First model version
Browse files- README.md +75 -0
- added_tokens.json +40 -0
- config.json +44 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- pytorch_model-00001-of-00002.bin +3 -0
- pytorch_model-00002-of-00002.bin +3 -0
- pytorch_model.bin.index.json +779 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- vocab.json +0 -0
README.md
CHANGED
|
@@ -1,3 +1,78 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
+
---
|
| 5 |
+
license: apache-2.0
|
| 6 |
+
---
|
| 7 |
+
# **MoLM**
|
| 8 |
+
MoLM is a collection of MoE-based language models ranging in scale from 4 billion to 8 billion parameters. This is the repository for the 8B pretrained model, converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom.
|
| 9 |
+
|
| 10 |
+
**Model Usage**
|
| 11 |
+
To load the model, you need install the [ModuleFormer package](https://github.com/IBM/ModuleFormer). Then you can load the model with the following code:
|
| 12 |
+
```
|
| 13 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM, AutoConfig, AutoModelForSequenceClassification
|
| 14 |
+
from moduleformer import ModuleFormerForCausalLM, ModuleFormerConfig, ModuleFormerForSequenceClassification
|
| 15 |
+
AutoConfig.register("moduleformer", ModuleFormerConfig)
|
| 16 |
+
AutoModelForCausalLM.register(ModuleFormerConfig, ModuleFormerForCausalLM)
|
| 17 |
+
AutoModelForSequenceClassification.register(ModuleFormerConfig, ModuleFormerForSequenceClassification)
|
| 18 |
+
|
| 19 |
+
tokenizer = AutoTokenizer.from_pretrained('ibm/MoLM-350M-4B')
|
| 20 |
+
model = AutoModelForCausalLM.from_pretrained('ibm/MoLM-350M-4B')
|
| 21 |
+
```
|
| 22 |
+
|
| 23 |
+
**Model Details**
|
| 24 |
+
MoLM-350M-4B is a MoE-based language models. It has 4 billion parameters, but each input token will only use 350M parameteres during its inference. Thus, it's computationally equivelant to a 350M dense model.
|
| 25 |
+
MoLM-700M-8B has 8 billion parameters and computationally equivelant to a 700M dense model.
|
| 26 |
+
Both models are trained on 300 billion tokens from publicly available sources, with a learning rate of 3.0 x 10<sup>-4</sup> and a global batch-size of 3M tokens.
|
| 27 |
+
|
| 28 |
+
**Model Developers** IBM
|
| 29 |
+
|
| 30 |
+
**Variations** MoLM comes in two different parameter sizes — 4B and 8B.
|
| 31 |
+
|
| 32 |
+
**Input** Models input text only.
|
| 33 |
+
|
| 34 |
+
**Output** Models generate text only.
|
| 35 |
+
|
| 36 |
+
**Model Architecture** MoLM is an auto-regressive language model that uses the ModuleFormer architecture. It has 16 attention modules in each attention layer and 32 MLP modules in each MLP layer. During inference, the model activate 2 modules in each layer for each token condition on the inputs. MoLM-350M-4B has 24 blocks and MoLM-700M-8B has 48 blocks.
|
| 37 |
+
|
| 38 |
+
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
|
| 39 |
+
|
| 40 |
+
**Research Paper** ["ModuleFormer: Modularity Emerges from Mixture-of-Experts"](https://arxiv.org/abs/2306.04640)
|
| 41 |
+
|
| 42 |
+
## Training Data
|
| 43 |
+
MoLM was pretrained on 300 billion tokens of data from publicly available sources.
|
| 44 |
+
|
| 45 |
+
## Evaluation Results
|
| 46 |
+
|
| 47 |
+
In this section, we report the results for the MoLM-350M-4B and MoLM-700M-8B models on standard academic benchmarks.For all the evaluations, we use our internal evaluations library.
|
| 48 |
+
|
| 49 |
+
|Model|Latency|Memory|Throughput|Hellaswag|PIQA|ARC-e|ARC-c|OBQA|
|
| 50 |
+
|---|---|---|---|---|---|---|---|---|
|
| 51 |
+
||ms|GB|tokens/sec|acc|acc|acc|acc|acc|
|
| 52 |
+
|Pythia 410M|554|25|59594|33.72|66.70|51.89|21.42|18.2|
|
| 53 |
+
|GPT-Neo 1.3B|991|23|32857|38.66|71.11|56.19|23.12|21.4|
|
| 54 |
+
|Pythia 1.4B|918|42|35559|40.41|70.84|60.52|26.11|22.2|
|
| 55 |
+
|MoLM-350M-4B|497|27|71017|39.21|70.13|56.44|23.55|20.8|
|
| 56 |
+
|GPT-Neo 2.7B|1737|35|18788|42.71|72.2|61.07|27.47|23.2|
|
| 57 |
+
|Pythia 2.8B|2111|70|15522|45.34|73.99|64.35|29.35|23.8|
|
| 58 |
+
|MoLM-700M-8B|939|38|37419|43.33|72.91|62.46|27.90|23.8|
|
| 59 |
+
|
| 60 |
+
|Model| |TriviaQA| | | HumanEval| |Wikitext|
|
| 61 |
+
|---|---|---|---|---|---|---|---|
|
| 62 |
+
||0-shot |1-shot |5-shot |pass@1 |pass@10 |pass@100 |PPL|
|
| 63 |
+
|Pythia 410M |2.32 |5.02 |6.42 |1.20 |3.85 |9.98 |20.09 |
|
| 64 |
+
|GPT-Neo 1.3B |5.24 |8.01 |9.74 |3.62 |6.87 |14.50 |16.16 |
|
| 65 |
+
|Pythia 1.4B |5.30 |9.87 |12.84 |2.19 |7.31 |14.33 |14.71|
|
| 66 |
+
|MoLM-350M-4B |5.40 |11.12 |13.70 |3.04 |6.99 |13.79 |15.15 |
|
| 67 |
+
|GPT-Neo 2.7B |4.82 |11.23 |13.67 |4.89 |9.54 |17.90 |13.93 |
|
| 68 |
+
|Pythia 2.8B |7.38 |15.58 |18.98 |4.91 |11.76 |21.54 |12.68|
|
| 69 |
+
|MoLM-700M-8B |11.47 |16.73 |20.75 |5.51 |12.58 |20.40 |12.97 |
|
| 70 |
+
|
| 71 |
+
## Ethical Considerations and Limitations
|
| 72 |
+
MoLM is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, MoLM’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of MoLM, developers should perform safety testing and tuning tailored to their specific applications of the model.
