15e162e2174fae3c0991f07bed8bab7045392f90ce21c43e4
|
| 3 |
+
size 4995862304
|
model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f65669cd40187a93528f39b1f0e14e4274293dd3e3d2d18dc30aec473ca4b22
|
| 3 |
+
size 4991101648
|
model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca7ec8944921e50cc2e9bf9b6bec890bd8ee8674937fc00e07f2441920e4361a
|
| 3 |
+
size 1997387152
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,897 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 11984246808
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"experts.0.lm_head.weight": "model-00001-of-00003.safetensors",
|
| 7 |
+
"experts.0.transformer.h.0.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 8 |
+
"experts.0.transformer.h.0.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"experts.0.transformer.h.0.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"experts.0.transformer.h.0.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"experts.0.transformer.h.0.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"experts.0.transformer.h.0.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"experts.0.transformer.h.1.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"experts.0.transformer.h.1.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 15 |
+
"experts.0.transformer.h.1.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"experts.0.transformer.h.1.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"experts.0.transformer.h.1.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 18 |
+
"experts.0.transformer.h.1.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"experts.0.transformer.h.10.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 20 |
+
"experts.0.transformer.h.10.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"experts.0.transformer.h.10.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"experts.0.transformer.h.10.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"experts.0.transformer.h.10.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"experts.0.transformer.h.10.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"experts.0.transformer.h.11.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"experts.0.transformer.h.11.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 27 |
+
"experts.0.transformer.h.11.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 28 |
+
"experts.0.transformer.h.11.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"experts.0.transformer.h.11.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 30 |
+
"experts.0.transformer.h.11.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 31 |
+
"experts.0.transformer.h.12.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 32 |
+
"experts.0.transformer.h.12.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"experts.0.transformer.h.12.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"experts.0.transformer.h.12.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"experts.0.transformer.h.12.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 36 |
+
"experts.0.transformer.h.12.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 37 |
+
"experts.0.transformer.h.13.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 38 |
+
"experts.0.transformer.h.13.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 39 |
+
"experts.0.transformer.h.13.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 40 |
+
"experts.0.transformer.h.13.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 41 |
+
"experts.0.transformer.h.13.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 42 |
+
"experts.0.transformer.h.13.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 43 |
+
"experts.0.transformer.h.14.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 44 |
+
"experts.0.transformer.h.14.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 45 |
+
"experts.0.transformer.h.14.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 46 |
+
"experts.0.transformer.h.14.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 47 |
+
"experts.0.transformer.h.14.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 48 |
+
"experts.0.transformer.h.14.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 49 |
+
"experts.0.transformer.h.15.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 50 |
+
"experts.0.transformer.h.15.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 51 |
+
"experts.0.transformer.h.15.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 52 |
+
"experts.0.transformer.h.15.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 53 |
+
"experts.0.transformer.h.15.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 54 |
+
"experts.0.transformer.h.15.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 55 |
+
"experts.0.transformer.h.16.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 56 |
+
"experts.0.transformer.h.16.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 57 |
+
"experts.0.transformer.h.16.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 58 |
+
"experts.0.transformer.h.16.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 59 |
+
"experts.0.transformer.h.16.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 60 |
+
"experts.0.transformer.h.16.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 61 |
+
"experts.0.transformer.h.17.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 62 |
+
"experts.0.transformer.h.17.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 63 |
+
"experts.0.transformer.h.17.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 64 |
+
"experts.0.transformer.h.17.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 65 |
+
"experts.0.transformer.h.17.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 66 |
+
"experts.0.transformer.h.17.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 67 |
+
"experts.0.transformer.h.18.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 68 |
+
"experts.0.transformer.h.18.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 69 |
+
"experts.0.transformer.h.18.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 70 |
+
"experts.0.transformer.h.18.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 71 |
+
"experts.0.transformer.h.18.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 72 |
+
"experts.0.transformer.h.18.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 73 |
+
"experts.0.transformer.h.19.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 74 |
+
"experts.0.transformer.h.19.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 75 |
+
"experts.0.transformer.h.19.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 76 |
+
"experts.0.transformer.h.19.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 77 |
+
"experts.0.transformer.h.19.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 78 |
+
"experts.0.transformer.h.19.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 79 |
+
"experts.0.transformer.h.2.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 80 |
+
"experts.0.transformer.h.2.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 81 |
+
"experts.0.transformer.h.2.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 82 |
+
"experts.0.transformer.h.2.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 83 |
+
"experts.0.transformer.h.2.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 84 |
+
"experts.0.transformer.h.2.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 85 |
+
"experts.0.transformer.h.20.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 86 |
+
"experts.0.transformer.h.20.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 87 |
+
"experts.0.transformer.h.20.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 88 |
+
"experts.0.transformer.h.20.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 89 |
+
"experts.0.transformer.h.20.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 90 |
+
"experts.0.transformer.h.20.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 91 |
+
"experts.0.transformer.h.21.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 92 |
+
"experts.0.transformer.h.21.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 93 |
+
"experts.0.transformer.h.21.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 94 |
+
"experts.0.transformer.h.21.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 95 |
+
"experts.0.transformer.h.21.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 96 |
+
"experts.0.transformer.h.21.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 97 |
+
"experts.0.transformer.h.22.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 98 |
+
"experts.0.transformer.h.22.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 99 |
+
"experts.0.transformer.h.22.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 100 |
+
"experts.0.transformer.h.22.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 101 |
+
"experts.0.transformer.h.22.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 102 |
+
"experts.0.transformer.h.22.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 103 |
+
"experts.0.transformer.h.23.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 104 |
+
"experts.0.transformer.h.23.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 105 |
+
"experts.0.transformer.h.23.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 106 |
+
"experts.0.transformer.h.23.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 107 |
+
"experts.0.transformer.h.23.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 108 |
+
"experts.0.transformer.h.23.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 109 |
+
"experts.0.transformer.h.3.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 110 |
+
"experts.0.transformer.h.3.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 111 |
+
"experts.0.transformer.h.3.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 112 |
+
"experts.0.transformer.h.3.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 113 |
+
"experts.0.transformer.h.3.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 114 |
