Quant for 8.0
Browse files- README.md +292 -38
- config.json +26 -0
- generation_config.json +6 -0
- model.safetensors.index.json +298 -0
- original_repo_url.txt +1 -0
- output.safetensors +3 -0
- special_tokens_map.json +35 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +49 -0
README.md
CHANGED
@@ -20,62 +20,316 @@ language:
|
|
20 |
- en
|
21 |
library_name: transformers
|
22 |
pipeline_tag: text-generation
|
23 |
-
quantized_by: bartowski
|
24 |
---
|
|
|
|
|
25 |
|
26 |
-
|
27 |
|
28 |
-
|
29 |
|
30 |
-
|
31 |
|
32 |
-
|
|
|
33 |
|
34 |
-
|
35 |
|
36 |
-
|
37 |
-
| ----- | ---- | ------- | ------ | ------ | ------ | ------------ |
|
38 |
-
| [8_0](https://huggingface.co/bartowski/AlphaMonarch-laser-exl2/tree/8_0) | 8.0 | 8.0 | 8.4 GB | 9.8 GB | 11.8 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
|
39 |
-
| [6_5](https://huggingface.co/bartowski/AlphaMonarch-laser-exl2/tree/6_5) | 6.5 | 8.0 | 7.2 GB | 8.6 GB | 10.6 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
|
40 |
-
| [5_0](https://huggingface.co/bartowski/AlphaMonarch-laser-exl2/tree/5_0) | 5.0 | 6.0 | 6.0 GB | 7.4 GB | 9.4 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
|
41 |
-
| [4_25](https://huggingface.co/bartowski/AlphaMonarch-laser-exl2/tree/4_25) | 4.25 | 6.0 | 5.3 GB | 6.7 GB | 8.7 GB | GPTQ equivalent bits per weight, slightly higher quality. |
|
42 |
-
| [3_5](https://huggingface.co/bartowski/AlphaMonarch-laser-exl2/tree/3_5) | 3.5 | 6.0 | 4.7 GB | 6.1 GB | 8.1 GB | Lower quality, only use if you have to. |
|
43 |
|
44 |
-
|
45 |
|
46 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
|
48 |
-
|
49 |
-
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/AlphaMonarch-laser-exl2 AlphaMonarch-laser-exl2-6_5
|
50 |
-
```
|
51 |
|
52 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
53 |
|
54 |
-
|
55 |
-
pip3 install huggingface-hub
|
56 |
-
```
|
57 |
|
58 |
-
|
|
|
|
|
|
|
|
|
59 |
|
60 |
-
|
61 |
-
mkdir AlphaMonarch-laser-exl2
|
62 |
-
huggingface-cli download bartowski/AlphaMonarch-laser-exl2 --local-dir AlphaMonarch-laser-exl2 --local-dir-use-symlinks False
|
63 |
-
```
|
64 |
|
65 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
|
67 |
-
|
68 |
|
69 |
-
|
70 |
-
|
71 |
-
|
72 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
73 |
|
74 |
-
Windows (which apparently doesn't like _ in folders sometimes?):
|
75 |
|
76 |
-
|
77 |
-
|
78 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
79 |
```
|
80 |
|
81 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
- en
|
21 |
library_name: transformers
|
22 |
pipeline_tag: text-generation
|
|
|
23 |
---
|
24 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
25 |
+
should probably proofread and complete it, then remove this comment. -->
|
26 |
|
27 |
+
# AlphaMonarch-laser
|
28 |
|
29 |
+
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64e380b2e12618b261fa6ba0/62S_ExHO6NKCM3NhPDrds.jpeg)
|
30 |
|
31 |
+
AlphaMonarch-laser is a DPO fine-tuned of [mlabonne/NeuralMonarch-7B](https://huggingface.co/mlabonne/NeuralMonarch-7B/) using the [argilla/OpenHermes2.5-dpo-binarized-alpha](https://huggingface.co/datasets/argilla/OpenHermes2.5-dpo-binarized-alpha) preference dataset but achieves better performance then [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B/) using LaserQLoRA. We have fine-tuned this model only on half of the projections, but have achieved better results as compared to the version released by Maximme Labonne. We have trained this model for 1080 steps.
