Hugging Face's logo

Siddharth63
/
LLM2vec-Qwen3-1.7-mntp

Safetensors
qwen3
Model card Files
xet
 Community
Siddharth63 commited on
Commit
2bb52ef
·
1 Parent(s): a2abc08

added

Browse files
Files changed (10) hide show
  1. .ipynb_checkpoints/config-checkpoint.json +60 -0
  2. .ipynb_checkpoints/llm2vec_config-checkpoint.json +6 -0
  3. README.md +0 -199
  4. config.json +2 -2
  5. generation_config.json +0 -6
  6. llm2vec_config.json +6 -0
  7. model-00002-of-00002.safetensors +0 -3
  8. model-00001-of-00002.safetensors → model.safetensors +2 -2
  9. model.safetensors.index.json +0 -318
  10. special_tokens_map.json +1 -7
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3BiModel"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 151643,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 6144,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention"
44
+ ],
45
+ "max_position_embeddings": 32768,
46
+ "max_window_layers": 28,
47
+ "model_type": "qwen3",
48
+ "num_attention_heads": 16,
49
+ "num_hidden_layers": 28,
50
+ "num_key_value_heads": 8,
51
+ "rms_norm_eps": 1e-06,
52
+ "rope_scaling": null,
53
+ "rope_theta": 1000000,
54
+ "sliding_window": null,
55
+ "tie_word_embeddings": true,
56
+ "transformers_version": "4.56.2",
57
+ "use_cache": true,
58
+ "use_sliding_window": false,
59
+ "vocab_size": 151936
60
+ }
.ipynb_checkpoints/llm2vec_config-checkpoint.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "pooling_mode": "mean",
3
+ "max_length": 512,
4
+ "doc_max_length": 400,
5
+ "skip_instruction": true
6
+ }
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]:** [More Information Needed]
34
- - **Demo [optional]:** [More Information Needed]
35
-
36
- ## Uses
37
-
38
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
-
40
- ### Direct Use
41
-
42
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
-
44
- [More Information Needed]
45
-
46
- ### Downstream Use [optional]
47
-
48
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
-
50
- [More Information Needed]
51
-
52
- ### Out-of-Scope Use
53
-
54
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
-
56
- [More Information Needed]
57
-
58
- ## Bias, Risks, and Limitations
59
-
60
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
-
62
- [More Information Needed]
63
-
64
- ### Recommendations
65
-
66
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
-
68
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
-
70
- ## How to Get Started with the Model
71
-
72
- Use the code below to get started with the model.
73
-
74
- [More Information Needed]
75
-
76
- ## Training Details
77
-
78
- ### Training Data
79
-
80
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
-
82
- [More Information Needed]
83
-
84
- ### Training Procedure
85
-
86
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
-
88
- #### Preprocessing [optional]
89
-
90
- [More Information Needed]
91
-
92
-
93
- #### Training Hyperparameters
94
-
95
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
-
97
- #### Speeds, Sizes, Times [optional]
98
-
99
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
-
101
- [More Information Needed]
102
-
103
- ## Evaluation
104
-
105
- <!-- This section describes the evaluation protocols and provides the results. -->
106
-
107
- ### Testing Data, Factors & Metrics
108
-
109
- #### Testing Data
110
-
111
- <!-- This should link to a Dataset Card if possible. -->
112
-
113
- [More Information Needed]
114
-
115
- #### Factors
116
-
117
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
-
119
- [More Information Needed]
120
-
121
- #### Metrics
122
-
123
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
-
125
- [More Information Needed]
126
-
127
- ### Results
128
-
129
- [More Information Needed]
130
-
131
- #### Summary
132
-
133
-
134
-
135
- ## Model Examination [optional]
136
-
137
- <!-- Relevant interpretability work for the model goes here -->
138
-
139
- [More Information Needed]
140
-
141
- ## Environmental Impact
142
-
143
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
-
145
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
-
147
- - **Hardware Type:** [More Information Needed]
148
- - **Hours used:** [More Information Needed]
149
- - **Cloud Provider:** [More Information Needed]
150
- - **Compute Region:** [More Information Needed]
151
- - **Carbon Emitted:** [More Information Needed]
152
-
153
- ## Technical Specifications [optional]
154
-
155
- ### Model Architecture and Objective
156
-
157
- [More Information Needed]
158
-
159
- ### Compute Infrastructure
160
-
161
- [More Information Needed]
162
-
163
- #### Hardware
164
-
165
- [More Information Needed]
166
-
167
- #### Software
168
-
169
- [More Information Needed]
170
-
171
- ## Citation [optional]
172
-
173
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
-
175
- **BibTeX:**
176
-
177
- [More Information Needed]
178
-
179
- **APA:**
180
-
181
- [More Information Needed]
182
-
183
- ## Glossary [optional]
184
-
185
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
-
187
- [More Information Needed]
188
-
189
- ## More Information [optional]
190
-
191
- [More Information Needed]
192
-
193
- ## Model Card Authors [optional]
194
-
195
- [More Information Needed]
196
-
197
- ## Model Card Contact
198
-
199
- [More Information Needed]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
  "architectures": [
3
- "Qwen3ForCausalLM"
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 151643,
8
- "dtype": "float32",
9
  "eos_token_id": 151643,
10
  "head_dim": 128,
11
  "hidden_act": "silu",
 
