Quant for 6.5
Browse files- .gitattributes +1 -0
- README.md +130 -35
- config.json +28 -0
- generation_config.json +7 -0
- model.safetensors.index.json +261 -0
- original_repo_url.txt +1 -0
- output-00001-of-00002.safetensors +3 -0
- output-00002-of-00002.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +49 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -3,69 +3,164 @@ dataset: Thermostatic/flowers
|
|
3 |
license: other
|
4 |
license_name: gemma-terms-of-use
|
5 |
license_link: https://ai.google.dev/gemma/terms
|
6 |
-
quantized_by: bartowski
|
7 |
-
pipeline_tag: text-generation
|
8 |
---
|
9 |
|
10 |
-
|
11 |
|
12 |
-
|
13 |
|
14 |
-
|
15 |
|
16 |
-
|
|
|
17 |
|
18 |
-
|
19 |
|
20 |
-
|
21 |
|
22 |
-
|
23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
|
25 |
-
|
26 |
|
27 |
-
|
28 |
|
29 |
-
|
|
|
30 |
|
31 |
-
|
|
|
32 |
|
33 |
-
|
|
|
34 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
|
36 |
-
|
37 |
|
38 |
-
|
|
|
|
|
39 |
|
40 |
-
|
41 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
```
|
43 |
|
44 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
|
46 |
-
|
47 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
```
|
49 |
|
50 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
|
52 |
-
|
53 |
-
|
54 |
-
|
|
|
|
|
|
|
|
|
|
|
55 |
```
|
56 |
|
57 |
-
To download from a different branch, add the `--revision` parameter:
|
58 |
|
59 |
-
|
|
|
|
|
|
|
|
|
60 |
|
61 |
-
```
|
62 |
-
|
63 |
-
|
|
|
|
|
|
|
64 |
```
|
65 |
|
66 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
|
68 |
-
|
69 |
-
mkdir gemma-orchid-7b-dpo-exl2-6.5
|
70 |
-
huggingface-cli download bartowski/gemma-orchid-7b-dpo-exl2 --revision 6_5 --local-dir gemma-orchid-7b-dpo-exl2-6.5 --local-dir-use-symlinks False
|
71 |
-
```
|
|
|
3 |
license: other
|
4 |
license_name: gemma-terms-of-use
|
5 |
license_link: https://ai.google.dev/gemma/terms
|
|
|
|
|
6 |
---
|
7 |
|
8 |
+
# Gemma Orchid 7b
|
9 |
|
10 |
+
<div align="center">
|
11 |
|
12 |
+
![image/webp](https://cdn-uploads.huggingface.co/production/uploads/6455cc8d679315e4ef16fbec/7pqiroePJW0WWm6JxwBoO.webp)
|
13 |
|
14 |
+
[<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)
|
15 |
+
</div>
|
16 |
|
17 |
+
This model is the second checkpoint of a future project. Its capable of function calling as well as having a strong base in communicational skills.
|
18 |
|
19 |
+
This model has been finetuned on roughly 80k samples so far.
|
20 |
|
21 |
+
# Training
|
22 |
|
23 |
+
+ Time to complete: ~20 hours
|
24 |
+
+ Datasets: Thermostatic/flowers, Intel/orca_dpo_pairs, jondurbin/truthy-dpo-v0.1, glaiveai/glaive_function_calling_v2
|
25 |
+
+ Cost: ~$20 in H100 hours
|
26 |
+
+ Evaluation loss: 0.69
|
27 |
+
+ Method: LoRa
|
28 |
+
+ Prompt Format: ChatML
|
29 |
|
30 |
+
Thermostatic/flowers is a blend of open source model generations formatted in ShareGPT. It also includes all of capybara.
|
31 |
|
32 |
+
#### Running the model on a CPU
|
33 |
|
34 |
+
```python
|
35 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
36 |
|
37 |
+
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
|
38 |
+
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b")
|
39 |
|
40 |
+
input_text = "Write me a poem about Machine Learning."
|
41 |
+
input_ids = tokenizer(input_text, return_tensors="pt")
|
42 |
|
43 |
+
outputs = model.generate(**input_ids)
|
44 |
+
print(tokenizer.decode(outputs[0]))
|
45 |
+
```
|
46 |
+
|
47 |
+
|
48 |
+
#### Running the model on a single / multi GPU
|
49 |
+
|
50 |
+
|
51 |
+
```python
|
52 |
+
# pip install accelerate
|
53 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
54 |
+
|
55 |
+
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
|
56 |
+
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", device_map="auto")
|
57 |
+
|
58 |
+
input_text = "Write me a poem about Machine Learning."