|
| 73 |
+
|
| 74 |
+
## MoLM Model Index
|
| 75 |
+
|Model|MoLM|
|
| 76 |
+
|---|---|
|
| 77 |
+
|350M-4B| [Link](https://huggingface.co/ibm/MoLM-350M-4B) |
|
| 78 |
+
|700M-8B| [Link](https://huggingface.co/ibm/MoLM-700M-8B) |
|
added_tokens.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"\t\t": 50294,
|
| 3 |
+
"\t\t\t": 50293,
|
| 4 |
+
"\t\t\t\t": 50292,
|
| 5 |
+
"\t\t\t\t\t": 50291,
|
| 6 |
+
"\t\t\t\t\t\t": 50290,
|
| 7 |
+
"\t\t\t\t\t\t\t": 50289,
|
| 8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
| 9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
| 10 |
+
" ": 50286,
|
| 11 |
+
" ": 50285,
|
| 12 |
+
" ": 50284,
|
| 13 |
+
" ": 50283,
|
| 14 |
+
" ": 50282,
|
| 15 |
+
" ": 50281,
|
| 16 |
+
" ": 50280,
|
| 17 |
+
" ": 50279,
|
| 18 |
+
" ": 50278,
|
| 19 |
+
" ": 50277,
|
| 20 |
+
" ": 50276,
|
| 21 |
+
" ": 50275,
|
| 22 |
+
" ": 50274,
|
| 23 |
+
" ": 50273,
|
| 24 |
+
" ": 50272,
|
| 25 |
+
" ": 50271,
|
| 26 |
+
" ": 50270,
|
| 27 |
+
" ": 50269,
|
| 28 |
+
" ": 50268,
|
| 29 |
+
" ": 50267,
|
| 30 |
+
" ": 50266,
|
| 31 |
+
" ": 50265,
|
| 32 |
+
" ": 50264,
|
| 33 |
+
" ": 50263,
|
| 34 |
+
" ": 50262,
|
| 35 |
+
" ": 50261,
|
| 36 |
+
" ": 50260,
|
| 37 |
+
" ": 50259,
|
| 38 |
+
" ": 50258,
|
| 39 |
+
" ": 50257
|
| 40 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./MoLM-700M-8B",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"ModuleFormerForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"att_func": "stickbreaking",
|
| 8 |
+
"att_hidden": 1024,
|
| 9 |
+
"attn_pdrop": 0,
|
| 10 |
+
"aux_loss_type": "mi",
|
| 11 |
+
"aux_loss_weight": 0,
|
| 12 |
+
"block_size": 512,
|
| 13 |
+
"bos_token_id": 50256,
|
| 14 |
+
"embd_pdrop": 0,
|
| 15 |
+
"eos_token_id": 50256,
|
| 16 |
+
"ffd_hidden": 2048,
|
| 17 |
+
"gate_type": "mlp",
|
| 18 |
+
"gating_size": 256,
|
| 19 |
+
"history_length": 512,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"k_att": 2,
|
| 22 |
+
"k_mlp": 2,
|
| 23 |
+
"layer_norm_epsilon": 1e-05,
|
| 24 |
+
"local_size": 1,
|
| 25 |
+
"model_type": "moduleformer",
|
| 26 |
+
"moe_pdrop": 0,
|
| 27 |
+
"moe_type": "moe",
|
| 28 |
+
"n_att_experts": 16,
|
| 29 |
+
"n_ctx": 24576,
|
| 30 |
+
"n_embd": 1024,
|
| 31 |
+
"n_head": 1,
|
| 32 |
+
"n_layer": 48,
|
| 33 |
+
"n_mlp_experts": 32,
|
| 34 |
+
"pre_norm": true,
|
| 35 |
+
"resid_pdrop": 0,
|
| 36 |
+
"sample_topk": 0,
|
| 37 |
+
"tie_word_embeddings": false,
|
| 38 |
+
"torch_dtype": "bfloat16",
|
| 39 |
+
"transformers_version": "4.28.1",
|
| 40 |
+
"universal": false,
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50295,
|
| 43 |
+
"world_size": null
|
| 44 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.28.1"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model-00001-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52477624553ada43d5b61d562756ec8cca326714ca1ff0fab751a4192c3e65b4
|
| 3 |
+
size 9993270641
|
pytorch_model-00002-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd2504c16d078188953043c0486374925e2c10faae64de0b3e9a621e3faaef42
|
| 3 |
+
size 6522083237
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,779 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 16515088384
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
| 7 |
+
"transformer.h.0.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 8 |
+
"transformer.h.0.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 9 |
+
"transformer.h.0.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 10 |
+
"transformer.h.0.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 11 |
+
"transformer.h.0.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 12 |
+
"transformer.h.0.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 13 |
+
"transformer.h.0.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 14 |
+
"transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 15 |
+
"transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 16 |
+
"transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 17 |
+
"transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 18 |
+
"transformer.h.0.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 19 |
+
"transformer.h.0.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 20 |
+
"transformer.h.0.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 21 |
+
"transformer.h.0.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 22 |
+
"transformer.h.0.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 23 |
+
"transformer.h.1.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 24 |
+
"transformer.h.1.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 25 |
+
"transformer.h.1.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 26 |
+
"transformer.h.1.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 27 |
+
"transformer.h.1.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 28 |
+
"transformer.h.1.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 29 |
+
"transformer.h.1.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 30 |
+
"transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 31 |
+
"transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 32 |
+
"transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 33 |
+
"transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 34 |
+
"transformer.h.1.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 35 |
+
"transformer.h.1.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 36 |
+
"transformer.h.1.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 37 |
+
"transformer.h.1.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 38 |
+
"transformer.h.1.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 39 |
+
"transformer.h.10.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 40 |
+
"transformer.h.10.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 41 |
+
"transformer.h.10.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 42 |
+
"transformer.h.10.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 43 |
+
"transformer.h.10.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 44 |
+
"transformer.h.10.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 45 |
+
"transformer.h.10.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 46 |
+
"transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 47 |
+
"transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 48 |
+
"transformer.h.10.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 49 |
+
"transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 50 |
+
"transformer.h.10.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 51 |
+
"transformer.h.10.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 52 |
+
"transformer.h.10.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 53 |
+
"transformer.h.10.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 54 |
+
"transformer.h.10.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 55 |
+
"transformer.h.11.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 56 |
+
"transformer.h.11.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 57 |
+
"transformer.h.11.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 58 |
+
"transformer.h.11.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 59 |
+
"transformer.h.11.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 60 |
+
"transformer.h.11.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 61 |
+
"transformer.h.11.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 62 |
+
"transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 63 |
+
"transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 64 |
+
"transformer.h.11.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 65 |
+
"transformer.h.11.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 66 |
+
"transformer.h.11.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 67 |
+
"transformer.h.11.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 68 |
+
"transformer.h.11.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 69 |
+
"transformer.h.11.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 70 |
+
"transformer.h.11.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 71 |
+
"transformer.h.12.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 72 |
+
"transformer.h.12.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 73 |
+
"transformer.h.12.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 74 |
+
"transformer.h.12.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 75 |
+
"transformer.h.12.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 76 |
+
"transformer.h.12.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 77 |
+
"transformer.h.12.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 78 |
+
"transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 79 |
+
"transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 80 |
+
"transformer.h.12.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 81 |
+
"transformer.h.12.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 82 |
+
"transformer.h.12.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 83 |
+
"transformer.h.12.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 84 |
+
"transformer.h.12.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 85 |
+
"transformer.h.12.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 86 |
+
"transformer.h.12.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 87 |
+
