Add files using upload-large-folder tool

README.md

@@ -0,0 +1,67 @@
+---
+tags:
+  - visual-language-navigation
+  - robotics
+  - multimodal
+  - fp8
+  - orcalab
+base_model: a8cheng/navila-llama3-8b-8f
+library_name: pytorch
+---
+
+# Orca_VLN NaVILA FP8
+
+E4M3 FP8 inference artifact for the
+[Orca_VLN](https://github.com/openverse-orca/Orca_VLN/tree/fp8) visual-language
+navigation baseline.
+
+The artifact quantizes 225 Linear layers in the NaVILA language model. The
+vision tower and multimodal projector remain FP16. It is approximately 9.0 GiB,
+compared with approximately 15.8 GiB for the source checkpoint.
+
+## Download and run
+
+Clone the `fp8` branch and run its installer:
+
+```bash
+git clone --branch fp8 https://github.com/openverse-orca/Orca_VLN.git
+cd Orca_VLN
+./NaVILA-Orca/scripts/setup_all.sh
+```
+
+Verify the exact FP8 CUDA kernel and start the service:
+
+```bash
+./NaVILA-Orca/scripts/test_navila_fp8_gpu.py
+./NaVILA-Orca/scripts/start_navvlm_server.sh -fp8
+```
+
+The runtime requires the project-owned `FP8Linear` implementation and is not a
+drop-in Transformers checkpoint. Use the loader shipped in the `fp8` branch.
+
+## Hardware
+
+- NVIDIA compute capability 8.9 or newer
+- PyTorch 2.7 with CUDA 12.8
+- RTX 4090 (Ada) and RTX 5070 Ti (Blackwell) are supported by the runtime
+- A 16 GiB RTX 5070 Ti should be dedicated to NaVILA inference; running
+  OrcaLab on the same GPU may exceed available VRAM
+
+## Artifact
+
+| File | Purpose |
+| --- | --- |
+| `model-fp8.pt` | Serialized NaVILA model with E4M3 LLM Linear weights |
+| `fp8_manifest.json` | Format, quantized module list, size, and checksum |
+| `config.json` | NaVILA model configuration |
+
+`model-fp8.pt` SHA-256:
+
+```text
+78ef32bf7a586321b105157a359385afd2998ce09e91525b9bf783c51cdd6f0a
+```
+
+The artifact was derived from
+[`a8cheng/navila-llama3-8b-8f`](https://huggingface.co/a8cheng/navila-llama3-8b-8f)
+at revision `b2294e96581454468d6b94f38201f4f965ef48b7`. Usage remains subject
+to the upstream NaVILA model and underlying model licenses.

config.json

@@ -0,0 +1,261 @@
+{
+  "_name_or_path": "./checkpoints/vila-long-8b-8f-scanqa-rxr-real-v1-seed10-bs10-1e4",
+  "architectures": [
+    "LlavaLlamaModel"
+  ],
+  "chat_template": null,
+  "drop_path_rate": 0.0,
+  "fps": 0.0,
+  "hidden_size": 4096,
+  "image_aspect_ratio": "resize",
+  "interpolate_mode": "linear",
+  "llm_cfg": {
+    "_name_or_path": "./checkpoints/vila-long-8b-8f-scanqa-rxr-real-v1-seed10-bs10-1e4/llm",
+    "add_cross_attention": false,
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 128000,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 128009,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 8192,
+    "min_length": 0,
+    "model_max_length": 4096,
+    "model_type": "llama",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 32,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "pretraining_tp": 1,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 500000.0,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "tokenizer_model_max_length": 4096,
+    "tokenizer_padding_side": "right",
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 128259
+  },
+  "mm_hidden_size": 1152,
+  "mm_projector_cfg": {
+    "_name_or_path": "./checkpoints/vila-long-8b-8f-scanqa-rxr-real-v1-seed10-bs10-1e4/mm_projector",
+    "add_cross_attention": false,
+    "architectures": [
+      "MultimodalProjector"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "mm_projector_type": "mlp_downsample",
+    "model_type": "v2l_projector",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "mm_projector_lr": null,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "cls_patch",
+  "mm_vision_select_layer": -2,
+  "model_dtype": "torch.bfloat16",
+  "model_type": "llava_llama",
+  "num_time_tokens": 0,
+  "num_video_frames": 8,
+  "resume_path": "./checkpoints/vila-long-8b-8f-scanqa-rxr-real-v1-seed10-bs10-1e4",
+  "s2": false,
+  "s2_max_split_size": 336,
+  "s2_scales": "336,672,1008",
+  "soft_ce_std": 1.0,
+  "time_token_format": "<t{t}>",
+  "time_token_ids": [],
+  "transformers_version": "4.37.2",
+  "tune_language_model": true,
+  "tune_mm_projector": true,
+  "tune_vision_tower": true,
+  "vision_resolution": -1,
+  "vision_tower_cfg": {
+    "_name_or_path": "./checkpoints/vila-long-8b-8f-scanqa-rxr-real-v1-seed10-bs10-1e4/vision_tower",
+    "add_cross_attention": false,
+    "architectures": [
+      "SiglipVisionModel"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 384,
+    "intermediate_size": 4304,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-06,
+    "length_penalty": 1.0,
+    "llm_depth_token_id": 128258,
+    "llm_mask_token_id": 128257,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "siglip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

