Overwrite with source/main @
Browse files- Modelfile +14 -0
- README.md +0 -199
- config.json +2 -2
- generation_config.json +13 -0
- model-00004-of-00007.safetensors → model-00001-of-00004.safetensors +2 -2
- model-00001-of-00007.safetensors → model-00002-of-00004.safetensors +2 -2
- model-00002-of-00007.safetensors → model-00003-of-00004.safetensors +2 -2
- model-00003-of-00007.safetensors → model-00004-of-00004.safetensors +2 -2
- model-00005-of-00007.safetensors +0 -3
- model-00006-of-00007.safetensors +0 -3
- model-00007-of-00007.safetensors +0 -3
- model.safetensors.index.json +400 -399
Modelfile
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# ollama modelfile auto-generated by llamafactory
|
| 2 |
+
|
| 3 |
+
FROM .
|
| 4 |
+
|
| 5 |
+
TEMPLATE """{{ if .System }}<|im_start|>system
|
| 6 |
+
{{ .System }}<|im_end|>
|
| 7 |
+
{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|im_start|>user
|
| 8 |
+
{{ .Content }}<|im_end|>
|
| 9 |
+
<|im_start|>assistant
|
| 10 |
+
{{ else if eq .Role "assistant" }}{{ .Content }}<|im_end|>
|
| 11 |
+
{{ end }}{{ end }}"""
|
| 12 |
+
|
| 13 |
+
PARAMETER stop "<|im_end|>"
|
| 14 |
+
PARAMETER num_ctx 4096
|
README.md
DELETED
|
@@ -1,199 +0,0 @@
|
|
| 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]:** [arxiv.org/abs/2505.15277]
|
| 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
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
|
@@ -22,7 +22,7 @@
|
|
| 22 |
"rope_theta": 1000000,
|
| 23 |
"sliding_window": null,
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
-
"torch_dtype": "
|
| 26 |
"transformers_version": "4.51.3",
|
| 27 |
"use_cache": true,
|
| 28 |
"use_sliding_window": false,
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
|
|
|
| 22 |
"rope_theta": 1000000,
|
| 23 |
"sliding_window": null,
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
"transformers_version": "4.51.3",
|
| 27 |
"use_cache": true,
|
| 28 |
"use_sliding_window": false,
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.51.3"
|
| 13 |
+
}
|
model-00004-of-00007.safetensors → model-00001-of-00004.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f22357f96b437972fe5c8621f787c8581a86e2ea7fe4229647d43d5160aa1296
|
| 3 |
+
size 4902257696
|
model-00001-of-00007.safetensors → model-00002-of-00004.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98c87f67fa42c58c01ad5531e3404065b0f825f0df498ff61729a80968a0717e
|
| 3 |
+
size 4915960368
|
model-00002-of-00007.safetensors → model-00003-of-00004.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1d8154a12d65e94aa7cb1360ab72be31e387f7b8ab302bdfa35412428a51b4e
|
| 3 |
+
size 4983068496
|
model-00003-of-00007.safetensors → model-00004-of-00004.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c60ea625dbb0b83c147f18b499686f6f6b7499f3ef2719d9bb555f2a97efd7e
|
| 3 |
+
size 1580230264
|
model-00005-of-00007.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b885092254922885d7d73d4bbb90ae441a9ef1b9d779d2f780d4d98a4a7b28aa
|
| 3 |
-
size 4832048272
|
|
|
|
|
|
|
|
|
|
|
|
model-00006-of-00007.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:efc070f2b22e67718b9d092cd0c5a76d33d6fa54b557c60c54b53cb681949409
|
| 3 |
-
size 4832048264
|
|
|
|
|
|
|
|
|
|
|
|
model-00007-of-00007.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:194fb63d055ca7520f190f403729bb8c47a3f29716e9996ea49865d939e2debc
|
| 3 |
-
size 973163080
|
|
|
|
|
|
|
|
|
|
|
|
model.safetensors.index.json
CHANGED
|
@@ -1,405 +1,406 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"layers.0.
|
| 9 |
-
"layers.0.mlp.
|
| 10 |
-
"layers.0.mlp.
|
| 11 |
-
"layers.0.
|
| 12 |
-
"layers.0.
|
| 13 |
-
"layers.0.self_attn.
|
| 14 |
-
"layers.0.self_attn.