"transformer.h.13.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 88 |
+
"transformer.h.13.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 89 |
+
"transformer.h.13.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 90 |
+
"transformer.h.13.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 91 |
+
"transformer.h.13.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 92 |
+
"transformer.h.13.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 93 |
+
"transformer.h.13.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 94 |
+
"transformer.h.13.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 95 |
+
"transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 96 |
+
"transformer.h.13.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 97 |
+
"transformer.h.13.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 98 |
+
"transformer.h.13.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 99 |
+
"transformer.h.13.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 100 |
+
"transformer.h.13.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 101 |
+
"transformer.h.13.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 102 |
+
"transformer.h.13.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 103 |
+
"transformer.h.14.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 104 |
+
"transformer.h.14.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 105 |
+
"transformer.h.14.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 106 |
+
"transformer.h.14.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 107 |
+
"transformer.h.14.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 108 |
+
"transformer.h.14.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 109 |
+
"transformer.h.14.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 110 |
+
"transformer.h.14.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 111 |
+
"transformer.h.14.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 112 |
+
"transformer.h.14.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 113 |
+
"transformer.h.14.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 114 |
+
"transformer.h.14.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 115 |
+
"transformer.h.14.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 116 |
+
"transformer.h.14.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 117 |
+
"transformer.h.14.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 118 |
+
"transformer.h.14.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 119 |
+
"transformer.h.15.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 120 |
+
"transformer.h.15.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 121 |
+
"transformer.h.15.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 122 |
+
"transformer.h.15.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 123 |
+
"transformer.h.15.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 124 |
+
"transformer.h.15.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 125 |
+
"transformer.h.15.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 126 |
+
"transformer.h.15.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 127 |
+
"transformer.h.15.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 128 |
+
"transformer.h.15.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 129 |
+
"transformer.h.15.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 130 |
+
"transformer.h.15.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 131 |
+
"transformer.h.15.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 132 |
+
"transformer.h.15.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 133 |
+
"transformer.h.15.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 134 |
+
"transformer.h.15.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 135 |
+
"transformer.h.16.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 136 |
+
"transformer.h.16.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 137 |
+
"transformer.h.16.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 138 |
+
"transformer.h.16.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 139 |
+
"transformer.h.16.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 140 |
+
"transformer.h.16.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 141 |
+
"transformer.h.16.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 142 |
+
"transformer.h.16.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 143 |
+
"transformer.h.16.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 144 |
+
"transformer.h.16.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 145 |
+
"transformer.h.16.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 146 |
+
"transformer.h.16.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 147 |
+
"transformer.h.16.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 148 |
+
"transformer.h.16.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 149 |
+
"transformer.h.16.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 150 |
+
"transformer.h.16.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 151 |
+
"transformer.h.17.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 152 |
+
"transformer.h.17.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 153 |
+
"transformer.h.17.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 154 |
+
"transformer.h.17.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 155 |
+
"transformer.h.17.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 156 |
+
"transformer.h.17.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 157 |
+
"transformer.h.17.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 158 |
+
"transformer.h.17.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 159 |
+
"transformer.h.17.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 160 |
+
"transformer.h.17.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 161 |
+
"transformer.h.17.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 162 |
+
"transformer.h.17.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 163 |
+
"transformer.h.17.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 164 |
+
"transformer.h.17.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 165 |
+
"transformer.h.17.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 166 |
+
"transformer.h.17.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 167 |
+
"transformer.h.18.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 168 |
+
"transformer.h.18.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 169 |
+
"transformer.h.18.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 170 |
+
"transformer.h.18.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 171 |
+
"transformer.h.18.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 172 |
+
"transformer.h.18.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 173 |
+
"transformer.h.18.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 174 |
+
"transformer.h.18.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 175 |
+
"transformer.h.18.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 176 |
+
"transformer.h.18.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 177 |
+
"transformer.h.18.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 178 |
+
"transformer.h.18.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 179 |
+
"transformer.h.18.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 180 |
+
"transformer.h.18.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 181 |
+
"transformer.h.18.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 182 |
+
"transformer.h.18.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 183 |
+
"transformer.h.19.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 184 |
+
"transformer.h.19.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 185 |
+
"transformer.h.19.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 186 |
+
"transformer.h.19.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 187 |
+
"transformer.h.19.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 188 |
+
"transformer.h.19.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 189 |
+
"transformer.h.19.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 190 |
+
"transformer.h.19.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 191 |
+
"transformer.h.19.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 192 |
+
"transformer.h.19.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 193 |
+
"transformer.h.19.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 194 |
+
"transformer.h.19.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 195 |
+
"transformer.h.19.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 196 |
+
"transformer.h.19.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 197 |
+
"transformer.h.19.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 198 |
+
"transformer.h.19.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 199 |
+
"transformer.h.2.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 200 |
+
"transformer.h.2.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 201 |
+
"transformer.h.2.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 202 |
+
"transformer.h.2.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 203 |
+
"transformer.h.2.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 204 |
+
"transformer.h.2.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 205 |