|
32 |
|
33 |
+
AlphaMonarch-laser is ranking 1 on YALL - [Yet Another LLM Leaderboard](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard).
|
34 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/64e380b2e12618b261fa6ba0/Jgxw1FZRx7nNAdSh7nYt1.png)
|
35 |
|
36 |
+
## 🏆 Evaluation results
|
37 |
|
38 |
+
# Nous Benchmark
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
|
40 |
+
### AGIEVAL
|
41 |
|
42 |
+
| Task | Version | Metric | Value | StdErr |
|
43 |
+
|---------------------------------|---------|--------------|--------|--------|
|
44 |
+
| agieval_aqua_rat | 0 | acc | 28.35% | 2.83% |
|
45 |
+
| agieval_aqua_rat | 0 | acc_norm | 26.38% | 2.77% |
|
46 |
+
| agieval_logiqa_en | 0 | acc | 38.25% | 1.91% |
|
47 |
+
| agieval_logiqa_en | 0 | acc_norm | 38.10% | 1.90% |
|
48 |
+
| agieval_lsat_ar | 0 | acc | 23.91% | 2.82% |
|
49 |
+
| agieval_lsat_ar | 0 | acc_norm | 23.48% | 2.80% |
|
50 |
+
| agieval_lsat_lr | 0 | acc | 52.75% | 2.21% |
|
51 |
+
| agieval_lsat_lr | 0 | acc_norm | 53.92% | 2.21% |
|
52 |
+
| agieval_lsat_rc | 0 | acc | 66.91% | 2.87% |
|
53 |
+
| agieval_lsat_rc | 0 | acc_norm | 67.29% | 2.87% |
|
54 |
+
| agieval_sat_en | 0 | acc | 78.64% | 2.86% |
|
55 |
+
| agieval_sat_en | 0 | acc_norm | 78.64% | 2.86% |
|
56 |
+
| agieval_sat_en_without_passage | 0 | acc | 45.15% | 3.48% |
|
57 |
+
| agieval_sat_en_without_passage | 0 | acc_norm | 44.17% | 3.47% |
|
58 |
+
| agieval_sat_math | 0 | acc | 33.18% | 3.18% |
|
59 |
+
| agieval_sat_math | 0 | acc_norm | 31.36% | 3.14% |
|
60 |
+
Average: 28.41%
|
61 |
|
62 |
+
### GPT4ALL
|
|
|
|
|
63 |
|
64 |
+
| Task | Version | Metric | Value | StdErr |
|
65 |
+
|--------------|---------|----------|-------|--------|
|
66 |
+
| arc_challenge| 0 | acc | 66.30%| ± 1.38%|
|
67 |
+
| | | acc_norm | 68.26%| ± 1.36%|
|
68 |
+
| arc_easy | 0 | acc | 86.57%| ± 0.70%|
|
69 |
+
| | | acc_norm | 80.81%| ± 0.81%|
|
70 |
+
| boolq | 1 | acc | 87.16%| ± 0.59%|
|
71 |
+
| hellaswag | 0 | acc | 69.60%| ± 0.46%|
|
72 |
+
| | | acc_norm | 87.45%| ± 0.33%|
|
73 |
+
| openbookqa | 0 | acc | 39.20%| ± 2.19%|
|
74 |
+
| | | acc_norm | 49.60%| ± 2.24%|
|
75 |
+
| piqa | 0 | acc | 83.03%| ± 0.88%|
|
76 |
+
| | | acc_norm | 84.87%| ± 0.84%|
|
77 |
+
| winogrande | 0 | acc | 81.06%| ± 1.10%|
|
78 |
+
Average: 76.98%
|
79 |
|
80 |
+
### TRUTHFUL-QA
|
|
|
|
|
81 |
|
82 |
+
| Task | Version | Metric | Value | StdErr |
|
83 |
+
|---------------|---------|--------|-------|--------|
|
84 |
+
| truthfulqa_mc | 1 | mc1 | 63.04%| ± 1.69%|
|
85 |
+
| truthfulqa_mc | 1 | mc2 | 78.39%| ± 1.37%|
|
86 |
+
Average: 70.71%
|
87 |
|
88 |
+
### BIGBENCH
|
|
|
|
|
|
|
89 |
|
90 |
+
| Task | Version | Metric | Value | StdErr |
|
91 |
+
|------------------------------------------------|---------|-----------------------|-------|--------------------|