|
| 15 |
-
"layers.0.self_attn.
|
| 16 |
-
"layers.0.self_attn.
|
| 17 |
-
"layers.0.self_attn.
|
| 18 |
-
"layers.
|
| 19 |
-
"layers.1.
|
| 20 |
-
"layers.1.mlp.
|
| 21 |
-
"layers.1.mlp.
|
| 22 |
-
"layers.1.
|
| 23 |
-
"layers.1.
|
| 24 |
-
"layers.1.self_attn.
|
| 25 |
-
"layers.1.self_attn.
|
| 26 |
-
"layers.1.self_attn.
|
| 27 |
-
"layers.1.self_attn.
|
| 28 |
-
"layers.1.self_attn.
|
| 29 |
-
"layers.
|
| 30 |
-
"layers.10.
|
| 31 |
-
"layers.10.mlp.
|
| 32 |
-
"layers.10.mlp.
|
| 33 |
-
"layers.10.
|
| 34 |
-
"layers.10.
|
| 35 |
-
"layers.10.self_attn.
|
| 36 |
-
"layers.10.self_attn.
|
| 37 |
-
"layers.10.self_attn.
|
| 38 |
-
"layers.10.self_attn.
|
| 39 |
-
"layers.10.self_attn.
|
| 40 |
-
"layers.
|
| 41 |
-
"layers.11.
|
| 42 |
-
"layers.11.mlp.
|
| 43 |
-
"layers.11.mlp.
|
| 44 |
-
"layers.11.
|
| 45 |
-
"layers.11.
|
| 46 |
-
"layers.11.self_attn.
|
| 47 |
-
"layers.11.self_attn.
|
| 48 |
-
"layers.11.self_attn.
|
| 49 |
-
"layers.11.self_attn.
|
| 50 |
-
"layers.11.self_attn.
|
| 51 |
-
"layers.
|
| 52 |
-
"layers.12.
|
| 53 |
-
"layers.12.mlp.
|
| 54 |
-
"layers.12.mlp.
|
| 55 |
-
"layers.12.
|
| 56 |
-
"layers.12.
|
| 57 |
-
"layers.12.self_attn.
|
| 58 |
-
"layers.12.self_attn.
|
| 59 |
-
"layers.12.self_attn.
|
| 60 |
-
"layers.12.self_attn.
|
| 61 |
-
"layers.12.self_attn.
|
| 62 |
-
"layers.
|
| 63 |
-
"layers.13.
|
| 64 |
-
"layers.13.mlp.
|
| 65 |
-
"layers.13.mlp.
|
| 66 |
-
"layers.13.
|
| 67 |
-
"layers.13.
|
| 68 |
-
"layers.13.self_attn.
|
| 69 |
-
"layers.13.self_attn.
|
| 70 |
-
"layers.13.self_attn.
|
| 71 |
-
"layers.13.self_attn.
|
| 72 |
-
"layers.13.self_attn.
|
| 73 |
-
"layers.
|
| 74 |
-
"layers.14.
|
| 75 |
-
"layers.14.mlp.
|
| 76 |
-
"layers.14.mlp.
|
| 77 |
-
"layers.14.
|
| 78 |
-
"layers.14.
|
| 79 |
-
"layers.14.self_attn.
|
| 80 |
-
"layers.14.self_attn.
|
| 81 |
-
"layers.14.self_attn.
|
| 82 |
-
"layers.14.self_attn.
|
| 83 |
-
"layers.14.self_attn.
|
| 84 |
-
"layers.
|
| 85 |
-
"layers.15.
|
| 86 |
-
"layers.15.mlp.
|
| 87 |
-
"layers.15.mlp.
|
| 88 |
-
"layers.15.
|
| 89 |
-
"layers.15.
|
| 90 |
-
"layers.15.self_attn.
|
| 91 |
-
"layers.15.self_attn.
|
| 92 |
-
"layers.15.self_attn.
|
| 93 |
-
"layers.15.self_attn.
|
| 94 |
-
"layers.15.self_attn.
|
| 95 |
-
"layers.
|
| 96 |
-
"layers.16.
|
| 97 |
-
"layers.16.mlp.
|
| 98 |
-
"layers.16.mlp.
|
| 99 |
-
"layers.16.
|
| 100 |
-
"layers.16.
|
| 101 |
-
"layers.16.self_attn.