+
"transformer.h.2.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 206 |
+
"transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 207 |
+
"transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 208 |
+
"transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 209 |
+
"transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 210 |
+
"transformer.h.2.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 211 |
+
"transformer.h.2.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 212 |
+
"transformer.h.2.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 213 |
+
"transformer.h.2.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 214 |
+
"transformer.h.2.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 215 |
+
"transformer.h.20.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 216 |
+
"transformer.h.20.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 217 |
+
"transformer.h.20.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 218 |
+
"transformer.h.20.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 219 |
+
"transformer.h.20.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 220 |
+
"transformer.h.20.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 221 |
+
"transformer.h.20.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 222 |
+
"transformer.h.20.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 223 |
+
"transformer.h.20.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 224 |
+
"transformer.h.20.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 225 |
+
"transformer.h.20.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 226 |
+
"transformer.h.20.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 227 |
+
"transformer.h.20.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 228 |
+
"transformer.h.20.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 229 |
+
"transformer.h.20.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 230 |
+
"transformer.h.20.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 231 |
+
"transformer.h.21.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 232 |
+
"transformer.h.21.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 233 |
+
"transformer.h.21.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 234 |
+
"transformer.h.21.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 235 |
+
"transformer.h.21.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 236 |
+
"transformer.h.21.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 237 |
+
"transformer.h.21.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 238 |
+
"transformer.h.21.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 239 |
+
"transformer.h.21.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 240 |
+
"transformer.h.21.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 241 |
+
"transformer.h.21.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 242 |
+
"transformer.h.21.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 243 |
+
"transformer.h.21.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 244 |
+
"transformer.h.21.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 245 |
+
"transformer.h.21.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 246 |
+
"transformer.h.21.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 247 |
+
"transformer.h.22.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 248 |
+
"transformer.h.22.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 249 |
+
"transformer.h.22.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 250 |
+
"transformer.h.22.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 251 |
+
"transformer.h.22.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 252 |
+
"transformer.h.22.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 253 |
+
"transformer.h.22.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 254 |
+
"transformer.h.22.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 255 |
+
"transformer.h.22.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 256 |
+
"transformer.h.22.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 257 |
+
"transformer.h.22.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 258 |
+
"transformer.h.22.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 259 |
+
"transformer.h.22.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 260 |
+
"transformer.h.22.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 261 |
+
"transformer.h.22.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 262 |
+
"transformer.h.22.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 263 |
+
"transformer.h.23.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 264 |
+
"transformer.h.23.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 265 |
+
"transformer.h.23.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 266 |
+
"transformer.h.23.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 267 |
+
"transformer.h.23.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 268 |
+
"transformer.h.23.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 269 |
+
"transformer.h.23.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 270 |
+
"transformer.h.23.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 271 |
+
"transformer.h.23.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 272 |
+
"transformer.h.23.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 273 |
+
"transformer.h.23.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 274 |
+
"transformer.h.23.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 275 |
+
"transformer.h.23.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 276 |
+
"transformer.h.23.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 277 |
+
"transformer.h.23.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 278 |
+
"transformer.h.23.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 279 |
+
"transformer.h.24.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 280 |
+
"transformer.h.24.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 281 |
+
"transformer.h.24.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 282 |
+
"transformer.h.24.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 283 |
+
"transformer.h.24.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 284 |
+
"transformer.h.24.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 285 |
+
"transformer.h.24.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 286 |
+
"transformer.h.24.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 287 |
+
"transformer.h.24.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 288 |
+
"transformer.h.24.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 289 |
+
"transformer.h.24.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 290 |
+
"transformer.h.24.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 291 |
+
"transformer.h.24.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 292 |
+
"transformer.h.24.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 293 |
+
"transformer.h.24.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 294 |
+
"transformer.h.24.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 295 |
+
"transformer.h.25.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 296 |
+
"transformer.h.25.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 297 |
+
"transformer.h.25.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 298 |
+
"transformer.h.25.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 299 |
+
"transformer.h.25.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 300 |
+
"transformer.h.25.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 301 |
+
"transformer.h.25.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 302 |
+
"transformer.h.25.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 303 |
+
"transformer.h.25.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 304 |
+
"transformer.h.25.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 305 |
+
"transformer.h.25.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 306 |
+
"transformer.h.25.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 307 |
+
"transformer.h.25.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 308 |
+
"transformer.h.25.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 309 |
+
"transformer.h.25.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 310 |
+
"transformer.h.25.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 311 |
+
"transformer.h.26.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 312 |
+
"transformer.h.26.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 313 |
+
"transformer.h.26.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 314 |
+
"transformer.h.26.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 315 |
+
"transformer.h.26.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 316 |
+
"transformer.h.26.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 317 |
+
"transformer.h.26.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 318 |
+
"transformer.h.26.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 319 |
+
"transformer.h.26.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 320 |
+
"transformer.h.26.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 321 |
+
"transformer.h.26.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 322 |
+
