nintwentydo commited on
Commit
b41e100
1 Parent(s): 2e170fc

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -1,35 +1,3 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
  *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz 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
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  *.safetensors filter=lfs diff=lfs merge=lfs -text
2
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
3
+ tokenizer.model filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ - fr
5
+ - de
6
+ - es
7
+ - it
8
+ - pt
9
+ - zh
10
+ - ja
11
+ - ru
12
+ - ko
13
+ license: other
14
+ license_name: mrl
15
+ base_model: mistralai/Pixtral-Large-Instruct-2411
16
+ base_model_relation: quantized
17
+ inference: false
18
+ license_link: https://mistral.ai/licenses/MRL-0.1.md
19
+ library_name: transformers
20
+ pipeline_tag: image-text-to-text
21
+ ---
22
+
23
+ # Pixtral-Large-Instruct-2411 🧡 ExLlamaV2 3.0bpw Quant
24
+
25
+ 3.0bpw quant of [Pixtral-Large-Instruct](https://huggingface.co/nintwentydo/Pixtral-Large-Instruct-2411).
26
+
27
+ Vision inputs working on dev branch of [ExLlamaV2](https://github.com/turboderp/exllamav2/tree/dev).
28
+
29
+
30
+ ## Tokenizer And Prompt Template
31
+ Using conversion of v7m1 tokenizer with 32k vocab size.
32
+
33
+ Chat template in chat_template.json uses the v7 instruct template:
34
+
35
+ ```
36
+ <s>[SYSTEM_PROMPT] <system prompt>[/SYSTEM_PROMPT][INST] <user message>[/INST] <assistant response></s>[INST] <user message>[/INST]
37
+ ```
38
+
39
+ ## Available Sizes
40
+
41
+ | Repo | Bits | Head Bits | Size |
42
+ | ----------- | ------ | ------ | ------ |
43
+ | nintwentydo/Pixtral-Large-Instruct-2411-exl2-2.5bpw | 2.5 | 6.0 | TBC |
44
+ | [nintwentydo/Pixtral-Large-Instruct-2411-exl2-3.0bpw](https://huggingface.co/nintwentydo/Pixtral-Large-Instruct-2411-exl2-3.0bpw) | 3.0 | 6.0 | 46.42 GB |
45
+ | [nintwentydo/Pixtral-Large-Instruct-2411-exl2-4.0bpw](https://huggingface.co/nintwentydo/Pixtral-Large-Instruct-2411-exl2-4.0bpw) | 4.0 | 6.0 | 60.61GB |
46
+ | nintwentydo/Pixtral-Large-Instruct-2411-exl2-5.0bpw | 5.0 | 6.0 | TBC |
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{{- bos_token }} \n{%- for message in messages %} \n {%- if message['role'] == 'user' %} \n {{- '[INST]' + ' ' }} \n {%- if message['content'] is not string %} \n {%- for chunk in message['content'] %} \n {%- if chunk['type'] == 'text' %} \n {{- chunk['content'] }} \n {%- elif chunk['type'] == 'image' %} \n {{- '[IMG]' }} \n {%- else %} \n {{- raise_exception('Unrecognized content type!') }} \n {%- endif %} \n {%- endfor %} \n {%- else %} \n {{- message['content'] }} \n {%- endif %} \n {{- '[\/INST]' }} \n {%- if not loop.last and messages[loop.index]['role'] == 'user' %} \n {{- eos_token }} \n {%- endif %} \n {%- elif message['role'] == 'system' %} \n {{- '[SYSTEM_PROMPT] ' + message['content'] + '[\/SYSTEM_PROMPT]' }} \n {%- elif message['role'] == 'assistant' %} \n {{- ' ' + message['content'] + eos_token }} \n {%- else %} \n {{- raise_exception('Only user, system and assistant roles are supported!') }} \n {%- endif %} \n{%- endfor %}"
3
+ }
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlavaForConditionalGeneration"
4
+ ],
5
+ "ignore_index": -100,
6
+ "image_seq_length": 1,
7
+ "image_token_index": 10,
8
+ "model_type": "llava",
9
+ "multimodal_projector_bias": false,
10
+ "projector_hidden_act": "gelu",
11
+ "text_config": {
12
+ "hidden_size": 12288,
13
+ "intermediate_size": 28672,
14
+ "is_composition": true,
15
+ "max_position_embeddings": 131072,
16
+ "model_type": "mistral",
17
+ "norm_eps": 1e-05,
18
+ "rms_norm_eps": 1e-05,
19
+ "num_attention_heads": 96,
20
+ "num_hidden_layers": 88,
21
+ "num_key_value_heads": 8,
22
+ "rope_theta": 1000000000,
23
+ "sliding_window": null,
24
+ "vocab_size": 32768
25
+ },
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.47.0.dev0",
28
+ "vision_config": {
29
+ "head_dim": 88,
30
+ "num_attention_heads": 16,
31
+ "hidden_act": "silu",
32
+ "hidden_size": 1408,
33
+ "image_size": 1024,
34
+ "image_token_id": 10,
35
+ "intermediate_size": 6144,
36
+ "model_type": "pixtral",
37
+ "num_hidden_layers": 40,
38
+ "patch_size": 16,
39
+ "rope_theta": 10000
40
+ },
41
+ "vision_feature_layer": -1,
42
+ "vision_feature_select_strategy": "full",
43
+ "quantization_config": {
44
+ "quant_method": "exl2",
45
+ "version": "0.2.6",
46
+ "bits": 3,
47
+ "head_bits": 6,
48
+ "calibration": {
49
+ "rows": 115,
50
+ "length": 2048,
51
+ "dataset": "(default)"
52
+ }
53
+ }
54
+ }
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": "4.48.0.dev0"
6
+ }
measurement.json ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
output-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ce514e144677e5e490ae7395574e9ac55bfc6c1c72e71161d3c1c558ea08f0e
3
+ size 10694948492
output-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dadb8fd8f1e4fb712869dd965559a58f2b89da9f759b05fc4310ff83ed3136d
3
+ size 10675975442
output-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c39a6d58ffe34d456683b950d01dcb32d5e1d3ac2dcbc606807ee12f7e687b3
3
+ size 10724636898
output-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7aedcc899763aeca2e5d9c031a81eeb85288e149f8b5cade4805208a69dccd3
3
+ size 10732768956
output-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae8a9e377f460a3a6bc114edafd52c81d29ee7f7e687bbd581462fca7ef30910
3
+ size 7014876124
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "PixtralImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "patch_size": {
18
+ "height": 16,
19
+ "width": 16
20
+ },
21
+ "processor_class": "PixtralProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 1024
26
+ }
27
+ }
processor_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_break_token": "[IMG_BREAK]",
3
+ "image_end_token": "[IMG_END]",
4
+ "image_token": "[IMG]",
5
+ "patch_size": 16,
6
+ "processor_class": "PixtralProcessor"
7
+ }
special_tokens_map.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 sha256:1b968b8dc352f42192367337c78ccc61e1eaddc6d641a579372d4f20694beb7a
3
+ size 587562
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff