Update README.md
Browse files
README.md
CHANGED
@@ -33,43 +33,30 @@ Trying to get better at medical Q & A
|
|
33 |
|
34 |
### Model Sources [optional]
|
35 |
|
36 |
-
<!-- Provide the basic links for the model. -->
|
37 |
|
38 |
-
- **Repository:** [
|
39 |
- **Paper [optional]:** [More Information Needed]
|
40 |
- **Demo [optional]:** [Tonic/MistralMed_Chat]
|
41 |
|
42 |
## Uses
|
43 |
|
44 |
-
|
45 |
|
46 |
### Direct Use
|
47 |
|
48 |
-
|
49 |
-
|
50 |
-
[More Information Needed]
|
51 |
|
52 |
### Downstream Use [optional]
|
53 |
|
54 |
-
|
55 |
-
|
56 |
-
[More Information Needed]
|
57 |
-
|
58 |
-
### Out-of-Scope Use
|
59 |
-
|
60 |
-
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
61 |
-
|
62 |
-
[More Information Needed]
|
63 |
-
|
64 |
-
## Bias, Risks, and Limitations
|
65 |
-
|
66 |
-
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
67 |
-
|
68 |
-
[More Information Needed]
|
69 |
|
70 |
### Recommendations
|
71 |
|
72 |
-
|
|
|
|
|
|
|
|
|
73 |
|
74 |
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
75 |
|
@@ -77,19 +64,49 @@ Users (both direct and downstream) should be made aware of the risks, biases and
|
|
77 |
|
78 |
Use the code below to get started with the model.
|
79 |
|
80 |
-
[
|
81 |
|
82 |
## Training Details
|
83 |
|
84 |
### Training Data
|
85 |
|
86 |
-
|
87 |
-
|
88 |
-
[More Information Needed]
|
89 |
|
90 |
### Training Procedure
|
91 |
|
92 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
93 |
|
94 |
#### Preprocessing [optional]
|
95 |
|
@@ -98,50 +115,29 @@ Use the code below to get started with the model.
|
|
98 |
|
99 |
#### Training Hyperparameters
|
100 |
|
101 |
-
- **Training regime:**
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
102 |
|
103 |
#### Speeds, Sizes, Times [optional]
|
104 |
|
105 |
-
|
106 |
-
|
107 |
-
[More Information Needed]
|
108 |
-
|
109 |
-
## Evaluation
|
110 |
-
|
111 |
-
<!-- This section describes the evaluation protocols and provides the results. -->
|
112 |
-
|
113 |
-
### Testing Data, Factors & Metrics
|
114 |
-
|
115 |
-
#### Testing Data
|
116 |
-
|
117 |
-
<!-- This should link to a Data Card if possible. -->
|
118 |
-
|
119 |
-
[More Information Needed]
|
120 |
-
|
121 |
-
#### Factors
|
122 |
-
|
123 |
-
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
124 |
-
|
125 |
-
[More Information Needed]
|
126 |
-
|
127 |
-
#### Metrics
|
128 |
-
|
129 |
-
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
130 |
-
|
131 |
-
[More Information Needed]
|
132 |
-
|
133 |
-
### Results
|
134 |
-
|
135 |
-
[More Information Needed]
|
136 |
-
|
137 |
-
#### Summary
|
138 |
-
|
139 |
-
|
140 |
-
|
141 |
-
## Model Examination [optional]
|
142 |
-
|
143 |
-
<!-- Relevant interpretability work for the model goes here -->
|
144 |
-
|
145 |
[More Information Needed]
|
146 |
|
147 |
## Environmental Impact
|
@@ -156,53 +152,180 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
156 |
- **Compute Region:** [More Information Needed]
|
157 |
- **Carbon Emitted:** [More Information Needed]
|
158 |
|
159 |
-
##
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
160 |
|
161 |
### Model Architecture and Objective
|
162 |
|
163 |
-
|
164 |
-
|
165 |
-
|
166 |
-
|
167 |
-
|
168 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
169 |
#### Hardware
|
170 |
|
171 |
-
|
172 |
-
|
173 |
-
#### Software
|
174 |
-
|
175 |
-
[More Information Needed]
|
176 |
-
|
177 |
-
## Citation [optional]
|
178 |
-
|
179 |
-
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
180 |
-
|
181 |
-
**BibTeX:**
|
182 |
-
|
183 |
-
[More Information Needed]
|
184 |
-
|
185 |
-
**APA:**
|
186 |
-
|
187 |
-
[More Information Needed]
|
188 |
-
|
189 |
-
## Glossary [optional]
|
190 |
-
|
191 |
-
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
192 |
-
|
193 |
-
[More Information Needed]
|
194 |
|
195 |
-
## More Information [optional]
|
196 |
|
197 |
-
[More Information Needed]
|
198 |
|
199 |
## Model Card Authors [optional]
|
200 |
|
201 |
-
[
|
202 |
|
203 |
## Model Card Contact
|
204 |
|
205 |
-
[
|
206 |
|
207 |
|
208 |
## Training procedure
|
|
|
33 |
|
34 |
### Model Sources [optional]
|
35 |
|
|
|
36 |
|
37 |
+
- **Repository:** [Tonic/mistralmed]
|
38 |
- **Paper [optional]:** [More Information Needed]
|
39 |
- **Demo [optional]:** [Tonic/MistralMed_Chat]
|
40 |
|
41 |
## Uses
|
42 |
|
43 |
+
This model can be used the same way you normally use mistral
|
44 |
|
45 |
### Direct Use
|
46 |
|
47 |
+
This model can do better in medical question and answer scenarios.