"transformer.h.26.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 323 |
+
"transformer.h.26.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 324 |
+
"transformer.h.26.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 325 |
+
"transformer.h.26.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 326 |
+
"transformer.h.26.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 327 |
+
"transformer.h.27.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 328 |
+
"transformer.h.27.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 329 |
+
"transformer.h.27.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 330 |
+
"transformer.h.27.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 331 |
+
"transformer.h.27.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 332 |
+
"transformer.h.27.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 333 |
+
"transformer.h.27.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 334 |
+
"transformer.h.27.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 335 |
+
"transformer.h.27.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 336 |
+
"transformer.h.27.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 337 |
+
"transformer.h.27.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 338 |
+
"transformer.h.27.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 339 |
+
"transformer.h.27.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 340 |
+
"transformer.h.27.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 341 |
+
"transformer.h.27.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 342 |
+
"transformer.h.27.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 343 |
+
"transformer.h.28.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 344 |
+
"transformer.h.28.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 345 |
+
"transformer.h.28.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 346 |
+
"transformer.h.28.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 347 |
+
"transformer.h.28.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 348 |
+
"transformer.h.28.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 349 |
+
"transformer.h.28.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 350 |
+
"transformer.h.28.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 351 |
+
"transformer.h.28.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 352 |
+
"transformer.h.28.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 353 |
+
"transformer.h.28.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 354 |
+
"transformer.h.28.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 355 |
+
"transformer.h.28.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 356 |
+
"transformer.h.28.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 357 |
+
"transformer.h.28.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 358 |
+
"transformer.h.28.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 359 |
+
"transformer.h.29.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 360 |
+
"transformer.h.29.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 361 |
+
"transformer.h.29.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 362 |
+
"transformer.h.29.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 363 |
+
"transformer.h.29.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 364 |
+
"transformer.h.29.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 365 |
+
"transformer.h.29.attn.q_proj.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 366 |
+
"transformer.h.29.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 367 |
+
"transformer.h.29.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 368 |
+
"transformer.h.29.ln_2.bias": "pytorch_model-00002-of-00002.bin",
|
| 369 |
+
"transformer.h.29.ln_2.weight": "pytorch_model-00002-of-00002.bin",
|
| 370 |
+
"transformer.h.29.mlpf.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 371 |
+
"transformer.h.29.mlpf.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 372 |
+
"transformer.h.29.mlpf.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 373 |
+
"transformer.h.29.mlpf.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 374 |
+
"transformer.h.29.mlpf.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 375 |
+
"transformer.h.3.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 376 |
+
"transformer.h.3.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 377 |
+
"transformer.h.3.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 378 |
+
"transformer.h.3.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 379 |
+
"transformer.h.3.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 380 |
+
"transformer.h.3.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 381 |
+
"transformer.h.3.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 382 |
+
"transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 383 |
+
"transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 384 |
+
"transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 385 |
+
"transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 386 |
+
"transformer.h.3.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 387 |
+
"transformer.h.3.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 388 |
+
"transformer.h.3.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 389 |
+
"transformer.h.3.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 390 |
+
"transformer.h.3.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 391 |
+
"transformer.h.30.attn.cum_weight": "pytorch_model-00002-of-00002.bin",
|
| 392 |
+
"transformer.h.30.attn.mask": "pytorch_model-00002-of-00002.bin",
|
| 393 |
+
"transformer.h.30.attn.q_proj.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 394 |
+
"transformer.h.30.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 395 |
+
"transformer.h.30.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 396 |
+
"transformer.h.30.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 397 |
+
"transformer.h.30.attn.q_proj.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 398 |
+
"transformer.h.30.ln_1.bias": "pytorch_model-00002-of-00002.bin",
|
| 399 |
+
"transformer.h.30.ln_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 400 |
+
"transformer.h.30.ln_2.bias": "pytorch_model-00002-of-00002.bin",
|
| 401 |
+
"transformer.h.30.ln_2.weight": "pytorch_model-00002-of-00002.bin",
|
| 402 |
+
"transformer.h.30.mlpf.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 403 |
+
"transformer.h.30.mlpf.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 404 |
+
"transformer.h.30.mlpf.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 405 |
+
"transformer.h.30.mlpf.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 406 |
+
"transformer.h.30.mlpf.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 407 |
+
"transformer.h.31.attn.cum_weight": "pytorch_model-00002-of-00002.bin",
|
| 408 |
+
"transformer.h.31.attn.mask": "pytorch_model-00002-of-00002.bin",
|
| 409 |
+
"transformer.h.31.attn.q_proj.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 410 |
+
"transformer.h.31.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 411 |
+
"transformer.h.31.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 412 |
+
"transformer.h.31.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 413 |
+
"transformer.h.31.attn.q_proj.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 414 |
+
"transformer.h.31.ln_1.bias": "pytorch_model-00002-of-00002.bin",
|
| 415 |
+
"transformer.h.31.ln_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 416 |
+
"transformer.h.31.ln_2.bias": "pytorch_model-00002-of-00002.bin",
|
| 417 |
+
"transformer.h.31.ln_2.weight": "pytorch_model-00002-of-00002.bin",
|
| 418 |
+
"transformer.h.31.mlpf.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 419 |
+
"transformer.h.31.mlpf.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 420 |
+
"transformer.h.31.mlpf.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 421 |
+
"transformer.h.31.mlpf.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 422 |
+
"transformer.h.31.mlpf.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 423 |
+
"transformer.h.32.attn.cum_weight": "pytorch_model-00002-of-00002.bin",
|
| 424 |
+
"transformer.h.32.attn.mask": "pytorch_model-00002-of-00002.bin",
|
| 425 |
+
"transformer.h.32.attn.q_proj.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 426 |
+
"transformer.h.32.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 427 |
+
"transformer.h.32.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 428 |
+
"transformer.h.32.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 429 |
+
"transformer.h.32.attn.q_proj.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 430 |
+
"transformer.h.32.ln_1.bias": "pytorch_model-00002-of-00002.bin",
|
| 431 |
+
"transformer.h.32.ln_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 432 |
+
"transformer.h.32.ln_2.bias": "pytorch_model-00002-of-00002.bin",
|
| 433 |
+
"transformer.h.32.ln_2.weight": "pytorch_model-00002-of-00002.bin",
|
| 434 |
+
"transformer.h.32.mlpf.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 435 |
+
"transformer.h.32.mlpf.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 436 |
+
"transformer.h.32.mlpf.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 437 |
+
"transformer.h.32.mlpf.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 438 |
