Instructions to use Jeethu/North-Micro-Vision-Instruct-PARO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jeethu/North-Micro-Vision-Instruct-PARO with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="Jeethu/North-Micro-Vision-Instruct-PARO")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Jeethu/North-Micro-Vision-Instruct-PARO")
model = AutoModelForMultimodalLM.from_pretrained("Jeethu/North-Micro-Vision-Instruct-PARO", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jeethu/North-Micro-Vision-Instruct-PARO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jeethu/North-Micro-Vision-Instruct-PARO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jeethu/North-Micro-Vision-Instruct-PARO",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Jeethu/North-Micro-Vision-Instruct-PARO

SGLang

How to use Jeethu/North-Micro-Vision-Instruct-PARO with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Jeethu/North-Micro-Vision-Instruct-PARO" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jeethu/North-Micro-Vision-Instruct-PARO",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Jeethu/North-Micro-Vision-Instruct-PARO" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jeethu/North-Micro-Vision-Instruct-PARO",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use Jeethu/North-Micro-Vision-Instruct-PARO with Docker Model Runner:
```
docker model run hf.co/Jeethu/North-Micro-Vision-Instruct-PARO
```

Jeethu commited on 9 days ago

Commit

5082a36

verified ·

1 Parent(s): 1d91e31

Upload folder using huggingface_hub

Browse files

Files changed (11) hide show

.gitattributes +1 -0
README.md +70 -0
chat_template.jinja +1 -0
config.json +164 -0
generation_config.json +12 -0
model.safetensors +3 -0
preprocessor_config.json +37 -0
special_tokens_map.json +37 -0
tokenizer.json +3 -0
tokenizer_config.json +340 -0
video_preprocessor_config.json +21 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,70 @@

+---
+library_name: transformers
+license: apache-2.0
+pipeline_tag: image-text-to-text
+language:
+  - en
+  - de
+  - fr
+  - es
+  - it
+  - pt
+  - hi
+  - ja
+  - ko
+  - zh
+  - ar
+tags:
+  - vision
+  - multimodal
+  - conversational
+  - multilingual
+  - native-resolution
+base_model:
+  - CohereLabs/North-Micro-Vision-Instruct
+base_model_relation: quantized
+---
+# Jeethu/North-Micro-Vision-Instruct
+**Pairwise Rotation Quantization for Efficient Reasoning LLM Inference**
+<p>
+  <a href="https://arxiv.org/abs/2511.10645"><img src="https://img.shields.io/badge/arXiv-2511.10645-b31b1b.svg" alt="Paper"></a>
+  <a href="https://paroquant.z-lab.ai"><img src="https://img.shields.io/badge/Blog-ParoQuant-blue" alt="Blog"></a>
+  <a href="https://huggingface.co/collections/z-lab/paroquant"><img src="https://img.shields.io/badge/%F0%9F%A4%97-Models-yellow" alt="Models"></a>
+  <a href="https://pypi.org/project/paroquant/"><img src="https://img.shields.io/pypi/v/paroquant" alt="PyPI"></a>
+</p>
+ParoQuant is the state-of-the-art INT4 quantization for LLMs. It closes the accuracy gap with FP16 while running at near-AWQ speed. Supports NVIDIA GPUs (vLLM, Transformers) and Apple Silicon (MLX). For more information, see https://github.com/z-lab/paroquant.
+Jeethu/North-Micro-Vision-Instruct is a 4-bit [CohereLabs/North-Micro-Vision-Instruct](https://huggingface.co/CohereLabs/North-Micro-Vision-Instruct) quantized with ParoQuant.
+## Evaluation
+The following evaluations were run on 2026-08-14 with deterministic greedy decoding. The source checkpoint was evaluated in its native BF16 dtype. This ParoQuant checkpoint uses INT4 language projections (group size 128, `krot=8`) with FP16 retained tensors, including the vision encoder. For context, the published [MLX affine 4-bit checkpoint](https://huggingface.co/mlx-community/North-Micro-Vision-Instruct-4bit) uses group size 64 with BF16 retained tensors.
+### Vision
+| Benchmark | Samples | Source BF16 | ParoQuant INT4 / FP16 | MLX affine 4-bit / BF16 |
+| --- | ---: | ---: | ---: | ---: |
+| [ChartQA](https://huggingface.co/datasets/lmms-lab/ChartQA) relaxed accuracy | 100 | 81.00% | 81.00% | 81.00% |
+| [MMStar](https://huggingface.co/datasets/Lin-Chen/MMStar) accuracy | 1,500 | 50.53% | 50.33% | 51.07% |
+ChartQA uses a fixed seed-0 stratified sample of 50 `human_test` and 50 `augmented_test` examples. Scoring follows the VLMEvalKit relaxed rule: case-insensitive exact text matching or a 5% relative tolerance for numeric answers. MMStar uses the complete validation split and extracts the selected option from deterministic generations.
+Against source BF16, ParoQuant changes ChartQA by 0.00 percentage points (paired bootstrap 95% CI: -3.00 to +3.00) and MMStar by -0.20 points (95% CI: -1.80 to +1.40). A targeted multi-image color-ordering, synthetic OCR, and object-counting smoke suite was also passed exactly by source BF16 and ParoQuant. MLX was semantically correct on all three cases and exact on two; its color response was verbose.
+### Text
+| Benchmark | Samples / tokens | Source BF16 | ParoQuant INT4 / FP16 | MLX affine 4-bit / BF16 |
+| --- | ---: | ---: | ---: | ---: |
+| [WikiText-2](https://huggingface.co/datasets/Salesforce/wikitext) perplexity (lower is better) | 32,704 tokens | 30.882 | **31.106** | 33.506 |
+| [ARC-Challenge](https://huggingface.co/datasets/allenai/ai2_arc) accuracy | 1,172 | 73.21% | **70.56%** | 69.88% |
+| [HellaSwag](https://huggingface.co/datasets/Rowan/hellaswag) accuracy | 2,000 | 49.50% | 48.20% | 49.00% |
+WikiText-2 perplexity uses 64 non-overlapping sequences of 512 tokens from the test split. ARC-Challenge uses the complete labeled test split. HellaSwag uses a fixed seed-0 sample from the validation split. ARC-Challenge and HellaSwag are zero-shot greedy chat multiple-choice evaluations with identical prompts and tokenization across backends; they are not canonical `lm-eval` log-likelihood scores.
+Against source BF16, the ParoQuant ARC-Challenge delta is -2.65 percentage points (paired bootstrap 95% CI: -4.18 to -1.11), while its HellaSwag delta is -1.30 points (95% CI: -2.80 to +0.20).
+Dataset revisions were pinned to `9e63b7df1592a1c2158e735cc1725454aef0d6d9` (ChartQA), `bc98d668301da7b14f648724866e57302778ab27` (MMStar), `210d026faf9955653af8916fad021475a3f00453` (ARC), `218ec52e09a7e7462a5400043bb9a69a41d06b76` (HellaSwag), and `b08601e04326c79dfdd32d625aee71d232d685c3` (WikiText).