|
92 |
+
| bigbench_causal_judgement | 0 | multiple_choice_grade| 60.00%| ± 3.56% |
|
93 |
+
| bigbench_date_understanding | 0 | multiple_choice_grade| 62.06%| ± 2.53% |
|
94 |
+
| bigbench_disambiguation_qa | 0 | multiple_choice_grade| 54.26%| ± 3.11% |
|
95 |
+
| bigbench_geometric_shapes | 0 | multiple_choice_grade| 23.96%| ± 2.26% |
|
96 |
+
| | | exact_str_match | 0.00% | ± 0.00% |
|
97 |
+
| bigbench_logical_deduction_five_objects | 0 | multiple_choice_grade| 32.80%| ± 2.10% |
|
98 |
+
| bigbench_logical_deduction_seven_objects | 0 | multiple_choice_grade| 23.86%| ± 1.61% |
|
99 |
+
| bigbench_logical_deduction_three_objects | 0 | multiple_choice_grade| 59.33%| ± 2.84% |
|
100 |
+
| bigbench_movie_recommendation | 0 | multiple_choice_grade| 58.00%| ± 2.21% |
|
101 |
+
| bigbench_navigate | 0 | multiple_choice_grade| 56.00%| ± 1.57% |
|
102 |
+
| bigbench_reasoning_about_colored_objects | 0 | multiple_choice_grade| 69.20%| ± 1.03% |
|
103 |
+
| bigbench_ruin_names | 0 | multiple_choice_grade| 55.36%| ± 2.35% |
|
104 |
+
| bigbench_salient_translation_error_detection | 0 | multiple_choice_grade| 41.48%| ± 1.56% |
|
105 |
+
| bigbench_snarks | 0 | multiple_choice_grade| 73.48%| ± 3.29% |
|
106 |
+
| bigbench_sports_understanding | 0 | multiple_choice_grade| 76.06%| ± 1.36% |
|
107 |
+
| bigbench_temporal_sequences | 0 | multiple_choice_grade| 55.50%| ± 1.57% |
|
108 |
+
| bigbench_tracking_shuffled_objects_five_objects| 0 | multiple_choice_grade| 23.28%| ± 1.20% |
|
109 |
+
| bigbench_tracking_shuffled_objects_seven_objects| 0 | multiple_choice_grade| 19.37%| ± 0.94% |
|
110 |
+
| bigbench_tracking_shuffled_objects_three_objects| 0 | multiple_choice_grade| 59.33%| ± 2.84% |
|
111 |
+
Average: 55.37%
|
112 |
|
113 |
+
# Openllm Benchmark
|
114 |
|
115 |
+
| Task |Version| Metric |Value| |Stderr|
|
116 |
+
|-------------|------:|--------|----:|---|-----:|
|
117 |
+
|arc_challenge| 0|acc |70.12|± | 1.30|
|
118 |
+
| | |acc_norm|73.27|± | 1.29|
|
119 |
+
|hellaswag | 0|acc |71.80|± | 0.44|
|
120 |
+
| | |acc_norm|89.20|± | 0.30|
|
121 |
+
|gsm8k | 0|acc |66.77|± | 1.2 |
|
122 |
+
|winogrande | 0|acc |84.6 |± | 1.0 |
|
123 |
+
|
124 |
+
Average: 73.5%
|
125 |
+
|
126 |
+
### TruthfulQA
|
127 |
+
| Task |Version|Metric|Value| |Stderr|
|
128 |
+
|-------------|------:|------|----:|---|-----:|
|
129 |
+
|truthfulqa_mc| 1|mc1 |62.79|± | 1.69|
|
130 |
+
| | |mc2 |77.90|± | 1.37|
|
131 |
+
|
132 |
+
### Training hyperparameters
|
133 |
+
|
134 |
+
The following hyperparameters were used during training:
|
135 |
+
- learning_rate: 5e-07
|
136 |
+
- train_batch_size: 1
|
137 |
+
- eval_batch_size: 8
|
138 |
+
- seed: 42
|
139 |
+
- gradient_accumulation_steps: 8
|
140 |
+