+
"experts.0.transformer.h.3.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 115 |
+
"experts.0.transformer.h.4.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 116 |
+
"experts.0.transformer.h.4.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 117 |
+
"experts.0.transformer.h.4.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 118 |
+
"experts.0.transformer.h.4.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 119 |
+
"experts.0.transformer.h.4.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 120 |
+
"experts.0.transformer.h.4.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 121 |
+
"experts.0.transformer.h.5.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 122 |
+
"experts.0.transformer.h.5.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 123 |
+
"experts.0.transformer.h.5.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 124 |
+
"experts.0.transformer.h.5.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 125 |
+
"experts.0.transformer.h.5.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 126 |
+
"experts.0.transformer.h.5.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 127 |
+
"experts.0.transformer.h.6.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 128 |
+
"experts.0.transformer.h.6.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 129 |
+
"experts.0.transformer.h.6.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 130 |
+
"experts.0.transformer.h.6.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 131 |
+
"experts.0.transformer.h.6.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 132 |
+
"experts.0.transformer.h.6.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 133 |
+
"experts.0.transformer.h.7.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 134 |
+
"experts.0.transformer.h.7.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 135 |
+
"experts.0.transformer.h.7.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 136 |
+
"experts.0.transformer.h.7.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 137 |
+
"experts.0.transformer.h.7.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 138 |
+
"experts.0.transformer.h.7.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 139 |
+
"experts.0.transformer.h.8.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 140 |
+
"experts.0.transformer.h.8.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 141 |
+
"experts.0.transformer.h.8.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 142 |
+
"experts.0.transformer.h.8.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 143 |
+
"experts.0.transformer.h.8.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 144 |
+
"experts.0.transformer.h.8.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 145 |
+
"experts.0.transformer.h.9.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 146 |
+
"experts.0.transformer.h.9.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 147 |
+
"experts.0.transformer.h.9.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 148 |
+
"experts.0.transformer.h.9.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 149 |
+
"experts.0.transformer.h.9.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 150 |
+
"experts.0.transformer.h.9.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 151 |
+
"experts.0.transformer.ln_f.weight": "model-00001-of-00003.safetensors",
|
| 152 |
+
"experts.0.transformer.wpe.weight": "model-00001-of-00003.safetensors",
|
| 153 |
+
"experts.0.transformer.wte.weight": "model-00001-of-00003.safetensors",
|
| 154 |
+
"experts.1.lm_head.weight": "model-00001-of-00003.safetensors",
|
| 155 |
+
"experts.1.transformer.h.0.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 156 |
+
"experts.1.transformer.h.0.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 157 |
+
"experts.1.transformer.h.0.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 158 |
+
"experts.1.transformer.h.0.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 159 |
+
"experts.1.transformer.h.0.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 160 |
+
"experts.1.transformer.h.0.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 161 |
+
"experts.1.transformer.h.1.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 162 |
+
"experts.1.transformer.h.1.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 163 |
+
"experts.1.transformer.h.1.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 164 |
+
"experts.1.transformer.h.1.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 165 |
+
"experts.1.transformer.h.1.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 166 |
+
"experts.1.transformer.h.1.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 167 |
+
"experts.1.transformer.h.10.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 168 |
+
"experts.1.transformer.h.10.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 169 |
+
"experts.1.transformer.h.10.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 170 |
+
"experts.1.transformer.h.10.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 171 |
+
"experts.1.transformer.h.10.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 172 |
+
"experts.1.transformer.h.10.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 173 |
+
"experts.1.transformer.h.11.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 174 |
+
"experts.1.transformer.h.11.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 175 |
+
"experts.1.transformer.h.11.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 176 |
+
"experts.1.transformer.h.11.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 177 |
+
"experts.1.transformer.h.11.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 178 |
+
"experts.1.transformer.h.11.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 179 |
+
"experts.1.transformer.h.12.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 180 |
+
"experts.1.transformer.h.12.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 181 |
+
"experts.1.transformer.h.12.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 182 |
+
"experts.1.transformer.h.12.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 183 |
+
"experts.1.transformer.h.12.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 184 |
+
"experts.1.transformer.h.12.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 185 |
+
"experts.1.transformer.h.13.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 186 |
+
"experts.1.transformer.h.13.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 187 |
+
"experts.1.transformer.h.13.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 188 |
+
"experts.1.transformer.h.13.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 189 |
+
"experts.1.transformer.h.13.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 190 |
+
"experts.1.transformer.h.13.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 191 |
+
"experts.1.transformer.h.14.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 192 |
+
"experts.1.transformer.h.14.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 193 |
+
"experts.1.transformer.h.14.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 194 |
+
"experts.1.transformer.h.14.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 195 |
+
"experts.1.transformer.h.14.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 196 |
+
"experts.1.transformer.h.14.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 197 |
+
"experts.1.transformer.h.15.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 198 |
+
"experts.1.transformer.h.15.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 199 |
+
"experts.1.transformer.h.15.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 200 |
+
"experts.1.transformer.h.15.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 201 |
+
"experts.1.transformer.h.15.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 202 |
+
"experts.1.transformer.h.15.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 203 |
+
"experts.1.transformer.h.16.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 204 |
+
"experts.1.transformer.h.16.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 205 |
+
"experts.1.transformer.h.16.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 206 |
+
"experts.1.transformer.h.16.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 207 |
+
"experts.1.transformer.h.16.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 208 |
+
"experts.1.transformer.h.16.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 209 |
+
"experts.1.transformer.h.17.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 210 |
+
"experts.1.transformer.h.17.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 211 |
+
"experts.1.transformer.h.17.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 212 |
+
"experts.1.transformer.h.17.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 213 |
+
"experts.1.transformer.h.17.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 214 |
+
"experts.1.transformer.h.17.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 215 |
+
"experts.1.transformer.h.18.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 216 |
+
"experts.1.transformer.h.18.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 217 |
+
"experts.1.transformer.h.18.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 218 |
+
"experts.1.transformer.h.18.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 219 |
+
"experts.1.transformer.h.18.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 220 |
+
"experts.1.transformer.h.18.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 221 |
+
"experts.1.transformer.h.19.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 222 |
+
"experts.1.transformer.h.19.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 223 |
+
"experts.1.transformer.h.19.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 224 |
+
"experts.1.transformer.h.19.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 225 |
+
"experts.1.transformer.h.19.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 226 |