+
"transformer.h.32.mlpf.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 439 |
+
"transformer.h.33.attn.cum_weight": "pytorch_model-00002-of-00002.bin",
|
| 440 |
+
"transformer.h.33.attn.mask": "pytorch_model-00002-of-00002.bin",
|
| 441 |
+
"transformer.h.33.attn.q_proj.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 442 |
+
"transformer.h.33.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 443 |
+
"transformer.h.33.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 444 |
+
"transformer.h.33.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 445 |
+
"transformer.h.33.attn.q_proj.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 446 |
+
"transformer.h.33.ln_1.bias": "pytorch_model-00002-of-00002.bin",
|
| 447 |
+
"transformer.h.33.ln_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 448 |
+
"transformer.h.33.ln_2.bias": "pytorch_model-00002-of-00002.bin",
|
| 449 |
+
"transformer.h.33.ln_2.weight": "pytorch_model-00002-of-00002.bin",
|
| 450 |
+
"transformer.h.33.mlpf.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 451 |
+
"transformer.h.33.mlpf.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 452 |
+
"transformer.h.33.mlpf.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 453 |
+
"transformer.h.33.mlpf.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 454 |
+
"transformer.h.33.mlpf.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 455 |
+
"transformer.h.34.attn.cum_weight": "pytorch_model-00002-of-00002.bin",
|
| 456 |
+
"transformer.h.34.attn.mask": "pytorch_model-00002-of-00002.bin",
|
| 457 |
+
"transformer.h.34.attn.q_proj.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 458 |
+
"transformer.h.34.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 459 |
+
"transformer.h.34.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 460 |
+
"transformer.h.34.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 461 |
+
"transformer.h.34.attn.q_proj.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 462 |
+
"transformer.h.34.ln_1.bias": "pytorch_model-00002-of-00002.bin",
|
| 463 |
+
"transformer.h.34.ln_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 464 |
+
"transformer.h.34.ln_2.bias": "pytorch_model-00002-of-00002.bin",
|
| 465 |
+
"transformer.h.34.ln_2.weight": "pytorch_model-00002-of-00002.bin",
|
| 466 |
+
"transformer.h.34.mlpf.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 467 |
+
"transformer.h.34.mlpf.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 468 |
+
"transformer.h.34.mlpf.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 469 |
+
"transformer.h.34.mlpf.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 470 |
+
"transformer.h.34.mlpf.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 471 |
+
"transformer.h.35.attn.cum_weight": "pytorch_model-00002-of-00002.bin",
|
| 472 |
+
"transformer.h.35.attn.mask": "pytorch_model-00002-of-00002.bin",
|
| 473 |
+
"transformer.h.35.attn.q_proj.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 474 |
+
"transformer.h.35.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 475 |
+
"transformer.h.35.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 476 |
+
"transformer.h.35.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 477 |
+
"transformer.h.35.attn.q_proj.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 478 |
+
"transformer.h.35.ln_1.bias": "pytorch_model-00002-of-00002.bin",
|
| 479 |
+
"transformer.h.35.ln_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 480 |
+
"transformer.h.35.ln_2.bias": "pytorch_model-00002-of-00002.bin",
|
| 481 |
+
"transformer.h.35.ln_2.weight": "pytorch_model-00002-of-00002.bin",
|
| 482 |
+
"transformer.h.35.mlpf.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 483 |
+
"transformer.h.35.mlpf.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 484 |
+
"transformer.h.35.mlpf.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 485 |
+
"transformer.h.35.mlpf.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 486 |
+
"transformer.h.35.mlpf.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 487 |
+
"transformer.h.36.attn.cum_weight": "pytorch_model-00002-of-00002.bin",
|
| 488 |
+
"transformer.h.36.attn.mask": "pytorch_model-00002-of-00002.bin",
|
| 489 |
+
"transformer.h.36.attn.q_proj.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 490 |
+
"transformer.h.36.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 491 |
+
"transformer.h.36.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 492 |
+
"transformer.h.36.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 493 |
+
"transformer.h.36.attn.q_proj.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 494 |
+
"transformer.h.36.ln_1.bias": "pytorch_model-00002-of-00002.bin",
|
| 495 |
+
"transformer.h.36.ln_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 496 |
+
"transformer.h.36.ln_2.bias": "pytorch_model-00002-of-00002.bin",
|
| 497 |
+
"transformer.h.36.ln_2.weight": "pytorch_model-00002-of-00002.bin",
|
| 498 |
+
"transformer.h.36.mlpf.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 499 |
+
"transformer.h.36.mlpf.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 500 |
+
"transformer.h.36.mlpf.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 501 |
+
"transformer.h.36.mlpf.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 502 |
+
"transformer.h.36.mlpf.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 503 |
+
"transformer.h.37.attn.cum_weight": "pytorch_model-00002-of-00002.bin",
|
| 504 |
+
"transformer.h.37.attn.mask": "pytorch_model-00002-of-00002.bin",
|
| 505 |
+
"transformer.h.37.attn.q_proj.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 506 |
+
"transformer.h.37.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 507 |
+
"transformer.h.37.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 508 |
+
"transformer.h.37.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 509 |
+
"transformer.h.37.attn.q_proj.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 510 |
+
"transformer.h.37.ln_1.bias": "pytorch_model-00002-of-00002.bin",
|
| 511 |
+
"transformer.h.37.ln_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 512 |
+
"transformer.h.37.ln_2.bias": "pytorch_model-00002-of-00002.bin",
|
| 513 |
+
"transformer.h.37.ln_2.weight": "pytorch_model-00002-of-00002.bin",
|
| 514 |
+
"transformer.h.37.mlpf.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 515 |
+
"transformer.h.37.mlpf.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 516 |
+
"transformer.h.37.mlpf.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 517 |
+
"transformer.h.37.mlpf.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 518 |
+
"transformer.h.37.mlpf.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 519 |
+
"transformer.h.38.attn.cum_weight": "pytorch_model-00002-of-00002.bin",
|
| 520 |
+
"transformer.h.38.attn.mask": "pytorch_model-00002-of-00002.bin",
|
| 521 |
+
"transformer.h.38.attn.q_proj.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 522 |
+
"transformer.h.38.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 523 |
+
"transformer.h.38.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 524 |
+
"transformer.h.38.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 525 |
+
"transformer.h.38.attn.q_proj.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 526 |
+
"transformer.h.38.ln_1.bias": "pytorch_model-00002-of-00002.bin",
|
| 527 |
+
"transformer.h.38.ln_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 528 |
+
"transformer.h.38.ln_2.bias": "pytorch_model-00002-of-00002.bin",
|
| 529 |
+
"transformer.h.38.ln_2.weight": "pytorch_model-00002-of-00002.bin",
|
| 530 |
+
"transformer.h.38.mlpf.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 531 |
+
"transformer.h.38.mlpf.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 532 |
+
"transformer.h.38.mlpf.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 533 |
+
"transformer.h.38.mlpf.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 534 |
+
"transformer.h.38.mlpf.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 535 |
+
"transformer.h.39.attn.cum_weight": "pytorch_model-00002-of-00002.bin",
|
| 536 |
+
"transformer.h.39.attn.mask": "pytorch_model-00002-of-00002.bin",
|
| 537 |
+
"transformer.h.39.attn.q_proj.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 538 |
+
"transformer.h.39.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 539 |
+
"transformer.h.39.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 540 |
+
"transformer.h.39.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 541 |
+
"transformer.h.39.attn.q_proj.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 542 |
+
"transformer.h.39.ln_1.bias": "pytorch_model-00002-of-00002.bin",
|
| 543 |
+
"transformer.h.39.ln_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 544 |
+
"transformer.h.39.ln_2.bias": "pytorch_model-00002-of-00002.bin",
|
| 545 |
+
"transformer.h.39.ln_2.weight": "pytorch_model-00002-of-00002.bin",
|
| 546 |
+
"transformer.h.39.mlpf.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 547 |
+
"transformer.h.39.mlpf.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 548 |
+
"transformer.h.39.mlpf.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 549 |
+
"transformer.h.39.mlpf.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 550 |
+
"transformer.h.39.mlpf.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 551 |