chat_template.jinja ADDED Viewed

	@@ -0,0 +1 @@

+ {{ bos_token }}{%- for message in messages %}{%- if message.role == 'system' %}{{- '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{%- if message.content is string %}{{- message.content }}{%- else %}{%- for content in message.content %}{%- if 'text' in content %}{{- content.text }}{%- endif %}{%- endfor %}{%- endif %}{{- '<|END_OF_TURN_TOKEN|>' }}{%- elif message.role == 'user' %}{{- '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' }}{%- if message.content is string %}{{- message.content }}{%- else %}{%- for content in message.content %}{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}<|VISION_START|><|IMAGE_PAD|><|VISION_END|>{%- elif content.type == 'video' or 'video' in content %}<|VISION_START|><|VIDEO_PAD|><|VISION_END|>{%- elif 'text' in content %}{{- content.text }}{%- endif %}{%- endfor %}{%- endif %}{{- '<|END_OF_TURN_TOKEN|>' }}{%- elif message.role == 'assistant' or message.role == 'chatbot' %}{{- '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{%- if message.content is string %}{{- message.content }}{%- else %}{%- for content in message.content %}{%- if 'text' in content %}{{- content.text }}{%- endif %}{%- endfor %}{%- endif %}{{- '<|END_OF_TURN_TOKEN|>' }}{%- endif %}{%- endfor %}{%- if add_generation_prompt %}{{- '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{%- endif %}

config.json ADDED Viewed

	@@ -0,0 +1,164 @@

+{
+  "transformers_version": "5.15.0.dev0",
+  "architectures": [
+    "CohereCompassForConditionalGeneration"
+  ],
+  "output_hidden_states": false,
+  "return_dict": true,
+  "dtype": "bfloat16",
+  "chunk_size_feed_forward": 0,
+  "is_encoder_decoder": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "problem_type": null,
+  "text_config": {
+    "architectures": null,
+    "output_hidden_states": false,
+    "return_dict": true,
+    "dtype": "bfloat16",
+    "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": false,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "problem_type": null,
+    "vocab_size": 262144,
+    "hidden_size": 2048,
+    "intermediate_size": 6144,
+    "logit_scale": 0.25,
+    "num_hidden_layers": 28,
+    "num_attention_heads": 16,
+    "num_key_value_heads": 8,
+    "hidden_act": "silu",
+    "max_position_embeddings": 500000,
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-05,
+    "use_cache": true,
+    "pad_token_id": 0,
+    "bos_token_id": 2,
+    "eos_token_id": 255001,
+    "tie_word_embeddings": true,
+    "rope_parameters": {
+      "sliding_attention": {
+        "mrope_interleaved": true,
+        "mrope_section": [
+          24,
+          20,
+          20
+        ],
+        "rope_type": "default",
+        "rope_theta": 50000
+      },
+      "full_attention": null,
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    },
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "sliding_window": 4096,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "score_shift_a": null,
+    "score_shift_b": null,
+    "pooling": null,
+    "head_dim": 128,
+    "_name_or_path": "",
+    "model_type": "cohere_compass_text",
+    "output_attentions": false
+  },
+  "vision_config": {
+    "architectures": null,
+    "output_hidden_states": false,
+    "return_dict": true,
+    "dtype": "bfloat16",
+    "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": false,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "problem_type": null,
+    "depth": 27,
+    "hidden_size": 1152,
+    "hidden_act": "gelu_pytorch_tanh",
+    "intermediate_size": 4304,
+    "num_heads": 16,
+    "in_channels": 3,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2,
+    "out_hidden_size": 2048,
+    "num_position_embeddings": 2304,
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ],
+    "initializer_range": 0.02,
+    "_name_or_path": "",
+    "model_type": "cohere_compass_vision",
+    "output_attentions": false
+  },
+  "fusion_config": {
+    "patch_embeddings": true
+  },
+  "image_token_id": 255031,
+  "video_token_id": 255032,
+  "vision_start_token_id": 255028,
+  "vision_end_token_id": 255029,
+  "tie_word_embeddings": true,
+  "_name_or_path": "",
+  "eos_token_id": 255001,
+  "pad_token_id": 0,
+  "model_type": "cohere_compass",
+  "output_attentions": false,
+  "quantization_config": {
+    "quant_method": "paroquant",
+    "bits": 4,
+    "group_size": 128,
+    "krot": 8
+  }
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,12 @@