|
59 |
+
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
|
60 |
+
|
61 |
+
outputs = model.generate(**input_ids)
|
62 |
+
print(tokenizer.decode(outputs[0]))
|
63 |
+
```
|
64 |
+
|
65 |
+
|
66 |
+
#### Running the model on a GPU using different precisions
|
67 |
+
|
68 |
+
* _Using `torch.float16`_
|
69 |
+
|
70 |
+
```python
|
71 |
+
# pip install accelerate
|
72 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
73 |
+
|
74 |
+
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
|
75 |
+
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", device_map="auto", torch_dtype=torch.float16)
|
76 |
+
|
77 |
+
input_text = "Write me a poem about Machine Learning."
|
78 |
+
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
|
79 |
+
|
80 |
+
outputs = model.generate(**input_ids)
|
81 |
+
print(tokenizer.decode(outputs[0]))
|
82 |
+
```
|
83 |
|
84 |
+
* _Using `torch.bfloat16`_
|
85 |
|
86 |
+
```python
|
87 |
+
# pip install accelerate
|
88 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
89 |
|
90 |
+
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
|
91 |
+
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", device_map="auto", torch_dtype=torch.bfloat16)
|
92 |
+
|
93 |
+
input_text = "Write me a poem about Machine Learning."
|
94 |
+
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
|
95 |
+
|
96 |
+
outputs = model.generate(**input_ids)
|
97 |
+
print(tokenizer.decode(outputs[0]))
|
98 |
```
|
99 |
|
100 |
+
#### Quantized Versions through `bitsandbytes`
|
101 |
+
|
102 |
+
* _Using 8-bit precision (int8)_
|
103 |
+
|
104 |
+
```python
|
105 |
+
# pip install bitsandbytes accelerate
|
106 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
|
107 |
+
|
108 |
+
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
|
109 |
|
110 |
+
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
|
111 |
+
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", quantization_config=quantization_config)
|
112 |
+
|
113 |
+
input_text = "Write me a poem about Machine Learning."
|
114 |
+
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
|
115 |
+
|
116 |
+
outputs = model.generate(**input_ids)
|
117 |
+
print(tokenizer.decode(outputs[0]))
|
118 |
```
|
119 |
|
120 |
+
* _Using 4-bit precision_
|
121 |
+
|
122 |
+
```python
|
123 |
+
# pip install bitsandbytes accelerate
|
124 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
|
125 |
+
|
126 |
+
quantization_config = BitsAndBytesConfig(load_in_4bit=True)
|
127 |
|
128 |
+
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
|
129 |
+
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b", quantization_config=quantization_config)
|
130 |
+
|
131 |
+
input_text = "Write me a poem about Machine Learning."
|
132 |
+
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
|
133 |
+
|
134 |
+
outputs = model.generate(**input_ids)
|
135 |
+
print(tokenizer.decode(outputs[0]))
|
136 |
```
|
137 |
|
|
|
138 |
|
139 |
+
#### Other optimizations
|
140 |
+
|
141 |
+
* _Flash Attention 2_
|
142 |
+
|
143 |
+
First make sure to install `flash-attn` in your environment `pip install flash-attn`
|
144 |
|
145 |
+
```diff
|
146 |
+
model = AutoModelForCausalLM.from_pretrained(
|
147 |
+
model_id,
|
148 |
+
torch_dtype=torch.float16,
|
149 |
+
+ attn_implementation="flash_attention_2"
|
150 |
+
).to(0)
|
151 |
```
|
152 |
|
153 |
+
### Inputs and outputs
|
154 |
+
|
155 |
+
* **Input:** Text string, such as a question, a prompt, or a document to be
|
156 |
+
summarized.
|
157 |
+
* **Output:** Generated English-language text in response to the input, such
|
158 |
+
as an answer to a question, or a summary of a document.
