Image-Text-to-Text
Transformers
English
ternary-quant
quantization
ternary
vlm
multimodal
video
edge
smolvlm
Instructions to use AsadIsmail/SmolVLM2-256M-Video-Instruct-ternary with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AsadIsmail/SmolVLM2-256M-Video-Instruct-ternary with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="AsadIsmail/SmolVLM2-256M-Video-Instruct-ternary")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AsadIsmail/SmolVLM2-256M-Video-Instruct-ternary", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use AsadIsmail/SmolVLM2-256M-Video-Instruct-ternary with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AsadIsmail/SmolVLM2-256M-Video-Instruct-ternary" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AsadIsmail/SmolVLM2-256M-Video-Instruct-ternary", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AsadIsmail/SmolVLM2-256M-Video-Instruct-ternary
- SGLang
How to use AsadIsmail/SmolVLM2-256M-Video-Instruct-ternary 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 "AsadIsmail/SmolVLM2-256M-Video-Instruct-ternary" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AsadIsmail/SmolVLM2-256M-Video-Instruct-ternary", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "AsadIsmail/SmolVLM2-256M-Video-Instruct-ternary" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AsadIsmail/SmolVLM2-256M-Video-Instruct-ternary", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AsadIsmail/SmolVLM2-256M-Video-Instruct-ternary with Docker Model Runner:
docker model run hf.co/AsadIsmail/SmolVLM2-256M-Video-Instruct-ternary
Add files using upload-large-folder tool
Browse files- README.md +37 -0
- broad_generative_report.json +151 -0
- metadata.json +0 -0
- tritplane/model_text_model_layers_0_self_attn_k_proj.npz +3 -0
- tritplane/model_text_model_layers_10_mlp_down_proj.npz +3 -0
- tritplane/model_text_model_layers_10_mlp_up_proj.npz +3 -0
- tritplane/model_text_model_layers_10_self_attn_k_proj.npz +3 -0
- tritplane/model_text_model_layers_10_self_attn_q_proj.npz +3 -0
- tritplane/model_text_model_layers_13_self_attn_q_proj.npz +3 -0
- tritplane/model_text_model_layers_15_self_attn_k_proj.npz +3 -0
- tritplane/model_text_model_layers_15_self_attn_q_proj.npz +3 -0
- tritplane/model_text_model_layers_16_self_attn_q_proj.npz +3 -0
- tritplane/model_text_model_layers_17_mlp_gate_proj.npz +3 -0
- tritplane/model_text_model_layers_17_mlp_up_proj.npz +3 -0
- tritplane/model_text_model_layers_18_mlp_down_proj.npz +3 -0
- tritplane/model_text_model_layers_18_self_attn_v_proj.npz +3 -0
- tritplane/model_text_model_layers_19_mlp_down_proj.npz +3 -0
- tritplane/model_text_model_layers_19_self_attn_k_proj.npz +3 -0
- tritplane/model_text_model_layers_19_self_attn_o_proj.npz +3 -0
- tritplane/model_text_model_layers_19_self_attn_q_proj.npz +3 -0
- tritplane/model_text_model_layers_20_self_attn_v_proj.npz +3 -0
- tritplane/model_text_model_layers_21_self_attn_k_proj.npz +3 -0
- tritplane/model_text_model_layers_21_self_attn_o_proj.npz +3 -0
- tritplane/model_text_model_layers_21_self_attn_q_proj.npz +3 -0
- tritplane/model_text_model_layers_22_mlp_up_proj.npz +3 -0
- tritplane/model_text_model_layers_22_self_attn_k_proj.npz +3 -0
- tritplane/model_text_model_layers_23_mlp_gate_proj.npz +3 -0
- tritplane/model_text_model_layers_24_mlp_down_proj.npz +3 -0
- tritplane/model_text_model_layers_24_self_attn_k_proj.npz +3 -0
- tritplane/model_text_model_layers_24_self_attn_o_proj.npz +3 -0
- tritplane/model_text_model_layers_24_self_attn_q_proj.npz +3 -0
- tritplane/model_text_model_layers_25_self_attn_v_proj.npz +3 -0
- tritplane/model_text_model_layers_27_self_attn_k_proj.npz +3 -0
- tritplane/model_text_model_layers_28_mlp_down_proj.npz +3 -0
- tritplane/model_text_model_layers_28_self_attn_k_proj.npz +3 -0
- tritplane/model_text_model_layers_28_self_attn_q_proj.npz +3 -0
- tritplane/model_text_model_layers_2_mlp_down_proj.npz +3 -0
- tritplane/model_text_model_layers_2_self_attn_v_proj.npz +3 -0
- tritplane/model_text_model_layers_3_mlp_up_proj.npz +3 -0
- tritplane/model_text_model_layers_3_self_attn_o_proj.npz +3 -0
- tritplane/model_text_model_layers_3_self_attn_q_proj.npz +3 -0
- tritplane/model_text_model_layers_5_mlp_gate_proj.npz +3 -0
- tritplane/model_text_model_layers_6_mlp_up_proj.npz +3 -0
- tritplane/model_text_model_layers_6_self_attn_o_proj.npz +3 -0
- tritplane/model_text_model_layers_6_self_attn_q_proj.npz +3 -0
- tritplane/model_text_model_layers_7_self_attn_v_proj.npz +3 -0
- tritplane/model_text_model_layers_8_self_attn_v_proj.npz +3 -0
- tritplane/model_text_model_layers_9_mlp_gate_proj.npz +3 -0
- tritplane/model_text_model_layers_9_mlp_up_proj.npz +3 -0
- tritplane/model_text_model_layers_9_self_attn_o_proj.npz +3 -0
README.md
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
library_name: transformers
|
| 5 |
+
tags:
|
| 6 |
+
- ternary-quant
|
| 7 |
+
- quantization
|
| 8 |
+
- ternary
|
| 9 |
+
- vlm
|
| 10 |
+
- multimodal
|
| 11 |
+
- video
|
| 12 |
+
- edge
|
| 13 |
+
- smolvlm
|
| 14 |
+
base_model: HuggingFaceTB/SmolVLM2-256M-Video-Instruct
|
| 15 |
+
pipeline_tag: image-text-to-text
|
| 16 |
+
license: apache-2.0
|
| 17 |
+
quantized_by: AsadIsmail
|
| 18 |
+
---
|
| 19 |
+
|
| 20 |
+
# SmolVLM2-256M-Video-Instruct — Ternary Quantized (tritplane3)
|
| 21 |
+
|
| 22 |
+
**Ternary-quantized version** of [HuggingFaceTB/SmolVLM2-256M-Video-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM2-256M-Video-Instruct) — the smallest video-understanding VLM, now even smaller. Ideal for edge deployment.