- total_train_batch_size: 8
|
141 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
142 |
+
- lr_scheduler_type: cosine
|
143 |
+
- lr_scheduler_warmup_steps: 100
|
144 |
+
- training_steps: 1080
|
145 |
|
|
|
146 |
|
147 |
+
|
148 |
+
### 📝 Axolotl Configuration
|
149 |
+
|
150 |
+
```yaml
|
151 |
+
base_model: mlabonne/NeuralMonarch-7B
|
152 |
+
model_type: MistralForCausalLM
|
153 |
+
tokenizer_type: LlamaTokenizer
|
154 |
+
is_mistral_derived_model: true
|
155 |
+
load_in_8bit: false
|
156 |
+
load_in_4bit: true
|
157 |
+
strict: false
|
158 |
+
rl: dpo
|
159 |
+
chat_template: chatml
|
160 |
+
datasets:
|
161 |
+
- path: mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha
|
162 |
+
split: train
|
163 |
+
type: chatml.intel
|
164 |
+
dataset_prepared_path:
|
165 |
+
val_set_size: 0.01
|
166 |
+
output_dir: ./out
|
167 |
+
adapter: qlora
|
168 |
+
lora_model_dir:
|
169 |
+
sequence_len: 1800
|
170 |
+
sample_packing: false
|
171 |
+
pad_to_sequence_len: false
|
172 |
+
lora_r: 16
|
173 |
+
lora_alpha: 16
|
174 |
+
lora_dropout: 0.05
|
175 |
+
lora_target_linear: true
|
176 |
+
lora_fan_in_fan_out:
|
177 |
+
lora_target_modules:
|
178 |
+
- layers.1.self_attn.q_proj
|
179 |
+
- layers.0.self_attn.q_proj
|
180 |
+
- layers.15.self_attn.q_proj
|
181 |
+
- layers.12.self_attn.q_proj
|
182 |
+
- layers.11.self_attn.q_proj
|
183 |
+
- layers.14.self_attn.q_proj
|
184 |
+
- layers.9.self_attn.q_proj
|
185 |
+
- layers.16.self_attn.q_proj
|
186 |
+
- layers.30.self_attn.q_proj
|
187 |
+
- layers.18.self_attn.q_proj
|
188 |
+
- layers.13.self_attn.q_proj
|
189 |
+
- layers.10.self_attn.q_proj
|
190 |
+
- layers.7.self_attn.q_proj
|
191 |
+
- layers.8.self_attn.q_proj
|
192 |
+
- layers.4.self_attn.q_proj
|
193 |
+
- layers.19.self_attn.q_proj
|
194 |
+
- layers.27.self_attn.k_proj
|
195 |
+
- layers.24.self_attn.k_proj
|
196 |
+
- layers.25.self_attn.k_proj
|
197 |
+
- layers.22.self_attn.k_proj
|
198 |
+
- layers.26.self_attn.k_proj
|
199 |
+
- layers.29.self_attn.k_proj
|
200 |
+
- layers.23.self_attn.k_proj
|
201 |
+
- layers.28.self_attn.k_proj
|
202 |
+
- layers.21.self_attn.k_proj
|
203 |
+
- layers.31.self_attn.k_proj
|
204 |
+
- layers.30.self_attn.k_proj
|
205 |
+
- layers.20.self_attn.k_proj
|
206 |
+
- layers.5.self_attn.k_proj
|
207 |
+
- layers.19.self_attn.k_proj
|
208 |
+
- layers.17.self_attn.k_proj
|
209 |
+
- layers.18.self_attn.k_proj
|
210 |
+
- layers.19.self_attn.v_proj
|
211 |
+
- layers.24.self_attn.v_proj
|
212 |
+
- layers.18.self_attn.v_proj
|
213 |
+
- layers.5.self_attn.v_proj
|
214 |
+
- layers.3.self_attn.v_proj
|
215 |
+
- layers.16.self_attn.v_proj
|
216 |
+
- layers.23.self_attn.v_proj
|
217 |
+
- layers.27.self_attn.v_proj
|
218 |
+
- layers.25.self_attn.v_proj
|
219 |
+
- layers.26.self_attn.v_proj