+
"experts.1.transformer.h.19.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 227 |
+
"experts.1.transformer.h.2.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 228 |
+
"experts.1.transformer.h.2.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 229 |
+
"experts.1.transformer.h.2.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 230 |
+
"experts.1.transformer.h.2.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 231 |
+
"experts.1.transformer.h.2.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 232 |
+
"experts.1.transformer.h.2.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 233 |
+
"experts.1.transformer.h.20.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 234 |
+
"experts.1.transformer.h.20.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 235 |
+
"experts.1.transformer.h.20.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 236 |
+
"experts.1.transformer.h.20.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 237 |
+
"experts.1.transformer.h.20.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 238 |
+
"experts.1.transformer.h.20.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 239 |
+
"experts.1.transformer.h.21.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 240 |
+
"experts.1.transformer.h.21.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 241 |
+
"experts.1.transformer.h.21.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 242 |
+
"experts.1.transformer.h.21.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 243 |
+
"experts.1.transformer.h.21.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 244 |
+
"experts.1.transformer.h.21.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 245 |
+
"experts.1.transformer.h.22.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 246 |
+
"experts.1.transformer.h.22.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 247 |
+
"experts.1.transformer.h.22.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 248 |
+
"experts.1.transformer.h.22.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 249 |
+
"experts.1.transformer.h.22.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 250 |
+
"experts.1.transformer.h.22.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 251 |
+
"experts.1.transformer.h.23.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 252 |
+
"experts.1.transformer.h.23.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 253 |
+
"experts.1.transformer.h.23.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 254 |
+
"experts.1.transformer.h.23.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 255 |
+
"experts.1.transformer.h.23.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 256 |
+
"experts.1.transformer.h.23.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 257 |
+
"experts.1.transformer.h.3.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 258 |
+
"experts.1.transformer.h.3.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 259 |
+
"experts.1.transformer.h.3.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 260 |
+
"experts.1.transformer.h.3.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 261 |
+
"experts.1.transformer.h.3.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 262 |
+
"experts.1.transformer.h.3.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 263 |
+
"experts.1.transformer.h.4.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 264 |
+
"experts.1.transformer.h.4.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 265 |
+
"experts.1.transformer.h.4.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 266 |
+
"experts.1.transformer.h.4.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 267 |
+
"experts.1.transformer.h.4.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 268 |
+
"experts.1.transformer.h.4.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 269 |
+
"experts.1.transformer.h.5.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 270 |
+
"experts.1.transformer.h.5.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 271 |
+
"experts.1.transformer.h.5.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 272 |
+
"experts.1.transformer.h.5.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 273 |
+
"experts.1.transformer.h.5.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 274 |
+
"experts.1.transformer.h.5.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 275 |
+
"experts.1.transformer.h.6.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 276 |
+
"experts.1.transformer.h.6.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 277 |
+
"experts.1.transformer.h.6.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 278 |
+
"experts.1.transformer.h.6.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 279 |
+
"experts.1.transformer.h.6.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 280 |
+
"experts.1.transformer.h.6.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 281 |
+
"experts.1.transformer.h.7.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 282 |
+
"experts.1.transformer.h.7.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 283 |
+
"experts.1.transformer.h.7.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 284 |
+
"experts.1.transformer.h.7.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 285 |
+
"experts.1.transformer.h.7.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 286 |
+
"experts.1.transformer.h.7.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 287 |
+
"experts.1.transformer.h.8.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 288 |
+
"experts.1.transformer.h.8.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 289 |
+
"experts.1.transformer.h.8.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 290 |
+
"experts.1.transformer.h.8.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 291 |
+
"experts.1.transformer.h.8.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 292 |
+
"experts.1.transformer.h.8.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 293 |
+
"experts.1.transformer.h.9.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 294 |
+
"experts.1.transformer.h.9.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 295 |
+
"experts.1.transformer.h.9.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 296 |
+
"experts.1.transformer.h.9.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 297 |
+
"experts.1.transformer.h.9.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 298 |
+
"experts.1.transformer.h.9.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 299 |
+
"experts.1.transformer.ln_f.weight": "model-00001-of-00003.safetensors",
|
| 300 |
+
"experts.1.transformer.wpe.weight": "model-00001-of-00003.safetensors",
|
| 301 |
+
"experts.1.transformer.wte.weight": "model-00001-of-00003.safetensors",
|
| 302 |
+
"experts.2.lm_head.weight": "model-00002-of-00003.safetensors",
|
| 303 |
+
"experts.2.transformer.h.0.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 304 |
+
"experts.2.transformer.h.0.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 305 |
+
"experts.2.transformer.h.0.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 306 |
+
"experts.2.transformer.h.0.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 307 |
+
"experts.2.transformer.h.0.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 308 |
+
"experts.2.transformer.h.0.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 309 |
+
"experts.2.transformer.h.1.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 310 |
+
"experts.2.transformer.h.1.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 311 |
+
"experts.2.transformer.h.1.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 312 |
+
"experts.2.transformer.h.1.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 313 |
+
"experts.2.transformer.h.1.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 314 |
+
"experts.2.transformer.h.1.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 315 |
+
"experts.2.transformer.h.10.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 316 |
+
"experts.2.transformer.h.10.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 317 |
+
"experts.2.transformer.h.10.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 318 |
+
"experts.2.transformer.h.10.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 319 |
+
"experts.2.transformer.h.10.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 320 |
+
"experts.2.transformer.h.10.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 321 |
+
"experts.2.transformer.h.11.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 322 |
+
"experts.2.transformer.h.11.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 323 |
+
"experts.2.transformer.h.11.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 324 |
+
"experts.2.transformer.h.11.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 325 |
+
"experts.2.transformer.h.11.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 326 |
+
"experts.2.transformer.h.11.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 327 |
+
"experts.2.transformer.h.12.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 328 |
+
"experts.2.transformer.h.12.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 329 |
+
"experts.2.transformer.h.12.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 330 |
+
"experts.2.transformer.h.12.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 331 |
+
"experts.2.transformer.h.12.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 332 |
+
"experts.2.transformer.h.12.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 333 |
+
"experts.2.transformer.h.13.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 334 |
+
"experts.2.transformer.h.13.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 335 |
+
"experts.2.transformer.h.13.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 336 |
+
"experts.2.transformer.h.13.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 337 |
+
"experts.2.transformer.h.13.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 338 |