|
|
|
|
|
48 |
|
49 |
### Downstream Use [optional]
|
50 |
|
51 |
+
This model is intended to be further fine tuned.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
|
53 |
### Recommendations
|
54 |
|
55 |
+
- Do Not Use As Is
|
56 |
+
- Fine Tune This Model Further
|
57 |
+
- For Educational Purposes Only
|
58 |
+
- Benchmark your model usage
|
59 |
+
- Evaluate the model before use
|
60 |
|
61 |
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
62 |
|
|
|
64 |
|
65 |
Use the code below to get started with the model.
|
66 |
|
67 |
+
[Tonic/MistralMED_Chat](https://huggingface.co/Tonic/MistralMED_Chat)
|
68 |
|
69 |
## Training Details
|
70 |
|
71 |
### Training Data
|
72 |
|
73 |
+
[MedQuad](https://huggingface.co/datasets/keivalya/MedQuad-MedicalQnADataset/viewer/default/train)
|
|
|
|
|
74 |
|
75 |
### Training Procedure
|
76 |
|
77 |
+
Dataset({
|
78 |
+
features: ['qtype', 'Question', 'Answer'],
|
79 |
+
num_rows: 16407
|
80 |
+
})
|
81 |
+
|
82 |
+
[2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 12628, 264, 2718, 12271, 5122, 272, 14164, 5746, 9283, 302, 272, 2787, 12271, 390, 264, 2692, 908, 395, 9623, 304, 6836, 3069, 28723, 13, 3260, 908, 1023, 6685, 272, 2718, 1423, 24329, 304, 272, 908, 1580, 347, 624, 302, 272, 2296, 5936, 262, 674, 647, 464, 3134, 647, 464, 28721, 495, 28730, 410, 262, 296, 647, 464, 19928, 647, 464, 14876, 28730, 9122, 647, 464, 28713, 16939, 647, 464, 3134, 28730, 720, 11009, 352, 647, 464, 267, 1805, 416, 647, 464, 3134, 28730, 9122, 14303, 13, 1014, 9623, 1580, 347, 624, 302, 272, 2296, 28747, 5936, 861, 647, 464, 5128, 28730, 11023, 28730, 1408, 647, 464, 11023, 28730, 4395, 647, 464, 16239, 263, 647, 464, 274, 9312, 647, 464, 28599, 647, 464, 2383, 411, 647, 464, 7449, 28730, 4837, 8524, 647, 464, 3537, 28730, 13102, 7449, 647, 464, 10470, 28713, 647, 464, 13952, 28730, 266, 28730, 2453, 314, 647, 464, 3537, 28730, 8502, 28730, 11023, 647, 464, 3537, 28730, 7502, 28730, 11023, 647, 464, 4101, 3591, 1421, 13, 13, 27332, 15255, 12271, 28747, 13, 3195, 460, 272, 19724, 354, 393, 1082, 721, 402, 4475, 294, 689, 6519, 300, 3250, 17428, 325, 9162, 28755, 28731, 1550, 13, 13, 27332, 11736, 288, 9283, 28747, 13, 28741, 331, 19742, 1683, 288, 17428, 28725, 481, 358, 721, 282, 17428, 28725, 442, 1683, 20837, 636, 721, 282, 17428, 6948, 6556, 1837, 304, 27729, 5827, 2818, 356, 2425, 472, 28723, 23331, 28733, 21255, 314, 3076, 695, 10747, 28725, 1259, 390, 16779, 294, 8731, 17653, 28725, 993, 347, 4525, 916, 2948, 10139, 28723, 5800, 7193, 506, 4894, 369, 13147, 494, 361, 262, 28725, 264, 7876, 1307, 298, 3363, 2856, 799, 7692, 282, 18257, 28725, 349, 5645, 1835, 393, 15155, 28790, 297, 11781, 311, 28725, 736, 349, 708, 6740, 5566, 298, 1760, 871, 11935, 938, 354, 5827, 302, 393, 15155, 297, 10589, 28723, 13, 2]
|
83 |
+
|
84 |
+