|
220 |
+
- layers.20.self_attn.v_proj
|
221 |
+
- layers.6.self_attn.v_proj
|
222 |
+
- layers.15.self_attn.v_proj
|
223 |
+
- layers.17.self_attn.v_proj
|
224 |
+
- layers.29.self_attn.v_proj
|
225 |
+
- layers.22.self_attn.v_proj
|
226 |
+
- layers.12.self_attn.o_proj
|
227 |
+
- layers.9.self_attn.o_proj
|
228 |
+
- layers.14.self_attn.o_proj
|
229 |
+
- layers.0.self_attn.o_proj
|
230 |
+
- layers.6.self_attn.o_proj
|
231 |
+
- layers.8.self_attn.o_proj
|
232 |
+
- layers.10.self_attn.o_proj
|
233 |
+
- layers.11.self_attn.o_proj
|
234 |
+
- layers.13.self_attn.o_proj
|
235 |
+
- layers.24.self_attn.o_proj
|
236 |
+
- layers.7.self_attn.o_proj
|
237 |
+
- layers.15.self_attn.o_proj
|
238 |
+
- layers.5.self_attn.o_proj
|
239 |
+
- layers.17.self_attn.o_proj
|
240 |
+
- layers.25.self_attn.o_proj
|
241 |
+
- layers.4.self_attn.o_proj
|
242 |
+
- layers.31.mlp.gate_proj
|
243 |
+
- layers.30.mlp.gate_proj
|
244 |
+
- layers.4.mlp.gate_proj
|
245 |
+
- layers.3.mlp.gate_proj
|
246 |
+
- layers.29.mlp.gate_proj
|
247 |
+
- layers.28.mlp.gate_proj
|
248 |
+
- layers.6.mlp.gate_proj
|
249 |
+
- layers.27.mlp.gate_proj
|
250 |
+
- layers.5.mlp.gate_proj
|
251 |
+
- layers.26.mlp.gate_proj
|
252 |
+
- layers.25.mlp.gate_proj
|
253 |
+
- layers.7.mlp.gate_proj
|
254 |
+
- layers.2.mlp.gate_proj
|
255 |
+
- layers.24.mlp.gate_proj
|
256 |
+
- layers.23.mlp.gate_proj
|
257 |
+
- layers.10.mlp.gate_proj
|
258 |
+
- layers.6.mlp.up_proj
|
259 |
+
- layers.4.mlp.up_proj
|
260 |
+
- layers.5.mlp.up_proj
|
261 |
+
- layers.27.mlp.up_proj
|
262 |
+
- layers.25.mlp.up_proj
|
263 |
+
- layers.26.mlp.up_proj
|
264 |
+
- layers.17.mlp.up_proj
|
265 |
+
- layers.24.mlp.up_proj
|
266 |
+
- layers.7.mlp.up_proj
|
267 |
+
- layers.10.mlp.up_proj
|
268 |
+
- layers.3.mlp.up_proj
|
269 |
+
- layers.11.mlp.up_proj
|
270 |
+
- layers.23.mlp.up_proj
|
271 |
+
- layers.9.mlp.up_proj
|
272 |
+
- layers.14.mlp.up_proj
|
273 |
+
- layers.18.mlp.up_proj
|
274 |
+
- layers.19.mlp.down_proj
|
275 |
+
- layers.20.mlp.down_proj
|
276 |
+
- layers.18.mlp.down_proj
|
277 |
+
- layers.21.mlp.down_proj
|
278 |
+
- layers.29.mlp.down_proj
|
279 |
+
- layers.1.mlp.down_proj
|
280 |
+
- layers.22.mlp.down_proj
|
281 |
+
- layers.28.mlp.down_proj
|
282 |
+
- layers.23.mlp.down_proj
|
283 |
+
- layers.30.mlp.down_proj
|
284 |
+
- layers.17.mlp.down_proj
|
285 |
+
- layers.4.mlp.down_proj
|
286 |
+
- layers.2.mlp.down_proj
|
287 |
+
- layers.15.mlp.down_proj
|
288 |
+
- layers.5.mlp.down_proj
|
289 |
+
wandb_project: axolotl
|
290 |
+
wandb_entity:
|
291 |
+
wandb_watch:
|
292 |
+
wandb_name:
|
293 |
+
wandb_log_model:
|
294 |
+
gradient_accumulation_steps: 8
|
295 |
+
micro_batch_size: 1
|
296 |
+
num_epochs: 1
|
297 |
+
optimizer: paged_adamw_32bit
|
298 |
+
lr_scheduler: cosine
|
299 |
+
learning_rate: 5e-7
|
300 |
+
train_on_inputs: false
|
301 |
+
group_by_length: false
|
302 |
+
bf16: true
|
303 |
+
fp16: false
|
304 |
+
tf32: true
|
305 |
+
gradient_checkpointing: true
|
306 |
+
early_stopping_patience:
|
307 |
+
resume_from_checkpoint:
|
308 |
+
local_rank:
|
309 |
+
logging_steps: 1
|
310 |
+
xformers_attention:
|
311 |
+
flash_attention: true
|
312 |
+
warmup_steps: 100
|
313 |
+
evals_per_epoch: 1
|
314 |
+
eval_table_size:
|
315 |
+
eval_table_max_new_tokens: 128
|
316 |
+
save_steps: 1080
|
317 |
+
max_steps: 1080
|
318 |
+
debug:
|
319 |
+
deepspeed:
|
320 |
+
weight_decay: 0.0
|
321 |
+
fsdp:
|
322 |
+
fsdp_config:
|
323 |
+
special_tokens:
|
324 |
```
|
325 |
|
326 |
+
|
327 |
+
### Framework versions
|
328 |
+
|
329 |
+
- Transformers 4.38.0.dev0
|
330 |
+
- Pytorch 2.1.2+cu118
|
331 |
+
- Datasets 2.17.0
|
332 |
+
- Tokenizers 0.15.0
|
333 |
+
- axolotl: 0.4.0
|
334 |
+
|
335 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mlabonne/NeuralMonarch-7B",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 10000.0,
|
20 |
+
"sliding_window": 4096,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.38.0.dev0",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 32000
|
26 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.38.0.dev0"
|
6 |
+
}
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 14483464192
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
287 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
296 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
297 |
+
}
|
298 |
+
}
|
original_repo_url.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
https://huggingface.co/abideen/AlphaMonarch-laser
|
output.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d0e7491a3607c5499fa766f030c5e6419e3a4c4a6ce0da1b7f0e614beb1a098
|
3 |
+
size 7370262600
|
special_tokens_map.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"unk_token": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [
|
31 |
+
"<unk>",
|
32 |
+
"<s>",
|
33 |
+
"</s>"
|
34 |
+
],
|
35 |
+
"bos_token": "<s>",
|
36 |
+
"chat_template": "{% for message in messages %}{{bos_token + message['role'] + '\n' + message['content'] + eos_token + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ bos_token + 'assistant\n' }}{% endif %}",
|
37 |
+
"clean_up_tokenization_spaces": false,
|
38 |
+
"eos_token": "</s>",
|
39 |
+
"legacy": true,
|
40 |
+
"model_max_length": 8192,
|
41 |
+
"pad_token": "</s>",
|
42 |
+
"padding_side": "left",
|
43 |
+
"sp_model_kwargs": {},
|
44 |
+
"spaces_between_special_tokens": false,
|
45 |
+
"split_special_tokens": false,
|
46 |
+
"tokenizer_class": "LlamaTokenizer",
|
47 |
+
"unk_token": "<unk>",
|
48 |
+
"use_default_system_prompt": true
|
49 |
+
}
|