+
"experts.2.transformer.h.13.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 339 |
+
"experts.2.transformer.h.14.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 340 |
+
"experts.2.transformer.h.14.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 341 |
+
"experts.2.transformer.h.14.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 342 |
+
"experts.2.transformer.h.14.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 343 |
+
"experts.2.transformer.h.14.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 344 |
+
"experts.2.transformer.h.14.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 345 |
+
"experts.2.transformer.h.15.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 346 |
+
"experts.2.transformer.h.15.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 347 |
+
"experts.2.transformer.h.15.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 348 |
+
"experts.2.transformer.h.15.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 349 |
+
"experts.2.transformer.h.15.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 350 |
+
"experts.2.transformer.h.15.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 351 |
+
"experts.2.transformer.h.16.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 352 |
+
"experts.2.transformer.h.16.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 353 |
+
"experts.2.transformer.h.16.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 354 |
+
"experts.2.transformer.h.16.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 355 |
+
"experts.2.transformer.h.16.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 356 |
+
"experts.2.transformer.h.16.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 357 |
+
"experts.2.transformer.h.17.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 358 |
+
"experts.2.transformer.h.17.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 359 |
+
"experts.2.transformer.h.17.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 360 |
+
"experts.2.transformer.h.17.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 361 |
+
"experts.2.transformer.h.17.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 362 |
+
"experts.2.transformer.h.17.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 363 |
+
"experts.2.transformer.h.18.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 364 |
+
"experts.2.transformer.h.18.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 365 |
+
"experts.2.transformer.h.18.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 366 |
+
"experts.2.transformer.h.18.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 367 |
+
"experts.2.transformer.h.18.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 368 |
+
"experts.2.transformer.h.18.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 369 |
+
"experts.2.transformer.h.19.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 370 |
+
"experts.2.transformer.h.19.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 371 |
+
"experts.2.transformer.h.19.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 372 |
+
"experts.2.transformer.h.19.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 373 |
+
"experts.2.transformer.h.19.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 374 |
+
"experts.2.transformer.h.19.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 375 |
+
"experts.2.transformer.h.2.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 376 |
+
"experts.2.transformer.h.2.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 377 |
+
"experts.2.transformer.h.2.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 378 |
+
"experts.2.transformer.h.2.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 379 |
+
"experts.2.transformer.h.2.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 380 |
+
"experts.2.transformer.h.2.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 381 |
+
"experts.2.transformer.h.20.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 382 |
+
"experts.2.transformer.h.20.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 383 |
+
"experts.2.transformer.h.20.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 384 |
+
"experts.2.transformer.h.20.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 385 |
+
"experts.2.transformer.h.20.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 386 |
+
"experts.2.transformer.h.20.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 387 |
+
"experts.2.transformer.h.21.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 388 |
+
"experts.2.transformer.h.21.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 389 |
+
"experts.2.transformer.h.21.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 390 |
+
"experts.2.transformer.h.21.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 391 |
+
"experts.2.transformer.h.21.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 392 |
+
"experts.2.transformer.h.21.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 393 |
+
"experts.2.transformer.h.22.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 394 |
+
"experts.2.transformer.h.22.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 395 |
+
"experts.2.transformer.h.22.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 396 |
+
"experts.2.transformer.h.22.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 397 |
+
"experts.2.transformer.h.22.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 398 |
+
"experts.2.transformer.h.22.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 399 |
+
"experts.2.transformer.h.23.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 400 |
+
"experts.2.transformer.h.23.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 401 |
+
"experts.2.transformer.h.23.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 402 |
+
"experts.2.transformer.h.23.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 403 |
+
"experts.2.transformer.h.23.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 404 |
+
"experts.2.transformer.h.23.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 405 |
+
"experts.2.transformer.h.3.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 406 |
+
"experts.2.transformer.h.3.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 407 |
+
"experts.2.transformer.h.3.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 408 |
+
"experts.2.transformer.h.3.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 409 |
+
"experts.2.transformer.h.3.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 410 |
+
"experts.2.transformer.h.3.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 411 |
+
"experts.2.transformer.h.4.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 412 |
+
"experts.2.transformer.h.4.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 413 |
+
"experts.2.transformer.h.4.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 414 |
+
"experts.2.transformer.h.4.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 415 |
+
"experts.2.transformer.h.4.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 416 |
+
"experts.2.transformer.h.4.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 417 |
+
"experts.2.transformer.h.5.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 418 |
+
"experts.2.transformer.h.5.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 419 |
+
"experts.2.transformer.h.5.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 420 |
+
"experts.2.transformer.h.5.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 421 |
+
"experts.2.transformer.h.5.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 422 |
+
"experts.2.transformer.h.5.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 423 |
+
"experts.2.transformer.h.6.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 424 |
+
"experts.2.transformer.h.6.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 425 |
+
"experts.2.transformer.h.6.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 426 |
+
"experts.2.transformer.h.6.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 427 |
+
"experts.2.transformer.h.6.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 428 |
+
"experts.2.transformer.h.6.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 429 |
+
"experts.2.transformer.h.7.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 430 |
+
"experts.2.transformer.h.7.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 431 |
+
"experts.2.transformer.h.7.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 432 |
+
"experts.2.transformer.h.7.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 433 |
+
"experts.2.transformer.h.7.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 434 |
+
"experts.2.transformer.h.7.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 435 |
+
"experts.2.transformer.h.8.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 436 |
+
"experts.2.transformer.h.8.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 437 |
+
"experts.2.transformer.h.8.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 438 |
+
"experts.2.transformer.h.8.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 439 |
+
"experts.2.transformer.h.8.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 440 |
+
"experts.2.transformer.h.8.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 441 |
+
"experts.2.transformer.h.9.attn.c_attn.weight": "model-00001-of-00003.safetensors",
|
| 442 |
+
"experts.2.transformer.h.9.attn.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 443 |
+
"experts.2.transformer.h.9.ln_1.weight": "model-00001-of-00003.safetensors",
|
| 444 |
+
"experts.2.transformer.h.9.ln_2.weight": "model-00001-of-00003.safetensors",
|
| 445 |
+
"experts.2.transformer.h.9.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
|
| 446 |
+
"experts.2.transformer.h.9.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
|
| 447 |
+
"experts.2.transformer.ln_f.weight": "model-00002-of-00003.safetensors",
|
| 448 |
+
"experts.2.transformer.wpe.weight": "model-00001-of-00003.safetensors",
|
| 449 |
+