MistralForCausalLM(
|
85 |
+
(model): MistralModel(
|
86 |
+
(embed_tokens): Embedding(32000, 4096)
|
87 |
+
(layers): ModuleList(
|
88 |
+
(0-31): 32 x MistralDecoderLayer(
|
89 |
+
(self_attn): MistralAttention(
|
90 |
+
(q_proj): Linear4bit(in_features=4096, out_features=4096, bias=False)
|
91 |
+
(k_proj): Linear4bit(in_features=4096, out_features=1024, bias=False)
|
92 |
+
(v_proj): Linear4bit(in_features=4096, out_features=1024, bias=False)
|
93 |
+
(o_proj): Linear4bit(in_features=4096, out_features=4096, bias=False)
|
94 |
+
(rotary_emb): MistralRotaryEmbedding()
|
95 |
+
)
|
96 |
+
(mlp): MistralMLP(
|
97 |
+
(gate_proj): Linear4bit(in_features=4096, out_features=14336, bias=False)
|
98 |
+
(up_proj): Linear4bit(in_features=4096, out_features=14336, bias=False)
|
99 |
+
(down_proj): Linear4bit(in_features=14336, out_features=4096, bias=False)
|
100 |
+
(act_fn): SiLUActivation()
|
101 |
+
)
|
102 |
+
(input_layernorm): MistralRMSNorm()
|
103 |
+
(post_attention_layernorm): MistralRMSNorm()
|
104 |
+
)
|
105 |
+
)
|
106 |
+
(norm): MistralRMSNorm()
|
107 |
+
)
|
108 |
+
(lm_head): Linear(in_features=4096, out_features=32000, bias=False)
|
109 |
+
)
|
110 |
|
111 |
#### Preprocessing [optional]
|
112 |
|
|
|
115 |
|
116 |
#### Training Hyperparameters
|
117 |
|
118 |
+
- **Training regime:**
|
119 |
+
config = LoraConfig(
|
120 |
+
r=8,
|
121 |
+
lora_alpha=16,
|
122 |
+
target_modules=[
|
123 |
+
"q_proj",
|
124 |
+
"k_proj",
|
125 |
+
"v_proj",
|
126 |
+
"o_proj",
|
127 |
+
"gate_proj",
|
128 |
+
"up_proj",
|
129 |
+
"down_proj",
|
130 |
+
"lm_head",
|
131 |
+
],
|
132 |
+
bias="none",
|
133 |
+
lora_dropout=0.05, # Conventional
|
134 |
+
task_type="CAUSAL_LM",
|
135 |
+
)
|
136 |
|
137 |
#### Speeds, Sizes, Times [optional]
|
138 |
|
139 |
+
trainable params: 21260288 || all params: 3773331456 || trainable%: 0.5634354746703705
|
140 |
+
TrainOutput(global_step=1000, training_loss=0.47226515007019043, metrics={'train_runtime': 3143.4141, 'train_samples_per_second': 2.545, 'train_steps_per_second': 0.318, 'total_flos': 1.75274075357184e+17, 'train_loss': 0.47226515007019043, 'epoch': 0.49})
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
141 |
[More Information Needed]
|
142 |
|
143 |
## Environmental Impact
|
|
|
152 |
- **Compute Region:** [More Information Needed]
|
153 |
- **Carbon Emitted:** [More Information Needed]
|
154 |
|
155 |
+
## Training Results
|
156 |
+
|
157 |
+
[1000/1000 52:20, Epoch 0/1]
|
158 |
+
Step Training Loss
|
159 |
+
50 0.474200
|
160 |
+
100 0.523300
|
161 |
+
150 0.484500
|
162 |
+
200 0.482800
|
163 |
+
250 0.498800
|
164 |
+
300 0.451800
|
165 |
+
350 0.491800
|
166 |
+
400 0.488000
|
167 |
+
450 0.472800
|
168 |
+
500 0.460400
|
169 |
+
550 0.464700
|
170 |
+
600 0.484800
|
171 |
+
650 0.474600
|
172 |
+
700 0.477900
|
173 |
+