+{
+  "bos_token_id": 2,
+  "eos_token_id": [
+    255001
+  ],
+  "pad_token_id": 0,
+  "do_sample": true,
+  "temperature": 0.7,
+  "top_p": 0.8,
+  "top_k": 20
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:966a132bf32ebdc548732d6a1b03ae0738d7562f68aed85b0c5b3d540999da0b
+size 2896904080

preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,37 @@

+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": false,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "merge_size": 2,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "CohereCompassProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "temporal_patch_size": 2,
+  "image_processor_type": "CohereCompassImageProcessor"
+}

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,37 @@

+{
+  "additional_special_tokens": [
+    "<|VISION_START|>",
+    "<|IMAGE_PAD|>",
+    "<|VISION_END|>",
+    "<|VISION_PAD|>",
+    "<|VIDEO_PAD|>"
+  ],
+  "bos_token": {
+    "content": "<BOS_TOKEN>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|END_OF_TURN_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<UNK>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6fcc5292908e0c8ad1400c67fe9413825c656486fe4190dce7d8d62c38bfbbf6
+size 19550662

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,340 @@

+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<MASK_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<BOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<EOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<UNK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255000": {
+      "content": "<|START_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255001": {
+      "content": "<|END_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255002": {
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255003": {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255004": {
+      "content": "<|SYSTEM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255005": {
+      "content": "<|NEW_FILE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255006": {
+      "content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255007": {
+      "content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255008": {
+      "content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255009": {
+      "content": "<|END_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255010": {
+      "content": "<|START_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255011": {
+      "content": "<|END_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255012": {
+      "content": "<|START_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255013": {
+      "content": "<|END_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255014": {
+      "content": "<|START_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255015": {
+      "content": "<|END_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255016": {
+      "content": "<|START_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255017": {
+      "content": "<|END_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255018": {
+      "content": "<|USER_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255019": {
+      "content": "<|USER_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255020": {
+      "content": "<|USER_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255021": {
+      "content": "<|USER_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255022": {
+      "content": "<|USER_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255023": {
+      "content": "<|USER_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255024": {
+      "content": "<|USER_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255025": {
+      "content": "<|USER_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255026": {
+      "content": "<|USER_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255027": {
+      "content": "<|USER_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255028": {
+      "content": "<|VISION_START|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255029": {
+      "content": "<|VISION_END|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255030": {
+      "content": "<|VISION_PAD|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255031": {
+      "content": "<|IMAGE_PAD|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255032": {
+      "content": "<|VIDEO_PAD|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|VISION_START|>",
+    "<|IMAGE_PAD|>",
+    "<|VISION_END|>",
+    "<|VISION_PAD|>",
+    "<|VIDEO_PAD|>"
+  ],
+  "bos_token": "<BOS_TOKEN>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
+  "extra_special_tokens": {},
+  "image_token": "<|IMAGE_PAD|>",
+  "legacy": true,
+  "max_pixels": 3868706,
+  "merges_file": null,
+  "min_pixels": 16384,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "padding_side": "right",
+  "processor_class": "CohereCompassProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "CohereTokenizer",
+  "unk_token": "<UNK>",
+  "use_default_system_prompt": false,
+  "video_token": "<|VIDEO_PAD|>",
+  "vision_end_token": "<|VISION_END|>",
+  "vision_start_token": "<|VISION_START|>",
+  "vocab_file": null
+}

video_preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+  "size": {
+    "longest_edge": 25165824,
+    "shortest_edge": 4096
+  },
+  "patch_size": 16,
+  "temporal_patch_size": 2,
+  "merge_size": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "CohereCompassProcessor",
+  "video_processor_type": "CohereCompassVideoProcessor"
+}