"experts.2.transformer.wte.weight": "model-00001-of-00003.safetensors",
|
| 450 |
+
"experts.3.lm_head.weight": "model-00002-of-00003.safetensors",
|
| 451 |
+
"experts.3.transformer.h.0.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 452 |
+
"experts.3.transformer.h.0.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 453 |
+
"experts.3.transformer.h.0.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 454 |
+
"experts.3.transformer.h.0.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 455 |
+
"experts.3.transformer.h.0.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 456 |
+
"experts.3.transformer.h.0.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 457 |
+
"experts.3.transformer.h.1.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 458 |
+
"experts.3.transformer.h.1.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 459 |
+
"experts.3.transformer.h.1.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 460 |
+
"experts.3.transformer.h.1.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 461 |
+
"experts.3.transformer.h.1.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 462 |
+
"experts.3.transformer.h.1.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 463 |
+
"experts.3.transformer.h.10.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 464 |
+
"experts.3.transformer.h.10.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 465 |
+
"experts.3.transformer.h.10.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 466 |
+
"experts.3.transformer.h.10.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 467 |
+
"experts.3.transformer.h.10.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 468 |
+
"experts.3.transformer.h.10.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 469 |
+
"experts.3.transformer.h.11.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 470 |
+
"experts.3.transformer.h.11.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 471 |
+
"experts.3.transformer.h.11.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 472 |
+
"experts.3.transformer.h.11.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 473 |
+
"experts.3.transformer.h.11.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 474 |
+
"experts.3.transformer.h.11.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 475 |
+
"experts.3.transformer.h.12.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 476 |
+
"experts.3.transformer.h.12.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 477 |
+
"experts.3.transformer.h.12.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 478 |
+
"experts.3.transformer.h.12.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 479 |
+
"experts.3.transformer.h.12.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 480 |
+
"experts.3.transformer.h.12.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 481 |
+
"experts.3.transformer.h.13.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 482 |
+
"experts.3.transformer.h.13.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 483 |
+
"experts.3.transformer.h.13.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 484 |
+
"experts.3.transformer.h.13.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 485 |
+
"experts.3.transformer.h.13.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 486 |
+
"experts.3.transformer.h.13.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 487 |
+
"experts.3.transformer.h.14.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 488 |
+
"experts.3.transformer.h.14.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 489 |
+
"experts.3.transformer.h.14.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 490 |
+
"experts.3.transformer.h.14.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 491 |
+
"experts.3.transformer.h.14.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 492 |
+
"experts.3.transformer.h.14.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 493 |
+
"experts.3.transformer.h.15.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 494 |
+
"experts.3.transformer.h.15.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 495 |
+
"experts.3.transformer.h.15.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 496 |
+
"experts.3.transformer.h.15.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 497 |
+
"experts.3.transformer.h.15.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 498 |
+
"experts.3.transformer.h.15.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 499 |
+
"experts.3.transformer.h.16.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 500 |
+
"experts.3.transformer.h.16.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 501 |
+
"experts.3.transformer.h.16.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 502 |
+
"experts.3.transformer.h.16.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 503 |
+
"experts.3.transformer.h.16.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 504 |
+
"experts.3.transformer.h.16.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 505 |
+
"experts.3.transformer.h.17.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 506 |
+
"experts.3.transformer.h.17.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 507 |
+
"experts.3.transformer.h.17.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 508 |
+
"experts.3.transformer.h.17.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 509 |
+
"experts.3.transformer.h.17.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 510 |
+
"experts.3.transformer.h.17.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 511 |
+
"experts.3.transformer.h.18.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 512 |
+
"experts.3.transformer.h.18.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 513 |
+
"experts.3.transformer.h.18.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 514 |
+
"experts.3.transformer.h.18.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 515 |
+
"experts.3.transformer.h.18.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 516 |
+
"experts.3.transformer.h.18.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 517 |
+
"experts.3.transformer.h.19.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 518 |
+
"experts.3.transformer.h.19.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 519 |
+
"experts.3.transformer.h.19.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 520 |
+
"experts.3.transformer.h.19.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 521 |
+
"experts.3.transformer.h.19.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 522 |
+
"experts.3.transformer.h.19.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 523 |
+
"experts.3.transformer.h.2.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 524 |
+
"experts.3.transformer.h.2.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 525 |
+
"experts.3.transformer.h.2.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 526 |
+
"experts.3.transformer.h.2.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 527 |
+
"experts.3.transformer.h.2.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 528 |
+
"experts.3.transformer.h.2.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 529 |
+
"experts.3.transformer.h.20.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 530 |
+
"experts.3.transformer.h.20.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 531 |
+
"experts.3.transformer.h.20.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 532 |
+
"experts.3.transformer.h.20.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 533 |
+
"experts.3.transformer.h.20.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 534 |
+
"experts.3.transformer.h.20.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 535 |
+
"experts.3.transformer.h.21.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 536 |
+
"experts.3.transformer.h.21.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 537 |
+
"experts.3.transformer.h.21.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 538 |
+
"experts.3.transformer.h.21.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 539 |
+
"experts.3.transformer.h.21.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 540 |
+
"experts.3.transformer.h.21.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 541 |
+
"experts.3.transformer.h.22.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 542 |
+
"experts.3.transformer.h.22.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 543 |
+
"experts.3.transformer.h.22.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 544 |
+
"experts.3.transformer.h.22.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 545 |
+
"experts.3.transformer.h.22.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 546 |
+
"experts.3.transformer.h.22.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 547 |
+
"experts.3.transformer.h.23.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 548 |
+
"experts.3.transformer.h.23.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 549 |
+
"experts.3.transformer.h.23.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 550 |
+
"experts.3.transformer.h.23.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 551 |
+
"experts.3.transformer.h.23.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 552 |
+
"experts.3.transformer.h.23.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 553 |
+
"experts.3.transformer.h.3.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 554 |
+
"experts.3.transformer.h.3.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 555 |
+
"experts.3.transformer.h.3.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 556 |
+
"experts.3.transformer.h.3.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 557 |
+
"experts.3.transformer.h.3.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 558 |
+
"experts.3.transformer.h.3.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 559 |
+
"experts.3.transformer.h.4.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 560 |
+
"experts.3.transformer.h.4.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 561 |