|
159 |
+
|
160 |
+
## Evaluations
|
161 |
+
|
162 |
+
In progress
|
163 |
+
|
164 |
+
## GGUF + iMatrix
|
165 |
|
166 |
+
In progress
|
|
|
|
|
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "macadeliccc/gemma-orchid-7b",
|
3 |
+
"architectures": [
|
4 |
+
"GemmaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 2,
|
9 |
+
"eos_token_id": 1,
|
10 |
+
"head_dim": 256,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_size": 3072,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 24576,
|
15 |
+
"max_position_embeddings": 8192,
|
16 |
+
"model_type": "gemma",
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 28,
|
19 |
+
"num_key_value_heads": 16,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"rms_norm_eps": 1e-06,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 10000.0,
|
24 |
+
"torch_dtype": "float16",
|
25 |
+
"transformers_version": "4.38.1",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 256000
|
28 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.38.1"
|
7 |
+
}
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,261 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 17075361792
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
7 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
8 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
9 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
10 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
11 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
12 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
13 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
14 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
15 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
16 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
17 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
18 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
19 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
20 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
21 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
22 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
23 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
24 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
25 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
26 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
27 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
28 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
29 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
30 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
31 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
32 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
33 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
34 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
35 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
36 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
37 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
38 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
39 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
40 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
41 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
42 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
43 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
44 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
45 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
46 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
47 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
48 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
49 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
50 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
51 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
52 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
53 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
54 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
55 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
56 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
57 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
58 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
59 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
60 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
61 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
62 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
63 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
64 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
65 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
66 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
67 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
68 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
69 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
70 |
+
"model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
71 |
+
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
72 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
73 |
+
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
74 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
75 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
76 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
77 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
78 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
79 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
80 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
81 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
82 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
83 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
84 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
85 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
86 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
87 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
88 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
89 |
+
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
90 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
91 |
+
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
92 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
93 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
94 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
95 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
96 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
97 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
98 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
99 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
100 |
+
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
101 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
102 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
103 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
104 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
105 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
106 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
107 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
108 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
109 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
110 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
111 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
112 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
113 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
114 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
115 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
116 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
117 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
118 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
119 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
120 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
121 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
122 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
123 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
124 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
125 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
126 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
127 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
128 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
129 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
130 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
131 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
132 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
133 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
134 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
135 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
136 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
137 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
138 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
139 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
140 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
141 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
142 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
143 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
144 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
145 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
146 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
147 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
148 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
149 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
150 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
151 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
152 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
153 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
154 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
155 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
156 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
157 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
158 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
159 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
160 |
+
"model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
161 |
+
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
162 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
163 |
+
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
164 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
165 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
166 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
167 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
168 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
169 |
+
"model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
170 |
+
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
171 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
172 |
+
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
173 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
174 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
175 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
176 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
177 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
178 |
+
"model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
179 |
+
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
180 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
181 |
+
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
182 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
183 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
184 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
185 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
186 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
187 |
+
"model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
188 |
+
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
189 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
190 |
+
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
191 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
192 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
193 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
194 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
195 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
196 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
197 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
198 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
199 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
200 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
201 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
202 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
203 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
204 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
205 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
206 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
207 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
208 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
209 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
210 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
211 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
212 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
213 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
214 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
215 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
216 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
217 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
218 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
219 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
220 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
221 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
222 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
223 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
224 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
225 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
226 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
227 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
228 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
229 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
230 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
231 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
232 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
233 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
234 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
235 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
236 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
237 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
238 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
239 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
240 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
241 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
242 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
243 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
244 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
245 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
246 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
247 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
248 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
249 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
250 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
251 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
252 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
253 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
254 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
255 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
256 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
257 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
258 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
259 |
+
"model.norm.weight": "model-00004-of-00004.safetensors"
|
260 |
+
}
|
261 |
+
}
|
original_repo_url.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
https://huggingface.co/macadeliccc/gemma-orchid-7b-dpo
|
output-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8748231228722a35fa4efc3a537eaf2cfb03e8d0802e713eb38fa16052410bd5
|
3 |
+
size 7868351240
|
output-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e90eb4de356ecbee20e218595dfb085dcd68e9072f7729af9c54583473dfbdf
|
3 |
+
size 786432096
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<bos>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<eos>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
|
3 |
+
size 17477553
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
3 |
+
size 4241003
|
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": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<bos>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"bos_token": "<bos>",
|
39 |
+
"clean_up_tokenization_spaces": false,
|
40 |
+
"eos_token": "<eos>",
|
41 |
+
"legacy": null,
|
42 |
+
"model_max_length": 1000000000000000019884624838656,
|
43 |
+
"pad_token": "<pad>",
|
44 |
+
"sp_model_kwargs": {},
|
45 |
+
"spaces_between_special_tokens": false,
|
46 |
+
"tokenizer_class": "GemmaTokenizer",
|
47 |
+
"unk_token": "<unk>",
|
48 |
+
"use_default_system_prompt": false
|
49 |
+
}
|