+
"transformer.h.4.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 552 |
+
"transformer.h.4.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 553 |
+
"transformer.h.4.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 554 |
+
"transformer.h.4.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 555 |
+
"transformer.h.4.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 556 |
+
"transformer.h.4.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 557 |
+
"transformer.h.4.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 558 |
+
"transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 559 |
+
"transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 560 |
+
"transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 561 |
+
"transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 562 |
+
"transformer.h.4.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 563 |
+
"transformer.h.4.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 564 |
+
"transformer.h.4.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 565 |
+
"transformer.h.4.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 566 |
+
"transformer.h.4.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 567 |
+
"transformer.h.40.attn.cum_weight": "pytorch_model-00002-of-00002.bin",
|
| 568 |
+
"transformer.h.40.attn.mask": "pytorch_model-00002-of-00002.bin",
|
| 569 |
+
"transformer.h.40.attn.q_proj.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 570 |
+
"transformer.h.40.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 571 |
+
"transformer.h.40.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 572 |
+
"transformer.h.40.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 573 |
+
"transformer.h.40.attn.q_proj.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 574 |
+
"transformer.h.40.ln_1.bias": "pytorch_model-00002-of-00002.bin",
|
| 575 |
+
"transformer.h.40.ln_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 576 |
+
"transformer.h.40.ln_2.bias": "pytorch_model-00002-of-00002.bin",
|
| 577 |
+
"transformer.h.40.ln_2.weight": "pytorch_model-00002-of-00002.bin",
|
| 578 |
+
"transformer.h.40.mlpf.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 579 |
+
"transformer.h.40.mlpf.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 580 |
+
"transformer.h.40.mlpf.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 581 |
+
"transformer.h.40.mlpf.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 582 |
+
"transformer.h.40.mlpf.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 583 |
+
"transformer.h.41.attn.cum_weight": "pytorch_model-00002-of-00002.bin",
|
| 584 |
+
"transformer.h.41.attn.mask": "pytorch_model-00002-of-00002.bin",
|
| 585 |
+
"transformer.h.41.attn.q_proj.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 586 |
+
"transformer.h.41.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 587 |
+
"transformer.h.41.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 588 |
+
"transformer.h.41.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 589 |
+
"transformer.h.41.attn.q_proj.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 590 |
+
"transformer.h.41.ln_1.bias": "pytorch_model-00002-of-00002.bin",
|
| 591 |
+
"transformer.h.41.ln_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 592 |
+
"transformer.h.41.ln_2.bias": "pytorch_model-00002-of-00002.bin",
|
| 593 |
+
"transformer.h.41.ln_2.weight": "pytorch_model-00002-of-00002.bin",
|
| 594 |
+
"transformer.h.41.mlpf.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 595 |
+
"transformer.h.41.mlpf.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 596 |
+
"transformer.h.41.mlpf.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 597 |
+
"transformer.h.41.mlpf.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 598 |
+
"transformer.h.41.mlpf.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 599 |
+
"transformer.h.42.attn.cum_weight": "pytorch_model-00002-of-00002.bin",
|
| 600 |
+
"transformer.h.42.attn.mask": "pytorch_model-00002-of-00002.bin",
|
| 601 |
+
"transformer.h.42.attn.q_proj.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 602 |
+
"transformer.h.42.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 603 |
+
"transformer.h.42.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 604 |
+
"transformer.h.42.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 605 |
+
"transformer.h.42.attn.q_proj.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 606 |
+
"transformer.h.42.ln_1.bias": "pytorch_model-00002-of-00002.bin",
|
| 607 |
+
"transformer.h.42.ln_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 608 |
+
"transformer.h.42.ln_2.bias": "pytorch_model-00002-of-00002.bin",
|
| 609 |
+
"transformer.h.42.ln_2.weight": "pytorch_model-00002-of-00002.bin",
|
| 610 |
+
"transformer.h.42.mlpf.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 611 |
+
"transformer.h.42.mlpf.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 612 |
+
"transformer.h.42.mlpf.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 613 |
+
"transformer.h.42.mlpf.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 614 |
+
"transformer.h.42.mlpf.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 615 |
+
"transformer.h.43.attn.cum_weight": "pytorch_model-00002-of-00002.bin",
|
| 616 |
+
"transformer.h.43.attn.mask": "pytorch_model-00002-of-00002.bin",
|
| 617 |
+
"transformer.h.43.attn.q_proj.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 618 |
+
"transformer.h.43.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 619 |
+
"transformer.h.43.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 620 |
+
"transformer.h.43.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 621 |
+
"transformer.h.43.attn.q_proj.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 622 |
+
"transformer.h.43.ln_1.bias": "pytorch_model-00002-of-00002.bin",
|
| 623 |
+
"transformer.h.43.ln_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 624 |
+
"transformer.h.43.ln_2.bias": "pytorch_model-00002-of-00002.bin",
|
| 625 |
+
"transformer.h.43.ln_2.weight": "pytorch_model-00002-of-00002.bin",
|
| 626 |
+
"transformer.h.43.mlpf.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 627 |
+
"transformer.h.43.mlpf.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 628 |
+
"transformer.h.43.mlpf.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 629 |
+
"transformer.h.43.mlpf.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 630 |
+
"transformer.h.43.mlpf.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 631 |
+
"transformer.h.44.attn.cum_weight": "pytorch_model-00002-of-00002.bin",
|
| 632 |
+
"transformer.h.44.attn.mask": "pytorch_model-00002-of-00002.bin",
|
| 633 |
+
"transformer.h.44.attn.q_proj.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 634 |
+
"transformer.h.44.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 635 |
+
"transformer.h.44.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 636 |
+
"transformer.h.44.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 637 |
+
"transformer.h.44.attn.q_proj.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 638 |
+
"transformer.h.44.ln_1.bias": "pytorch_model-00002-of-00002.bin",
|
| 639 |
+
"transformer.h.44.ln_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 640 |
+
"transformer.h.44.ln_2.bias": "pytorch_model-00002-of-00002.bin",
|
| 641 |
+
"transformer.h.44.ln_2.weight": "pytorch_model-00002-of-00002.bin",
|
| 642 |
+
"transformer.h.44.mlpf.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 643 |
+
"transformer.h.44.mlpf.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 644 |
+
"transformer.h.44.mlpf.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 645 |
+
"transformer.h.44.mlpf.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 646 |
+
"transformer.h.44.mlpf.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 647 |
+
"transformer.h.45.attn.cum_weight": "pytorch_model-00002-of-00002.bin",
|
| 648 |
+
"transformer.h.45.attn.mask": "pytorch_model-00002-of-00002.bin",
|
| 649 |
+
"transformer.h.45.attn.q_proj.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 650 |
+
"transformer.h.45.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 651 |
+
"transformer.h.45.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 652 |
+
"transformer.h.45.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 653 |
+
"transformer.h.45.attn.q_proj.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 654 |
+
"transformer.h.45.ln_1.bias": "pytorch_model-00002-of-00002.bin",
|
| 655 |
+
"transformer.h.45.ln_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 656 |
+
"transformer.h.45.ln_2.bias": "pytorch_model-00002-of-00002.bin",
|
| 657 |
+
"transformer.h.45.ln_2.weight": "pytorch_model-00002-of-00002.bin",
|
| 658 |
+
"transformer.h.45.mlpf.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 659 |
+
"transformer.h.45.mlpf.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 660 |
+
"transformer.h.45.mlpf.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 661 |
+
"transformer.h.45.mlpf.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 662 |
+
"transformer.h.45.mlpf.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 663 |
+
"transformer.h.46.attn.cum_weight": "pytorch_model-00002-of-00002.bin",
|
| 664 |
+
"transformer.h.46.attn.mask": "pytorch_model-00002-of-00002.bin",