750 0.445300
|
174 |
+
800 0.431300
|
175 |
+
850 0.461500
|
176 |
+
900 0.451200
|
177 |
+
950 0.470800
|
178 |
+
1000 0.454900
|
179 |
|
180 |
### Model Architecture and Objective
|
181 |
|
182 |
+
PeftModelForCausalLM(
|
183 |
+
(base_model): LoraModel(
|
184 |
+
(model): MistralForCausalLM(
|
185 |
+
(model): MistralModel(
|
186 |
+
(embed_tokens): Embedding(32000, 4096)
|
187 |
+
(layers): ModuleList(
|
188 |
+
(0-31): 32 x MistralDecoderLayer(
|
189 |
+
(self_attn): MistralAttention(
|
190 |
+
(q_proj): Linear4bit(
|
191 |
+
(lora_dropout): ModuleDict(
|
192 |
+
(default): Dropout(p=0.05, inplace=False)
|
193 |
+
)
|
194 |
+
(lora_A): ModuleDict(
|
195 |
+
(default): Linear(in_features=4096, out_features=8, bias=False)
|
196 |
+
)
|
197 |
+
(lora_B): ModuleDict(
|
198 |
+
(default): Linear(in_features=8, out_features=4096, bias=False)
|
199 |
+
)
|
200 |
+
(lora_embedding_A): ParameterDict()
|
201 |
+
(lora_embedding_B): ParameterDict()
|
202 |
+
(base_layer): Linear4bit(in_features=4096, out_features=4096, bias=False)
|
203 |
+
)
|
204 |
+
(k_proj): Linear4bit(
|
205 |
+
(lora_dropout): ModuleDict(
|
206 |
+
(default): Dropout(p=0.05, inplace=False)
|
207 |
+
)
|
208 |
+
(lora_A): ModuleDict(
|
209 |
+
(default): Linear(in_features=4096, out_features=8, bias=False)
|
210 |
+
)
|
211 |
+
(lora_B): ModuleDict(
|
212 |
+
(default): Linear(in_features=8, out_features=1024, bias=False)
|
213 |
+
)
|
214 |
+
(lora_embedding_A): ParameterDict()
|
215 |
+
(lora_embedding_B): ParameterDict()
|
216 |
+
(base_layer): Linear4bit(in_features=4096, out_features=1024, bias=False)
|
217 |
+
)
|
218 |
+
(v_proj): Linear4bit(
|
219 |
+
(lora_dropout): ModuleDict(
|
220 |
+
(default): Dropout(p=0.05, inplace=False)
|
221 |
+
)
|
222 |
+
(lora_A): ModuleDict(
|
223 |
+
(default): Linear(in_features=4096, out_features=8, bias=False)
|
224 |
+
)
|
225 |
+
(lora_B): ModuleDict(
|
226 |
+
(default): Linear(in_features=8, out_features=1024, bias=False)
|
227 |
+
)
|
228 |
+
(lora_embedding_A): ParameterDict()
|
229 |
+
(lora_embedding_B): ParameterDict()
|
230 |
+
(base_layer): Linear4bit(in_features=4096, out_features=1024, bias=False)
|
231 |
+
)
|
232 |
+
(o_proj): Linear4bit(
|
233 |
+
(lora_dropout): ModuleDict(
|
234 |
+
(default): Dropout(p=0.05, inplace=False)
|
235 |
+
)
|
236 |
+
(lora_A): ModuleDict(
|
237 |
+
(default): Linear(in_features=4096, out_features=8, bias=False)
|
238 |
+
)
|
239 |
+
(lora_B): ModuleDict(
|
240 |
+
(default): Linear(in_features=8, out_features=4096, bias=False)
|
241 |
+
)
|
242 |
+
(lora_embedding_A): ParameterDict()
|
243 |
+
(lora_embedding_B): ParameterDict()
|
244 |
+
(base_layer): Linear4bit(in_features=4096, out_features=4096, bias=False)
|
245 |
+
)
|
246 |
+
(rotary_emb): MistralRotaryEmbedding()
|
247 |
+
)
|
248 |
+
(mlp): MistralMLP(
|
249 |
+