fp8_manifest.json

@@ -0,0 +1,244 @@
+{
+  "format": "orca-navila-fp8-e4m3-v1",
+  "source": "a8cheng/navila-llama3-8b-8f@b2294e96581454468d6b94f38201f4f965ef48b7",
+  "torch_version": "2.3.0+cu121",
+  "weight_dtype": "float8_e4m3fn",
+  "activation_dtype": "dynamic_float8_e4m3fn",
+  "quantized_component": "llm_linear_layers",
+  "high_precision_components": [
+    "vision_tower",
+    "mm_projector"
+  ],
+  "quantized_module_count": 225,
+  "quantized_modules": [
+    "model.layers.0.self_attn.q_proj",
+    "model.layers.0.self_attn.k_proj",
+    "model.layers.0.self_attn.v_proj",
+    "model.layers.0.self_attn.o_proj",
+    "model.layers.0.mlp.gate_proj",
+    "model.layers.0.mlp.up_proj",
+    "model.layers.0.mlp.down_proj",
+    "model.layers.1.self_attn.q_proj",
+    "model.layers.1.self_attn.k_proj",
+    "model.layers.1.self_attn.v_proj",
+    "model.layers.1.self_attn.o_proj",
+    "model.layers.1.mlp.gate_proj",
+    "model.layers.1.mlp.up_proj",
+    "model.layers.1.mlp.down_proj",
+    "model.layers.2.self_attn.q_proj",
+    "model.layers.2.self_attn.k_proj",
+    "model.layers.2.self_attn.v_proj",
+    "model.layers.2.self_attn.o_proj",
+    "model.layers.2.mlp.gate_proj",
+    "model.layers.2.mlp.up_proj",
+    "model.layers.2.mlp.down_proj",
+    "model.layers.3.self_attn.q_proj",
+    "model.layers.3.self_attn.k_proj",
+    "model.layers.3.self_attn.v_proj",
+    "model.layers.3.self_attn.o_proj",
+    "model.layers.3.mlp.gate_proj",
+    "model.layers.3.mlp.up_proj",
+    "model.layers.3.mlp.down_proj",
+    "model.layers.4.self_attn.q_proj",
+    "model.layers.4.self_attn.k_proj",
+    "model.layers.4.self_attn.v_proj",
+    "model.layers.4.self_attn.o_proj",
+    "model.layers.4.mlp.gate_proj",
+    "model.layers.4.mlp.up_proj",
+    "model.layers.4.mlp.down_proj",
+    "model.layers.5.self_attn.q_proj",
+    "model.layers.5.self_attn.k_proj",
+    "model.layers.5.self_attn.v_proj",
+    "model.layers.5.self_attn.o_proj",
+    "model.layers.5.mlp.gate_proj",
+    "model.layers.5.mlp.up_proj",
+    "model.layers.5.mlp.down_proj",
+    "model.layers.6.self_attn.q_proj",
+    "model.layers.6.self_attn.k_proj",
+    "model.layers.6.self_attn.v_proj",
+    "model.layers.6.self_attn.o_proj",
+    "model.layers.6.mlp.gate_proj",
+    "model.layers.6.mlp.up_proj",
+    "model.layers.6.mlp.down_proj",
+    "model.layers.7.self_attn.q_proj",
+    "model.layers.7.self_attn.k_proj",
+    "model.layers.7.self_attn.v_proj",
+    "model.layers.7.self_attn.o_proj",
+    "model.layers.7.mlp.gate_proj",
+    "model.layers.7.mlp.up_proj",
+    "model.layers.7.mlp.down_proj",
+    "model.layers.8.self_attn.q_proj",
+    "model.layers.8.self_attn.k_proj",
+    "model.layers.8.self_attn.v_proj",
+    "model.layers.8.self_attn.o_proj",
+    "model.layers.8.mlp.gate_proj",
+    "model.layers.8.mlp.up_proj",
+    "model.layers.8.mlp.down_proj",
+    "model.layers.9.self_attn.q_proj",
+    "model.layers.9.self_attn.k_proj",
+    "model.layers.9.self_attn.v_proj",
+    "model.layers.9.self_attn.o_proj",
+    "model.layers.9.mlp.gate_proj",
+    "model.layers.9.mlp.up_proj",
+    "model.layers.9.mlp.down_proj",
+    "model.layers.10.self_attn.q_proj",