|
| 102 |
-
"layers.16.self_attn.
|
| 103 |
-
"layers.16.self_attn.
|
| 104 |
-
"layers.16.self_attn.
|
| 105 |
-
"layers.16.self_attn.
|
| 106 |
-
"layers.
|
| 107 |
-
"layers.17.
|
| 108 |
-
"layers.17.mlp.
|
| 109 |
-
"layers.17.mlp.
|
| 110 |
-
"layers.17.
|
| 111 |
-
"layers.17.
|
| 112 |
-
"layers.17.self_attn.
|
| 113 |
-
"layers.17.self_attn.
|
| 114 |
-
"layers.17.self_attn.
|
| 115 |
-
"layers.17.self_attn.
|
| 116 |
-
"layers.17.self_attn.
|
| 117 |
-
"layers.
|
| 118 |
-
"layers.18.
|
| 119 |
-
"layers.18.mlp.
|
| 120 |
-
"layers.18.mlp.
|
| 121 |
-
"layers.18.
|
| 122 |
-
"layers.18.
|
| 123 |
-
"layers.18.self_attn.
|
| 124 |
-
"layers.18.self_attn.
|
| 125 |
-
"layers.18.self_attn.
|
| 126 |
-
"layers.18.self_attn.
|
| 127 |
-
"layers.18.self_attn.
|
| 128 |
-
"layers.
|
| 129 |
-
"layers.19.
|
| 130 |
-
"layers.19.mlp.
|
| 131 |
-
"layers.19.mlp.
|
| 132 |
-
"layers.19.
|
| 133 |
-
"layers.19.
|
| 134 |
-
"layers.19.self_attn.
|
| 135 |
-
"layers.19.self_attn.
|
| 136 |
-
"layers.19.self_attn.
|
| 137 |
-
"layers.19.self_attn.
|
| 138 |
-
"layers.19.self_attn.
|
| 139 |
-
"layers.
|
| 140 |
-
"layers.2.
|
| 141 |
-
"layers.2.mlp.
|
| 142 |
-
"layers.2.mlp.
|
| 143 |
-
"layers.2.
|
| 144 |
-
"layers.2.
|
| 145 |
-
"layers.2.self_attn.
|
| 146 |
-
"layers.2.self_attn.
|
| 147 |
-
"layers.2.self_attn.
|
| 148 |
-
"layers.2.self_attn.
|
| 149 |
-
"layers.2.self_attn.
|
| 150 |
-
"layers.
|
| 151 |
-
"layers.20.
|
| 152 |
-
"layers.20.mlp.
|
| 153 |
-
"layers.20.mlp.
|
| 154 |
-
"layers.20.
|
| 155 |
-
"layers.20.
|
| 156 |
-
"layers.20.self_attn.
|
| 157 |
-
"layers.20.self_attn.
|
| 158 |
-
"layers.20.self_attn.
|
| 159 |
-
"layers.20.self_attn.
|
| 160 |
-
"layers.20.self_attn.
|
| 161 |
-
"layers.
|
| 162 |
-
"layers.21.
|
| 163 |
-
"layers.21.mlp.
|
| 164 |
-
"layers.21.mlp.
|
| 165 |
-
"layers.21.
|
| 166 |
-
"layers.21.
|
| 167 |
-
"layers.21.self_attn.
|
| 168 |
-
"layers.21.self_attn.
|
| 169 |
-
"layers.21.self_attn.
|
| 170 |
-
"layers.21.self_attn.
|
| 171 |
-
"layers.21.self_attn.
|
| 172 |
-
"layers.
|
| 173 |
-
"layers.22.
|
| 174 |
-
"layers.22.mlp.
|
| 175 |
-
"layers.22.mlp.
|
| 176 |
-
"layers.22.
|
| 177 |
-
"layers.22.
|
| 178 |
-
"layers.22.self_attn.
|
| 179 |
-
"layers.22.self_attn.
|
| 180 |
-
"layers.22.self_attn.
|
| 181 |
-
"layers.22.self_attn.
|
| 182 |
-
"layers.22.self_attn.
|
| 183 |
-
"layers.
|
| 184 |
-
"layers.23.
|
| 185 |
-
"layers.23.mlp.
|
| 186 |
-
"layers.23.mlp.
|
| 187 |
-
"layers.23.
|
| 188 |
-
"layers.23.