(gate_proj): Linear4bit(
|
250 |
+
(lora_dropout): ModuleDict(
|
251 |
+
(default): Dropout(p=0.05, inplace=False)
|
252 |
+
)
|
253 |
+
(lora_A): ModuleDict(
|
254 |
+
(default): Linear(in_features=4096, out_features=8, bias=False)
|
255 |
+
)
|
256 |
+
(lora_B): ModuleDict(
|
257 |
+
(default): Linear(in_features=8, out_features=14336, bias=False)
|
258 |
+
)
|
259 |
+
(lora_embedding_A): ParameterDict()
|
260 |
+
(lora_embedding_B): ParameterDict()
|
261 |
+
(base_layer): Linear4bit(in_features=4096, out_features=14336, bias=False)
|
262 |
+
)
|
263 |
+
(up_proj): Linear4bit(
|
264 |
+
(lora_dropout): ModuleDict(
|
265 |
+
(default): Dropout(p=0.05, inplace=False)
|
266 |
+
)
|
267 |
+
(lora_A): ModuleDict(
|
268 |
+
(default): Linear(in_features=4096, out_features=8, bias=False)
|
269 |
+
)
|
270 |
+
(lora_B): ModuleDict(
|
271 |
+
(default): Linear(in_features=8, out_features=14336, bias=False)
|
272 |
+
)
|
273 |
+
(lora_embedding_A): ParameterDict()
|
274 |
+
(lora_embedding_B): ParameterDict()
|
275 |
+
(base_layer): Linear4bit(in_features=4096, out_features=14336, bias=False)
|
276 |
+
)
|
277 |
+
(down_proj): Linear4bit(
|
278 |
+
(lora_dropout): ModuleDict(
|
279 |
+
(default): Dropout(p=0.05, inplace=False)
|
280 |
+
)
|
281 |
+
(lora_A): ModuleDict(
|
282 |
+
(default): Linear(in_features=14336, out_features=8, bias=False)
|
283 |
+
)
|
284 |
+
(lora_B): ModuleDict(
|
285 |
+
(default): Linear(in_features=8, out_features=4096, bias=False)
|
286 |
+
)
|
287 |
+
(lora_embedding_A): ParameterDict()
|
288 |
+
(lora_embedding_B): ParameterDict()
|
289 |
+
(base_layer): Linear4bit(in_features=14336, out_features=4096, bias=False)
|
290 |
+
)
|
291 |
+
(act_fn): SiLUActivation()
|
292 |
+
)
|
293 |
+
(input_layernorm): MistralRMSNorm()
|
294 |
+
(post_attention_layernorm): MistralRMSNorm()
|
295 |
+
)
|
296 |
+
)
|
297 |
+
(norm): MistralRMSNorm()
|
298 |
+
)
|
299 |
+
(lm_head): Linear(
|
300 |
+
in_features=4096, out_features=32000, bias=False
|
301 |
+
(lora_dropout): ModuleDict(
|
302 |
+
(default): Dropout(p=0.05, inplace=False)
|
303 |
+
)
|
304 |
+
(lora_A): ModuleDict(
|
305 |
+
(default): Linear(in_features=4096, out_features=8, bias=False)
|
306 |
+
)
|
307 |
+
(lora_B): ModuleDict(
|
308 |
+
(default): Linear(in_features=8, out_features=32000, bias=False)
|
309 |
+
)
|
310 |
+
(lora_embedding_A): ParameterDict()
|
311 |
+
(lora_embedding_B): ParameterDict()
|
312 |
+
)
|
313 |
+
)
|
314 |
+
)
|
315 |
+
)
|
316 |
#### Hardware
|
317 |
|
318 |
+
A100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
319 |
|
|
|
320 |
|
|
|
321 |
|
322 |
## Model Card Authors [optional]
|
323 |
|
324 |
+
[Tonic](https://huggingface.co/Tonic)
|
325 |
|
326 |
## Model Card Contact
|
327 |
|
328 |
+
[Tonic](https://huggingface.co/Tonic)
|
329 |
|
330 |
|
331 |
## Training procedure
|