+    "model.layers.10.self_attn.k_proj",
+    "model.layers.10.self_attn.v_proj",
+    "model.layers.10.self_attn.o_proj",
+    "model.layers.10.mlp.gate_proj",
+    "model.layers.10.mlp.up_proj",
+    "model.layers.10.mlp.down_proj",
+    "model.layers.11.self_attn.q_proj",
+    "model.layers.11.self_attn.k_proj",
+    "model.layers.11.self_attn.v_proj",
+    "model.layers.11.self_attn.o_proj",
+    "model.layers.11.mlp.gate_proj",
+    "model.layers.11.mlp.up_proj",
+    "model.layers.11.mlp.down_proj",
+    "model.layers.12.self_attn.q_proj",
+    "model.layers.12.self_attn.k_proj",
+    "model.layers.12.self_attn.v_proj",
+    "model.layers.12.self_attn.o_proj",
+    "model.layers.12.mlp.gate_proj",
+    "model.layers.12.mlp.up_proj",
+    "model.layers.12.mlp.down_proj",
+    "model.layers.13.self_attn.q_proj",
+    "model.layers.13.self_attn.k_proj",
+    "model.layers.13.self_attn.v_proj",
+    "model.layers.13.self_attn.o_proj",
+    "model.layers.13.mlp.gate_proj",
+    "model.layers.13.mlp.up_proj",
+    "model.layers.13.mlp.down_proj",
+    "model.layers.14.self_attn.q_proj",
+    "model.layers.14.self_attn.k_proj",
+    "model.layers.14.self_attn.v_proj",
+    "model.layers.14.self_attn.o_proj",
+    "model.layers.14.mlp.gate_proj",
+    "model.layers.14.mlp.up_proj",
+    "model.layers.14.mlp.down_proj",
+    "model.layers.15.self_attn.q_proj",
+    "model.layers.15.self_attn.k_proj",
+    "model.layers.15.self_attn.v_proj",
+    "model.layers.15.self_attn.o_proj",
+    "model.layers.15.mlp.gate_proj",
+    "model.layers.15.mlp.up_proj",
+    "model.layers.15.mlp.down_proj",
+    "model.layers.16.self_attn.q_proj",
+    "model.layers.16.self_attn.k_proj",
+    "model.layers.16.self_attn.v_proj",
+    "model.layers.16.self_attn.o_proj",
+    "model.layers.16.mlp.gate_proj",
+    "model.layers.16.mlp.up_proj",
+    "model.layers.16.mlp.down_proj",
+    "model.layers.17.self_attn.q_proj",
+    "model.layers.17.self_attn.k_proj",
+    "model.layers.17.self_attn.v_proj",
+    "model.layers.17.self_attn.o_proj",
+    "model.layers.17.mlp.gate_proj",
+    "model.layers.17.mlp.up_proj",
+    "model.layers.17.mlp.down_proj",
+    "model.layers.18.self_attn.q_proj",
+    "model.layers.18.self_attn.k_proj",
+    "model.layers.18.self_attn.v_proj",
+    "model.layers.18.self_attn.o_proj",
+    "model.layers.18.mlp.gate_proj",
+    "model.layers.18.mlp.up_proj",
+    "model.layers.18.mlp.down_proj",
+    "model.layers.19.self_attn.q_proj",
+    "model.layers.19.self_attn.k_proj",
+    "model.layers.19.self_attn.v_proj",
+    "model.layers.19.self_attn.o_proj",
+    "model.layers.19.mlp.gate_proj",
+    "model.layers.19.mlp.up_proj",
+    "model.layers.19.mlp.down_proj",
+    "model.layers.20.self_attn.q_proj",
+    "model.layers.20.self_attn.k_proj",
+    "model.layers.20.self_attn.v_proj",
+    "model.layers.20.self_attn.o_proj",
+    "model.layers.20.mlp.gate_proj",
+    "model.layers.20.mlp.up_proj",
+    "model.layers.20.mlp.down_proj",
+    "model.layers.21.self_attn.q_proj",
+    "model.layers.21.self_attn.k_proj",
+    "model.layers.21.self_attn.v_proj",
+    "model.layers.21.self_attn.o_proj",
+    "model.layers.21.mlp.gate_proj",