|
| 189 |
-
"layers.23.self_attn.
|
| 190 |
-
"layers.23.self_attn.
|
| 191 |
-
"layers.23.self_attn.
|
| 192 |
-
"layers.23.self_attn.
|
| 193 |
-
"layers.23.self_attn.
|
| 194 |
-
"layers.
|
| 195 |
-
"layers.24.
|
| 196 |
-
"layers.24.mlp.
|
| 197 |
-
"layers.24.mlp.
|
| 198 |
-
"layers.24.
|
| 199 |
-
"layers.24.
|
| 200 |
-
"layers.24.self_attn.
|
| 201 |
-
"layers.24.self_attn.
|
| 202 |
-
"layers.24.self_attn.
|
| 203 |
-
"layers.24.self_attn.
|
| 204 |
-
"layers.24.self_attn.
|
| 205 |
-
"layers.
|
| 206 |
-
"layers.25.
|
| 207 |
-
"layers.25.mlp.
|
| 208 |
-
"layers.25.mlp.
|
| 209 |
-
"layers.25.
|
| 210 |
-
"layers.25.
|
| 211 |
-
"layers.25.self_attn.
|
| 212 |
-
"layers.25.self_attn.
|
| 213 |
-
"layers.25.self_attn.
|
| 214 |
-
"layers.25.self_attn.
|
| 215 |
-
"layers.25.self_attn.
|
| 216 |
-
"layers.
|
| 217 |
-
"layers.26.
|
| 218 |
-
"layers.26.mlp.
|
| 219 |
-
"layers.26.mlp.
|
| 220 |
-
"layers.26.
|
| 221 |
-
"layers.26.
|
| 222 |
-
"layers.26.self_attn.
|
| 223 |
-
"layers.26.self_attn.
|
| 224 |
-
"layers.26.self_attn.
|
| 225 |
-
"layers.26.self_attn.
|
| 226 |
-
"layers.26.self_attn.
|
| 227 |
-
"layers.
|
| 228 |
-
"layers.27.
|
| 229 |
-
"layers.27.mlp.
|
| 230 |
-
"layers.27.mlp.
|
| 231 |
-
"layers.27.
|
| 232 |
-
"layers.27.
|
| 233 |
-
"layers.27.self_attn.
|
| 234 |
-
"layers.27.self_attn.
|
| 235 |
-
"layers.27.self_attn.
|
| 236 |
-
"layers.27.self_attn.
|
| 237 |
-
"layers.27.self_attn.
|
| 238 |
-
"layers.
|
| 239 |
-
"layers.28.
|
| 240 |
-
"layers.28.mlp.
|
| 241 |
-
"layers.28.mlp.
|
| 242 |
-
"layers.28.
|
| 243 |
-
"layers.28.
|
| 244 |
-
"layers.28.self_attn.
|
| 245 |
-
"layers.28.self_attn.
|
| 246 |
-
"layers.28.self_attn.
|
| 247 |
-
"layers.28.self_attn.
|
| 248 |
-
"layers.28.self_attn.
|
| 249 |
-
"layers.
|
| 250 |
-
"layers.29.
|
| 251 |
-
"layers.29.mlp.
|
| 252 |
-
"layers.29.mlp.
|
| 253 |
-
"layers.29.
|
| 254 |
-
"layers.29.
|
| 255 |
-
"layers.29.self_attn.
|
| 256 |
-
"layers.29.self_attn.
|
| 257 |
-
"layers.29.self_attn.
|
| 258 |
-
"layers.29.self_attn.
|
| 259 |
-
"layers.29.self_attn.
|
| 260 |
-
"layers.
|
| 261 |
-
"layers.3.
|
| 262 |
-
"layers.3.mlp.
|
| 263 |
-
"layers.3.mlp.
|
| 264 |
-
"layers.3.
|
| 265 |
-
"layers.3.
|
| 266 |
-
"layers.3.self_attn.
|
| 267 |
-
"layers.3.self_attn.
|
| 268 |
-
"layers.3.self_attn.
|
| 269 |
-
"layers.3.self_attn.
|
| 270 |
-
"layers.3.self_attn.
|
| 271 |
-
"layers.
|
| 272 |
-
"layers.30.
|
| 273 |
-
"layers.30.mlp.
|
| 274 |
-
"layers.30.mlp.