+
"experts.3.transformer.h.4.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 562 |
+
"experts.3.transformer.h.4.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 563 |
+
"experts.3.transformer.h.4.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 564 |
+
"experts.3.transformer.h.4.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 565 |
+
"experts.3.transformer.h.5.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 566 |
+
"experts.3.transformer.h.5.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 567 |
+
"experts.3.transformer.h.5.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 568 |
+
"experts.3.transformer.h.5.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 569 |
+
"experts.3.transformer.h.5.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 570 |
+
"experts.3.transformer.h.5.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 571 |
+
"experts.3.transformer.h.6.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 572 |
+
"experts.3.transformer.h.6.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 573 |
+
"experts.3.transformer.h.6.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 574 |
+
"experts.3.transformer.h.6.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 575 |
+
"experts.3.transformer.h.6.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 576 |
+
"experts.3.transformer.h.6.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 577 |
+
"experts.3.transformer.h.7.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 578 |
+
"experts.3.transformer.h.7.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 579 |
+
"experts.3.transformer.h.7.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 580 |
+
"experts.3.transformer.h.7.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 581 |
+
"experts.3.transformer.h.7.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 582 |
+
"experts.3.transformer.h.7.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 583 |
+
"experts.3.transformer.h.8.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 584 |
+
"experts.3.transformer.h.8.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 585 |
+
"experts.3.transformer.h.8.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 586 |
+
"experts.3.transformer.h.8.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 587 |
+
"experts.3.transformer.h.8.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 588 |
+
"experts.3.transformer.h.8.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 589 |
+
"experts.3.transformer.h.9.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 590 |
+
"experts.3.transformer.h.9.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 591 |
+
"experts.3.transformer.h.9.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 592 |
+
"experts.3.transformer.h.9.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 593 |
+
"experts.3.transformer.h.9.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 594 |
+
"experts.3.transformer.h.9.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 595 |
+
"experts.3.transformer.ln_f.weight": "model-00002-of-00003.safetensors",
|
| 596 |
+
"experts.3.transformer.wpe.weight": "model-00002-of-00003.safetensors",
|
| 597 |
+
"experts.3.transformer.wte.weight": "model-00002-of-00003.safetensors",
|
| 598 |
+
"experts.4.lm_head.weight": "model-00002-of-00003.safetensors",
|
| 599 |
+
"experts.4.transformer.h.0.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 600 |
+
"experts.4.transformer.h.0.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 601 |
+
"experts.4.transformer.h.0.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 602 |
+
"experts.4.transformer.h.0.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 603 |
+
"experts.4.transformer.h.0.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 604 |
+
"experts.4.transformer.h.0.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 605 |
+
"experts.4.transformer.h.1.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 606 |
+
"experts.4.transformer.h.1.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 607 |
+
"experts.4.transformer.h.1.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 608 |
+
"experts.4.transformer.h.1.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 609 |
+
"experts.4.transformer.h.1.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 610 |
+
"experts.4.transformer.h.1.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 611 |
+
"experts.4.transformer.h.10.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 612 |
+
"experts.4.transformer.h.10.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 613 |
+
"experts.4.transformer.h.10.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 614 |
+
"experts.4.transformer.h.10.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 615 |
+
"experts.4.transformer.h.10.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 616 |
+
"experts.4.transformer.h.10.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 617 |
+
"experts.4.transformer.h.11.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 618 |
+
"experts.4.transformer.h.11.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 619 |
+
"experts.4.transformer.h.11.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 620 |
+
"experts.4.transformer.h.11.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 621 |
+
"experts.4.transformer.h.11.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 622 |
+
"experts.4.transformer.h.11.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 623 |
+
"experts.4.transformer.h.12.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 624 |
+
"experts.4.transformer.h.12.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 625 |
+
"experts.4.transformer.h.12.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 626 |
+
"experts.4.transformer.h.12.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 627 |
+
"experts.4.transformer.h.12.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 628 |
+
"experts.4.transformer.h.12.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 629 |
+
"experts.4.transformer.h.13.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 630 |
+
"experts.4.transformer.h.13.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 631 |
+
"experts.4.transformer.h.13.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 632 |
+
"experts.4.transformer.h.13.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 633 |
+
"experts.4.transformer.h.13.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 634 |
+
"experts.4.transformer.h.13.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 635 |
+
"experts.4.transformer.h.14.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 636 |
+
"experts.4.transformer.h.14.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 637 |
+
"experts.4.transformer.h.14.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 638 |
+
"experts.4.transformer.h.14.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 639 |
+
"experts.4.transformer.h.14.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 640 |
+
"experts.4.transformer.h.14.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 641 |
+
"experts.4.transformer.h.15.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 642 |
+
"experts.4.transformer.h.15.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 643 |
+
"experts.4.transformer.h.15.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 644 |
+
"experts.4.transformer.h.15.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 645 |
+
"experts.4.transformer.h.15.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 646 |
+
"experts.4.transformer.h.15.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 647 |
+
"experts.4.transformer.h.16.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 648 |
+
"experts.4.transformer.h.16.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 649 |
+
"experts.4.transformer.h.16.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 650 |
+
"experts.4.transformer.h.16.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 651 |
+
"experts.4.transformer.h.16.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 652 |
+
"experts.4.transformer.h.16.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 653 |
+
"experts.4.transformer.h.17.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 654 |
+
"experts.4.transformer.h.17.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 655 |
+
"experts.4.transformer.h.17.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 656 |
+
"experts.4.transformer.h.17.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 657 |
+
"experts.4.transformer.h.17.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 658 |
+
"experts.4.transformer.h.17.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 659 |
+
"experts.4.transformer.h.18.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 660 |
+
"experts.4.transformer.h.18.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 661 |
+
"experts.4.transformer.h.18.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 662 |
+
"experts.4.transformer.h.18.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 663 |
+
"experts.4.transformer.h.18.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 664 |
+
"experts.4.transformer.h.18.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 665 |
+
"experts.4.transformer.h.19.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 666 |
+
"experts.4.transformer.h.19.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 667 |
+
"experts.4.transformer.h.19.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 668 |
+
"experts.4.transformer.h.19.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 669 |
+
"experts.4.transformer.h.19.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 670 |
+
"experts.4.transformer.h.19.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 671 |
+
"experts.4.transformer.h.2.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 672 |
+