+    "model.layers.21.mlp.up_proj",
+    "model.layers.21.mlp.down_proj",
+    "model.layers.22.self_attn.q_proj",
+    "model.layers.22.self_attn.k_proj",
+    "model.layers.22.self_attn.v_proj",
+    "model.layers.22.self_attn.o_proj",
+    "model.layers.22.mlp.gate_proj",
+    "model.layers.22.mlp.up_proj",
+    "model.layers.22.mlp.down_proj",
+    "model.layers.23.self_attn.q_proj",
+    "model.layers.23.self_attn.k_proj",
+    "model.layers.23.self_attn.v_proj",
+    "model.layers.23.self_attn.o_proj",
+    "model.layers.23.mlp.gate_proj",
+    "model.layers.23.mlp.up_proj",
+    "model.layers.23.mlp.down_proj",
+    "model.layers.24.self_attn.q_proj",
+    "model.layers.24.self_attn.k_proj",
+    "model.layers.24.self_attn.v_proj",
+    "model.layers.24.self_attn.o_proj",
+    "model.layers.24.mlp.gate_proj",
+    "model.layers.24.mlp.up_proj",
+    "model.layers.24.mlp.down_proj",
+    "model.layers.25.self_attn.q_proj",
+    "model.layers.25.self_attn.k_proj",
+    "model.layers.25.self_attn.v_proj",
+    "model.layers.25.self_attn.o_proj",
+    "model.layers.25.mlp.gate_proj",
+    "model.layers.25.mlp.up_proj",
+    "model.layers.25.mlp.down_proj",
+    "model.layers.26.self_attn.q_proj",
+    "model.layers.26.self_attn.k_proj",
+    "model.layers.26.self_attn.v_proj",
+    "model.layers.26.self_attn.o_proj",
+    "model.layers.26.mlp.gate_proj",
+    "model.layers.26.mlp.up_proj",
+    "model.layers.26.mlp.down_proj",
+    "model.layers.27.self_attn.q_proj",
+    "model.layers.27.self_attn.k_proj",
+    "model.layers.27.self_attn.v_proj",
+    "model.layers.27.self_attn.o_proj",
+    "model.layers.27.mlp.gate_proj",
+    "model.layers.27.mlp.up_proj",
+    "model.layers.27.mlp.down_proj",
+    "model.layers.28.self_attn.q_proj",
+    "model.layers.28.self_attn.k_proj",
+    "model.layers.28.self_attn.v_proj",
+    "model.layers.28.self_attn.o_proj",
+    "model.layers.28.mlp.gate_proj",
+    "model.layers.28.mlp.up_proj",
+    "model.layers.28.mlp.down_proj",
+    "model.layers.29.self_attn.q_proj",
+    "model.layers.29.self_attn.k_proj",
+    "model.layers.29.self_attn.v_proj",
+    "model.layers.29.self_attn.o_proj",
+    "model.layers.29.mlp.gate_proj",
+    "model.layers.29.mlp.up_proj",
+    "model.layers.29.mlp.down_proj",
+    "model.layers.30.self_attn.q_proj",
+    "model.layers.30.self_attn.k_proj",
+    "model.layers.30.self_attn.v_proj",
+    "model.layers.30.self_attn.o_proj",
+    "model.layers.30.mlp.gate_proj",
+    "model.layers.30.mlp.up_proj",
+    "model.layers.30.mlp.down_proj",
+    "model.layers.31.self_attn.q_proj",
+    "model.layers.31.self_attn.k_proj",
+    "model.layers.31.self_attn.v_proj",
+    "model.layers.31.self_attn.o_proj",
+    "model.layers.31.mlp.gate_proj",
+    "model.layers.31.mlp.up_proj",
+    "model.layers.31.mlp.down_proj",
+    "lm_head"
+  ],
+  "model_file": "model-fp8.pt",
+  "model_sha256": "78ef32bf7a586321b105157a359385afd2998ce09e91525b9bf783c51cdd6f0a",
+  "model_bytes": 9626294873,
+  "elapsed_seconds": 25.561
+}

model-fp8.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ef32bf7a586321b105157a359385afd2998ce09e91525b9bf783c51cdd6f0a
+size 9626294873