|
| 665 |
+
"transformer.h.46.attn.q_proj.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 666 |
+
"transformer.h.46.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 667 |
+
"transformer.h.46.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 668 |
+
"transformer.h.46.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 669 |
+
"transformer.h.46.attn.q_proj.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 670 |
+
"transformer.h.46.ln_1.bias": "pytorch_model-00002-of-00002.bin",
|
| 671 |
+
"transformer.h.46.ln_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 672 |
+
"transformer.h.46.ln_2.bias": "pytorch_model-00002-of-00002.bin",
|
| 673 |
+
"transformer.h.46.ln_2.weight": "pytorch_model-00002-of-00002.bin",
|
| 674 |
+
"transformer.h.46.mlpf.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 675 |
+
"transformer.h.46.mlpf.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 676 |
+
"transformer.h.46.mlpf.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 677 |
+
"transformer.h.46.mlpf.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 678 |
+
"transformer.h.46.mlpf.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 679 |
+
"transformer.h.47.attn.cum_weight": "pytorch_model-00002-of-00002.bin",
|
| 680 |
+
"transformer.h.47.attn.mask": "pytorch_model-00002-of-00002.bin",
|
| 681 |
+
"transformer.h.47.attn.q_proj.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 682 |
+
"transformer.h.47.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 683 |
+
"transformer.h.47.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 684 |
+
"transformer.h.47.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 685 |
+
"transformer.h.47.attn.q_proj.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 686 |
+
"transformer.h.47.ln_1.bias": "pytorch_model-00002-of-00002.bin",
|
| 687 |
+
"transformer.h.47.ln_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 688 |
+
"transformer.h.47.ln_2.bias": "pytorch_model-00002-of-00002.bin",
|
| 689 |
+
"transformer.h.47.ln_2.weight": "pytorch_model-00002-of-00002.bin",
|
| 690 |
+
"transformer.h.47.mlpf.experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 691 |
+
"transformer.h.47.mlpf.gate.w_gate.0.bias": "pytorch_model-00002-of-00002.bin",
|
| 692 |
+
"transformer.h.47.mlpf.gate.w_gate.0.weight": "pytorch_model-00002-of-00002.bin",
|
| 693 |
+
"transformer.h.47.mlpf.gate.w_gate.3.weight": "pytorch_model-00002-of-00002.bin",
|
| 694 |
+
"transformer.h.47.mlpf.output_experts.weight": "pytorch_model-00002-of-00002.bin",
|
| 695 |
+
"transformer.h.5.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 696 |
+
"transformer.h.5.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 697 |
+
"transformer.h.5.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 698 |
+
"transformer.h.5.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 699 |
+
"transformer.h.5.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 700 |
+
"transformer.h.5.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 701 |
+
"transformer.h.5.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 702 |
+
"transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 703 |
+
"transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 704 |
+
"transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 705 |
+
"transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 706 |
+
"transformer.h.5.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 707 |
+
"transformer.h.5.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 708 |
+
"transformer.h.5.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 709 |
+
"transformer.h.5.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 710 |
+
"transformer.h.5.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 711 |
+
"transformer.h.6.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 712 |
+
"transformer.h.6.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 713 |
+
"transformer.h.6.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 714 |
+
"transformer.h.6.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 715 |
+
"transformer.h.6.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 716 |
+
"transformer.h.6.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 717 |
+
"transformer.h.6.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 718 |
+
"transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 719 |
+
"transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 720 |
+
"transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 721 |
+
"transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 722 |
+
"transformer.h.6.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 723 |
+
"transformer.h.6.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 724 |
+
"transformer.h.6.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 725 |
+
"transformer.h.6.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 726 |
+
"transformer.h.6.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 727 |
+
"transformer.h.7.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 728 |
+
"transformer.h.7.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 729 |
+
"transformer.h.7.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 730 |
+
"transformer.h.7.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 731 |
+
"transformer.h.7.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 732 |
+
"transformer.h.7.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 733 |
+
"transformer.h.7.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 734 |
+
"transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 735 |
+
"transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 736 |
+
"transformer.h.7.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 737 |
+
"transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 738 |
+
"transformer.h.7.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 739 |
+
"transformer.h.7.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 740 |
+
"transformer.h.7.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 741 |
+
"transformer.h.7.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 742 |
+
"transformer.h.7.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 743 |
+
"transformer.h.8.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 744 |
+
"transformer.h.8.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 745 |
+
"transformer.h.8.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 746 |
+
"transformer.h.8.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 747 |
+
"transformer.h.8.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 748 |
+
"transformer.h.8.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 749 |
+
"transformer.h.8.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 750 |
+
"transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 751 |
+
"transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 752 |
+
"transformer.h.8.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 753 |
+
"transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 754 |
+
"transformer.h.8.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 755 |
+
"transformer.h.8.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 756 |
+
"transformer.h.8.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 757 |
+
"transformer.h.8.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 758 |
+
"transformer.h.8.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 759 |
+
"transformer.h.9.attn.cum_weight": "pytorch_model-00001-of-00002.bin",
|
| 760 |
+
"transformer.h.9.attn.mask": "pytorch_model-00001-of-00002.bin",
|
| 761 |
+
"transformer.h.9.attn.q_proj.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 762 |
+
"transformer.h.9.attn.q_proj.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 763 |
+
"transformer.h.9.attn.q_proj.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 764 |
+
"transformer.h.9.attn.q_proj.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 765 |
+
"transformer.h.9.attn.q_proj.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 766 |
+
"transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00002.bin",
|
| 767 |
+
"transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 768 |
+
"transformer.h.9.ln_2.bias": "pytorch_model-00001-of-00002.bin",
|
| 769 |
+
"transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00002.bin",
|
| 770 |
+
"transformer.h.9.mlpf.experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 771 |
+
"transformer.h.9.mlpf.gate.w_gate.0.bias": "pytorch_model-00001-of-00002.bin",
|
| 772 |
+
"transformer.h.9.mlpf.gate.w_gate.0.weight": "pytorch_model-00001-of-00002.bin",
|
| 773 |
+
"transformer.h.9.mlpf.gate.w_gate.3.weight": "pytorch_model-00001-of-00002.bin",
|
| 774 |
+
"transformer.h.9.mlpf.output_experts.weight": "pytorch_model-00001-of-00002.bin",
|
| 775 |
+
"transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
|
| 776 |
+
"transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
|
| 777 |
+
"transformer.wte.weight": "pytorch_model-00001-of-00002.bin"
|
| 778 |
+
}
|
| 779 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
| 5 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"model_max_length": 2048,
|
| 7 |
+
"tokenizer_class": "CodeGenTokenizer",
|
| 8 |
+
"unk_token": "<|endoftext|>"
|
| 9 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|