|
| 275 |
-
"layers.30.
|
| 276 |
-
"layers.30.
|
| 277 |
-
"layers.30.self_attn.
|
| 278 |
-
"layers.30.self_attn.
|
| 279 |
-
"layers.30.self_attn.
|
| 280 |
-
"layers.30.self_attn.
|
| 281 |
-
"layers.30.self_attn.
|
| 282 |
-
"layers.
|
| 283 |
-
"layers.31.
|
| 284 |
-
"layers.31.mlp.
|
| 285 |
-
"layers.31.mlp.
|
| 286 |
-
"layers.31.
|
| 287 |
-
"layers.31.
|
| 288 |
-
"layers.31.self_attn.
|
| 289 |
-
"layers.31.self_attn.
|
| 290 |
-
"layers.31.self_attn.
|
| 291 |
-
"layers.31.self_attn.
|
| 292 |
-
"layers.31.self_attn.
|
| 293 |
-
"layers.
|
| 294 |
-
"layers.32.
|
| 295 |
-
"layers.32.mlp.
|
| 296 |
-
"layers.32.mlp.
|
| 297 |
-
"layers.32.
|
| 298 |
-
"layers.32.
|
| 299 |
-
"layers.32.self_attn.
|
| 300 |
-
"layers.32.self_attn.
|
| 301 |
-
"layers.32.self_attn.
|
| 302 |
-
"layers.32.self_attn.
|
| 303 |
-
"layers.32.self_attn.
|
| 304 |
-
"layers.
|
| 305 |
-
"layers.33.
|
| 306 |
-
"layers.33.mlp.
|
| 307 |
-
"layers.33.mlp.
|
| 308 |
-
"layers.33.
|
| 309 |
-
"layers.33.
|
| 310 |
-
"layers.33.self_attn.
|
| 311 |
-
"layers.33.self_attn.
|
| 312 |
-
"layers.33.self_attn.
|
| 313 |
-
"layers.33.self_attn.
|
| 314 |
-
"layers.33.self_attn.
|
| 315 |
-
"layers.
|
| 316 |
-
"layers.34.
|
| 317 |
-
"layers.34.mlp.
|
| 318 |
-
"layers.34.mlp.
|
| 319 |
-
"layers.34.
|
| 320 |
-
"layers.34.
|
| 321 |
-
"layers.34.self_attn.
|
| 322 |
-
"layers.34.self_attn.
|
| 323 |
-
"layers.34.self_attn.
|
| 324 |
-
"layers.34.self_attn.
|
| 325 |
-
"layers.34.self_attn.
|
| 326 |
-
"layers.
|
| 327 |
-
"layers.35.
|
| 328 |
-
"layers.35.mlp.
|
| 329 |
-
"layers.35.mlp.
|
| 330 |
-
"layers.35.
|
| 331 |
-
"layers.35.
|
| 332 |
-
"layers.35.self_attn.
|
| 333 |
-
"layers.35.self_attn.
|
| 334 |
-
"layers.35.self_attn.
|
| 335 |
-
"layers.35.self_attn.
|
| 336 |
-
"layers.35.self_attn.
|
| 337 |
-
"layers.
|
| 338 |
-
"layers.4.
|
| 339 |
-
"layers.4.mlp.
|
| 340 |
-
"layers.4.mlp.
|
| 341 |
-
"layers.4.
|
| 342 |
-
"layers.4.
|
| 343 |
-
"layers.4.self_attn.
|
| 344 |
-
"layers.4.self_attn.
|
| 345 |
-
"layers.4.self_attn.
|
| 346 |
-
"layers.4.self_attn.
|
| 347 |
-
"layers.4.self_attn.
|
| 348 |
-
"layers.
|
| 349 |
-
"layers.5.
|
| 350 |
-
"layers.5.mlp.
|
| 351 |
-
"layers.5.mlp.
|
| 352 |
-
"layers.5.
|
| 353 |
-
"layers.5.
|
| 354 |
-
"layers.5.self_attn.
|
| 355 |
-
"layers.5.self_attn.
|
| 356 |
-
"layers.5.self_attn.
|
| 357 |
-
"layers.5.self_attn.
|
| 358 |
-
"layers.5.self_attn.
|
| 359 |
-
"layers.
|
| 360 |
-
"layers.6.
|
| 361 |
-
"layers.6.mlp.