"experts.4.transformer.h.2.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 673 |
+
"experts.4.transformer.h.2.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 674 |
+
"experts.4.transformer.h.2.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 675 |
+
"experts.4.transformer.h.2.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 676 |
+
"experts.4.transformer.h.2.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 677 |
+
"experts.4.transformer.h.20.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 678 |
+
"experts.4.transformer.h.20.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 679 |
+
"experts.4.transformer.h.20.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 680 |
+
"experts.4.transformer.h.20.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 681 |
+
"experts.4.transformer.h.20.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 682 |
+
"experts.4.transformer.h.20.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 683 |
+
"experts.4.transformer.h.21.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 684 |
+
"experts.4.transformer.h.21.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 685 |
+
"experts.4.transformer.h.21.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 686 |
+
"experts.4.transformer.h.21.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 687 |
+
"experts.4.transformer.h.21.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 688 |
+
"experts.4.transformer.h.21.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 689 |
+
"experts.4.transformer.h.22.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 690 |
+
"experts.4.transformer.h.22.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 691 |
+
"experts.4.transformer.h.22.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 692 |
+
"experts.4.transformer.h.22.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 693 |
+
"experts.4.transformer.h.22.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 694 |
+
"experts.4.transformer.h.22.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 695 |
+
"experts.4.transformer.h.23.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 696 |
+
"experts.4.transformer.h.23.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 697 |
+
"experts.4.transformer.h.23.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 698 |
+
"experts.4.transformer.h.23.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 699 |
+
"experts.4.transformer.h.23.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 700 |
+
"experts.4.transformer.h.23.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 701 |
+
"experts.4.transformer.h.3.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 702 |
+
"experts.4.transformer.h.3.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 703 |
+
"experts.4.transformer.h.3.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 704 |
+
"experts.4.transformer.h.3.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 705 |
+
"experts.4.transformer.h.3.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 706 |
+
"experts.4.transformer.h.3.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 707 |
+
"experts.4.transformer.h.4.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 708 |
+
"experts.4.transformer.h.4.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 709 |
+
"experts.4.transformer.h.4.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 710 |
+
"experts.4.transformer.h.4.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 711 |
+
"experts.4.transformer.h.4.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 712 |
+
"experts.4.transformer.h.4.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 713 |
+
"experts.4.transformer.h.5.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 714 |
+
"experts.4.transformer.h.5.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 715 |
+
"experts.4.transformer.h.5.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 716 |
+
"experts.4.transformer.h.5.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 717 |
+
"experts.4.transformer.h.5.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 718 |
+
"experts.4.transformer.h.5.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 719 |
+
"experts.4.transformer.h.6.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 720 |
+
"experts.4.transformer.h.6.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 721 |
+
"experts.4.transformer.h.6.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 722 |
+
"experts.4.transformer.h.6.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 723 |
+
"experts.4.transformer.h.6.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 724 |
+
"experts.4.transformer.h.6.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 725 |
+
"experts.4.transformer.h.7.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 726 |
+
"experts.4.transformer.h.7.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 727 |
+
"experts.4.transformer.h.7.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 728 |
+
"experts.4.transformer.h.7.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 729 |
+
"experts.4.transformer.h.7.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 730 |
+
"experts.4.transformer.h.7.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 731 |
+
"experts.4.transformer.h.8.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 732 |
+
"experts.4.transformer.h.8.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 733 |
+
"experts.4.transformer.h.8.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 734 |
+
"experts.4.transformer.h.8.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 735 |
+
"experts.4.transformer.h.8.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 736 |
+
"experts.4.transformer.h.8.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 737 |
+
"experts.4.transformer.h.9.attn.c_attn.weight": "model-00002-of-00003.safetensors",
|
| 738 |
+
"experts.4.transformer.h.9.attn.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 739 |
+
"experts.4.transformer.h.9.ln_1.weight": "model-00002-of-00003.safetensors",
|
| 740 |
+
"experts.4.transformer.h.9.ln_2.weight": "model-00002-of-00003.safetensors",
|
| 741 |
+
"experts.4.transformer.h.9.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
|
| 742 |
+
"experts.4.transformer.h.9.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
|
| 743 |
+
"experts.4.transformer.ln_f.weight": "model-00002-of-00003.safetensors",
|
| 744 |
+
"experts.4.transformer.wpe.weight": "model-00002-of-00003.safetensors",
|
| 745 |
+
"experts.4.transformer.wte.weight": "model-00002-of-00003.safetensors",
|
| 746 |
+
"experts.5.lm_head.weight": "model-00003-of-00003.safetensors",
|
| 747 |
+
"experts.5.transformer.h.0.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 748 |
+
"experts.5.transformer.h.0.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 749 |
+
"experts.5.transformer.h.0.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 750 |
+
"experts.5.transformer.h.0.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 751 |
+
"experts.5.transformer.h.0.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 752 |
+
"experts.5.transformer.h.0.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 753 |
+
"experts.5.transformer.h.1.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 754 |
+
"experts.5.transformer.h.1.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 755 |
+
"experts.5.transformer.h.1.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 756 |
+
"experts.5.transformer.h.1.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 757 |
+
"experts.5.transformer.h.1.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 758 |
+
"experts.5.transformer.h.1.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 759 |
+
"experts.5.transformer.h.10.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 760 |
+
"experts.5.transformer.h.10.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 761 |
+
"experts.5.transformer.h.10.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 762 |
+
"experts.5.transformer.h.10.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 763 |
+
"experts.5.transformer.h.10.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 764 |
+
"experts.5.transformer.h.10.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 765 |
+
"experts.5.transformer.h.11.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 766 |
+
"experts.5.transformer.h.11.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 767 |
+
"experts.5.transformer.h.11.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 768 |
+
"experts.5.transformer.h.11.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 769 |
+
"experts.5.transformer.h.11.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 770 |
+
"experts.5.transformer.h.11.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 771 |
+
"experts.5.transformer.h.12.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 772 |
+
"experts.5.transformer.h.12.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 773 |
+
"experts.5.transformer.h.12.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 774 |
+
"experts.5.transformer.h.12.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 775 |
+
"experts.5.transformer.h.12.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 776 |
+
"experts.5.transformer.h.12.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 777 |
+
"experts.5.transformer.h.13.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 778 |
+
"experts.5.transformer.h.13.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 779 |
+
"experts.5.transformer.h.13.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 780 |
+
"experts.5.transformer.h.13.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 781 |
+
"experts.5.transformer.h.13.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 782 |
+
"experts.5.transformer.h.13.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 783 |
+
"experts.5.transformer.h.14.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 784 |
+