1
  {
2
  "architectures": [
3
+ "Qwen3BiModel"
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 151643,
8
+ "dtype": "bfloat16",
9
  "eos_token_id": 151643,
10
  "head_dim": 128,
11
  "hidden_act": "silu",
generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "bos_token_id": 151643,
3
- "eos_token_id": 151643,
4
- "max_new_tokens": 2048,
5
- "transformers_version": "4.56.2"
6
- }
 
 
 
 
 
 
 
llm2vec_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "pooling_mode": "mean",
3
+ "max_length": 512,
4
+ "doc_max_length": 400,
5
+ "skip_instruction": true
6
+ }
model-00002-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:46620b301118d35a0c709c24b706b287c68ea152f4c19d4b8f8015dbe16e6bd2
3
- size 1912795688
 
 
 
 
model-00001-of-00002.safetensors → model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb6a6d0ba9c587978631bd2bcadd3fdffc28b5d1dd36deb3673178b5a5bfebc7
3
- size 4969539560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7379b98e9177656848a99133d4a3a10d81d40b8957c0f3527ee2b811fd624534
3
+ size 3441183752
model.safetensors.index.json DELETED
@@ -1,318 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_parameters": 1720574976,
4
- "total_size": 6882299904
5
- },
6
- "weight_map": {
7
- "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
- "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
14
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
- "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
17
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
18
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
19
- "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
22
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
23
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
- "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
25
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
26
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
27
- "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
28
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
29
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
30
- "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
31
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
32
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
33
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
34
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
35
- "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
36
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
37
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
38
- "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
39
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
40
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
41
- "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
42
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
43
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
44
- "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
45
- "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
46
- "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
47
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
48
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
49
- "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
50
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
- "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
- "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
- "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
- "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
- "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
- "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
58
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
- "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
61
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
62
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
63
- "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
- "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
65
- "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
66
- "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
67
- "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
68
- "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
69
- "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
70
- "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
71
- "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
72
- "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
73
- "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
74
- "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
75
- "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
76
- "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
77
- "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
78
- "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
79
- "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
80
- "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
81
- "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
82
- "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
83
- "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
84
- "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
85
- "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
86
- "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
87
- "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
88
- "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
89
- "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
90
- "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
91
- "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
92
- "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
93
- "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
94
- "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
95
- "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
96
- "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
97
- "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
98
- "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
99
- "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
100
- "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
101
- "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
102
- "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
- "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
- "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
105
- "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
- "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
- "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
- "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
- "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
- "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
- "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
- "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
113
- "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
114
- "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
115
- "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
116
- "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
117
- "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
118
- "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
119
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
120
- "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
121
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
122
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
123
- "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
124
- "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
125
- "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
126
- "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
127
- "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
128
- "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
129
- "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
130
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
131
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
132
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
133
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
134
- "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
135
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
136
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
137
- "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
138
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
139
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
140
- "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
141
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
142
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
143
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
144
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
145
- "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
146
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
148
- "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
149
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
- "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
154
- "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
155
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
- "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
157
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
158
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
159
- "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
160
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
161
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
162
- "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
163
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
164
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
165
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
166
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
167
- "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
168
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
169
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
170
- "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
171
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
172
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
173
- "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
174
- "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
175
- "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
176
- "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
177
- "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
178
- "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
179
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
180
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
181
- "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
182
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
183
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
184
- "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
185
- "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
186
- "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
187
- "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
188
- "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
189
- "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
190
- "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
191
- "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
192
- "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
193
- "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
194
- "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
195
- "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
196
- "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
197
- "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
198
- "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
199
- "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
200
- "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
201
- "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
202
- "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
203
- "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
204
- "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
205
- "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
206
- "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
207
- "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
208
- "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
209
- "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
210
- "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
211
- "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
212
- "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
213
- "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
214
- "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
215
- "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
216
- "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
217
- "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
218
- "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
219
- "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
220
- "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
221
- "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
222
- "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
223
- "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
224
- "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
225
- "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
226
- "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
227
- "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
228
- "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
229
- "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
230
- "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
231
- "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
232
- "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
233
- "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
234
- "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
235
- "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
236
- "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
237
- "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
238
- "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
239
- "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
240
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
241
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
242
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
243
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
244
- "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
245
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
246
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
247
- "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
248
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
249
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
250
- "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
251
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
252
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
253
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
254
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
255
- "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
256
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
258
- "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
259
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
260
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
261
- "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
262
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
263
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
264
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
265
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
266
- "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
267
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
268
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
269
- "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
270
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
271
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
272
- "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
273
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
274
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
275
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
276
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
277
- "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
278
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
279
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
280
- "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
281
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
282
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
283
- "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
284
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
285
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
286
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
287
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
288
- "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
289
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
290
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
291
- "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
292
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
293
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
294
- "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
295
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
296
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
297
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
298
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
299
- "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
300
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
301
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
302
- "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
303
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
304
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
305
- "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
306
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
307
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
308
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
309
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
310
- "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
311
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
312
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
313
- "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
314
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
315
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
316
- "model.norm.weight": "model-00002-of-00002.safetensors"
317
- }
318
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
special_tokens_map.json CHANGED
@@ -21,11 +21,5 @@
21
  "rstrip": false,
22
  "single_word": false
23
  },
24
- "pad_token": {
25
- "content": "<|endoftext|>",
26
- "lstrip": false,
27
- "normalized": false,
28
- "rstrip": false,
29
- "single_word": false
30
- }
31
  }
 
21
  "rstrip": false,
22
  "single_word": false
23
  },
24
+ "pad_token": "<|endoftext|>"
 
 
 
 
 
 
25
  }