|
| 362 |
-
"layers.6.mlp.
|
| 363 |
-
"layers.6.
|
| 364 |
-
"layers.6.
|
| 365 |
-
"layers.6.self_attn.
|
| 366 |
-
"layers.6.self_attn.
|
| 367 |
-
"layers.6.self_attn.
|
| 368 |
-
"layers.6.self_attn.
|
| 369 |
-
"layers.6.self_attn.
|
| 370 |
-
"layers.
|
| 371 |
-
"layers.7.
|
| 372 |
-
"layers.7.mlp.
|
| 373 |
-
"layers.7.mlp.
|
| 374 |
-
"layers.7.
|
| 375 |
-
"layers.7.
|
| 376 |
-
"layers.7.self_attn.
|
| 377 |
-
"layers.7.self_attn.
|
| 378 |
-
"layers.7.self_attn.
|
| 379 |
-
"layers.7.self_attn.
|
| 380 |
-
"layers.7.self_attn.
|
| 381 |
-
"layers.
|
| 382 |
-
"layers.8.
|
| 383 |
-
"layers.8.mlp.
|
| 384 |
-
"layers.8.mlp.
|
| 385 |
-
"layers.8.
|
| 386 |
-
"layers.8.
|
| 387 |
-
"layers.8.self_attn.
|
| 388 |
-
"layers.8.self_attn.
|
| 389 |
-
"layers.8.self_attn.
|
| 390 |
-
"layers.8.self_attn.
|
| 391 |
-
"layers.8.self_attn.
|
| 392 |
-
"layers.
|
| 393 |
-
"layers.9.
|
| 394 |
-
"layers.9.mlp.
|
| 395 |
-
"layers.9.mlp.
|
| 396 |
-
"layers.9.
|
| 397 |
-
"layers.9.
|
| 398 |
-
"layers.9.self_attn.
|
| 399 |
-
"layers.9.self_attn.
|
| 400 |
-
"layers.9.self_attn.
|
| 401 |
-
"layers.9.self_attn.
|
| 402 |
-
"layers.9.self_attn.
|
| 403 |
-
"
|
|
|
|
| 404 |
}
|
| 405 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 16381470720
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 31 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 125 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 127 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 130 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 131 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 134 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 135 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 138 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 140 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 141 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 142 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 143 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 144 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 145 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 146 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 147 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 148 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 149 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 150 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 151 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 152 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 153 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 154 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 155 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 156 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 157 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 158 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 159 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 160 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 161 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 162 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 163 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 164 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 165 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 166 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 167 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 168 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 169 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 170 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 171 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 172 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 173 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 179 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 180 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 181 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 182 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 183 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 184 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 257 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 258 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 259 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 260 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 273 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 274 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 275 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 276 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 277 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 278 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 279 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 280 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 281 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 282 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 283 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 284 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 285 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 286 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 287 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 288 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 289 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 290 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 291 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 292 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 293 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 294 |
+
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 295 |
+
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 296 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 297 |
+
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 298 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 299 |
+
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 300 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 301 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 302 |
+
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 303 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 304 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 305 |
+
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 306 |
+
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 307 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 308 |
+
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 309 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 310 |
+
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 311 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 312 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 313 |
+
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 314 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 315 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 316 |
+
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 317 |
+
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 318 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 319 |
+
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 320 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 321 |
+
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 322 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 323 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 324 |
+
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 325 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 326 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 327 |
+
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 328 |
+
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 329 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 330 |
+
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 331 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 332 |
+
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 333 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 334 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 335 |
+
"model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 336 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 337 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 338 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 339 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 340 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 341 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 342 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 343 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 344 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 345 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 346 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 347 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 348 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 349 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 350 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 351 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 352 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 353 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 354 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 355 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 356 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 357 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 358 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 359 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 361 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 362 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 363 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 365 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 366 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 367 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 368 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 369 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 370 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 371 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 372 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 373 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 374 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 375 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 376 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 377 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 378 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 379 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 380 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 381 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 382 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 383 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 384 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 385 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 386 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 387 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 388 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 389 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 390 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 391 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 392 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 393 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 394 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 395 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 396 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 397 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 398 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 399 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 400 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 401 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 402 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 403 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 404 |
+
"model.norm.weight": "model-00004-of-00004.safetensors"
|
| 405 |
}
|
| 406 |
}
|