"experts.5.transformer.h.14.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 785 |
+
"experts.5.transformer.h.14.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 786 |
+
"experts.5.transformer.h.14.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 787 |
+
"experts.5.transformer.h.14.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 788 |
+
"experts.5.transformer.h.14.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 789 |
+
"experts.5.transformer.h.15.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 790 |
+
"experts.5.transformer.h.15.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 791 |
+
"experts.5.transformer.h.15.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 792 |
+
"experts.5.transformer.h.15.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 793 |
+
"experts.5.transformer.h.15.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 794 |
+
"experts.5.transformer.h.15.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 795 |
+
"experts.5.transformer.h.16.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 796 |
+
"experts.5.transformer.h.16.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 797 |
+
"experts.5.transformer.h.16.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 798 |
+
"experts.5.transformer.h.16.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 799 |
+
"experts.5.transformer.h.16.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 800 |
+
"experts.5.transformer.h.16.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 801 |
+
"experts.5.transformer.h.17.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 802 |
+
"experts.5.transformer.h.17.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 803 |
+
"experts.5.transformer.h.17.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 804 |
+
"experts.5.transformer.h.17.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 805 |
+
"experts.5.transformer.h.17.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 806 |
+
"experts.5.transformer.h.17.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 807 |
+
"experts.5.transformer.h.18.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 808 |
+
"experts.5.transformer.h.18.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 809 |
+
"experts.5.transformer.h.18.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 810 |
+
"experts.5.transformer.h.18.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 811 |
+
"experts.5.transformer.h.18.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 812 |
+
"experts.5.transformer.h.18.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 813 |
+
"experts.5.transformer.h.19.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 814 |
+
"experts.5.transformer.h.19.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 815 |
+
"experts.5.transformer.h.19.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 816 |
+
"experts.5.transformer.h.19.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 817 |
+
"experts.5.transformer.h.19.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 818 |
+
"experts.5.transformer.h.19.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 819 |
+
"experts.5.transformer.h.2.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 820 |
+
"experts.5.transformer.h.2.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 821 |
+
"experts.5.transformer.h.2.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 822 |
+
"experts.5.transformer.h.2.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 823 |
+
"experts.5.transformer.h.2.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 824 |
+
"experts.5.transformer.h.2.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 825 |
+
"experts.5.transformer.h.20.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 826 |
+
"experts.5.transformer.h.20.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 827 |
+
"experts.5.transformer.h.20.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 828 |
+
"experts.5.transformer.h.20.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 829 |
+
"experts.5.transformer.h.20.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 830 |
+
"experts.5.transformer.h.20.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 831 |
+
"experts.5.transformer.h.21.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 832 |
+
"experts.5.transformer.h.21.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 833 |
+
"experts.5.transformer.h.21.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 834 |
+
"experts.5.transformer.h.21.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 835 |
+
"experts.5.transformer.h.21.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 836 |
+
"experts.5.transformer.h.21.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 837 |
+
"experts.5.transformer.h.22.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 838 |
+
"experts.5.transformer.h.22.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 839 |
+
"experts.5.transformer.h.22.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 840 |
+
"experts.5.transformer.h.22.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 841 |
+
"experts.5.transformer.h.22.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 842 |
+
"experts.5.transformer.h.22.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 843 |
+
"experts.5.transformer.h.23.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 844 |
+
"experts.5.transformer.h.23.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 845 |
+
"experts.5.transformer.h.23.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 846 |
+
"experts.5.transformer.h.23.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 847 |
+
"experts.5.transformer.h.23.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 848 |
+
"experts.5.transformer.h.23.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 849 |
+
"experts.5.transformer.h.3.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 850 |
+
"experts.5.transformer.h.3.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 851 |
+
"experts.5.transformer.h.3.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 852 |
+
"experts.5.transformer.h.3.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 853 |
+
"experts.5.transformer.h.3.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 854 |
+
"experts.5.transformer.h.3.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 855 |
+
"experts.5.transformer.h.4.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 856 |
+
"experts.5.transformer.h.4.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 857 |
+
"experts.5.transformer.h.4.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 858 |
+
"experts.5.transformer.h.4.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 859 |
+
"experts.5.transformer.h.4.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 860 |
+
"experts.5.transformer.h.4.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 861 |
+
"experts.5.transformer.h.5.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 862 |
+
"experts.5.transformer.h.5.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 863 |
+
"experts.5.transformer.h.5.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 864 |
+
"experts.5.transformer.h.5.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 865 |
+
"experts.5.transformer.h.5.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 866 |
+
"experts.5.transformer.h.5.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 867 |
+
"experts.5.transformer.h.6.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 868 |
+
"experts.5.transformer.h.6.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 869 |
+
"experts.5.transformer.h.6.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 870 |
+
"experts.5.transformer.h.6.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 871 |
+
"experts.5.transformer.h.6.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 872 |
+
"experts.5.transformer.h.6.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 873 |
+
"experts.5.transformer.h.7.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 874 |
+
"experts.5.transformer.h.7.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 875 |
+
"experts.5.transformer.h.7.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 876 |
+
"experts.5.transformer.h.7.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 877 |
+
"experts.5.transformer.h.7.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 878 |
+
"experts.5.transformer.h.7.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 879 |
+
"experts.5.transformer.h.8.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 880 |
+
"experts.5.transformer.h.8.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 881 |
+
"experts.5.transformer.h.8.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 882 |
+
"experts.5.transformer.h.8.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 883 |
+
"experts.5.transformer.h.8.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 884 |
+
"experts.5.transformer.h.8.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 885 |
+
"experts.5.transformer.h.9.attn.c_attn.weight": "model-00003-of-00003.safetensors",
|
| 886 |
+
"experts.5.transformer.h.9.attn.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 887 |
+
"experts.5.transformer.h.9.ln_1.weight": "model-00003-of-00003.safetensors",
|
| 888 |
+
"experts.5.transformer.h.9.ln_2.weight": "model-00003-of-00003.safetensors",
|
| 889 |
+
"experts.5.transformer.h.9.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
|
| 890 |
+
"experts.5.transformer.h.9.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
|
| 891 |
+
"experts.5.transformer.ln_f.weight": "model-00003-of-00003.safetensors",
|
| 892 |
+
"experts.5.transformer.wpe.weight": "model-00003-of-00003.safetensors",
|
| 893 |
+
"experts.5.transformer.wte.weight": "model-00003-of-00003.safetensors",
|
| 894 |
+
"router.0.bias": "model-00001-of-00003.safetensors",
|
| 895 |
+
"router.0.weight": "model-00001-of-00003.safetensors"
|
| 896 |
+
}
|
| 897 |
+
}
|