|
| 23 |
+
|
| 24 |
+
## Specifications
|
| 25 |
+
|
| 26 |
+
| Property | Value |
|
| 27 |
+
|---|---|
|
| 28 |
+
| **Base Model** | [HuggingFaceTB/SmolVLM2-256M-Video-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM2-256M-Video-Instruct) |
|
| 29 |
+
| **Parameters** | 256M |
|
| 30 |
+
| **Quantization** | tritplane3 (211 linear layers) |
|
| 31 |
+
| **Full-model effective bits** | 12.91 |
|
| 32 |
+
| **Compression ratio** | 1.24× |
|
| 33 |
+
| **Avg reconstruction error** | 0.1488 |
|
| 34 |
+
|
| 35 |
+
## Collection
|
| 36 |
+
|
| 37 |
+
Part of [ternary-models](https://huggingface.co/collections/AsadIsmail/ternary-models-vlms-multimodal-and-audio-69df85ff0b776624d6645d2a).
|
broad_generative_report.json
ADDED
|
@@ -0,0 +1,151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"method": "Broad-tritplane3",
|
| 3 |
+
"model": "HuggingFaceTB/SmolVLM2-256M-Video-Instruct",
|
| 4 |
+
"model_info": {
|
| 5 |
+
"model_name": "HuggingFaceTB/SmolVLM2-256M-Video-Instruct",
|
| 6 |
+
"model_family": "image_text_to_text",
|
| 7 |
+
"model_type": "smolvlm",
|
| 8 |
+
"architectures": [
|
| 9 |
+
"SmolVLMForConditionalGeneration"
|
| 10 |
+
],
|
| 11 |
+
"asset_kind": "processor",
|
| 12 |
+
"components": [
|
| 13 |
+
{
|
| 14 |
+
"name": "text_backbone",
|
| 15 |
+
"path": "model.text_model.layers",
|
| 16 |
+
"kind": "decoder_stack",
|
| 17 |
+
"module_type": "ModuleList",
|
| 18 |
+
"parameter_count": 106202880,
|
| 19 |
+
"linear_like_count": 210,
|
| 20 |
+
"sample_linear_like_names": [
|
| 21 |
+
"0.self_attn.q_proj",
|
| 22 |
+
"0.self_attn.k_proj",
|
| 23 |
+
"0.self_attn.v_proj",
|
| 24 |
+
"0.self_attn.o_proj",
|
| 25 |
+
"0.mlp.gate_proj",
|
| 26 |
+
"0.mlp.up_proj",
|
| 27 |
+
"0.mlp.down_proj",
|
| 28 |
+
"1.self_attn.q_proj"
|
| 29 |
+
]
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"name": "multimodal_connector",
|
| 33 |
+
"path": "model.connector",
|
| 34 |
+
"kind": "projector",
|
| 35 |
+
"module_type": "SmolVLMConnector",
|
| 36 |
+
"parameter_count": 7077888,
|
| 37 |
+
"linear_like_count": 1,
|
| 38 |
+
"sample_linear_like_names": [
|
| 39 |
+
"modality_projection.proj"
|
| 40 |
+
]
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"name": "vision_backbone",
|
| 44 |
+
"path": "model.vision_model.encoder.layers",
|
| 45 |
+
"kind": "vision_stack",
|
| 46 |
+
"module_type": "ModuleList",
|
| 47 |
+
"parameter_count": 85054464,
|
| 48 |
+
"linear_like_count": 72,
|
| 49 |
+
"sample_linear_like_names": [
|
| 50 |
+
"0.self_attn.k_proj",
|
| 51 |
+
"0.self_attn.v_proj",
|
| 52 |
+
"0.self_attn.q_proj",
|
| 53 |
+
"0.self_attn.out_proj",
|
| 54 |
+
"0.mlp.fc1",
|
| 55 |
+
"0.mlp.fc2",
|
| 56 |
+
"1.self_attn.k_proj",
|
| 57 |
+
"1.self_attn.v_proj"
|
| 58 |
+
]
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"name": "lm_head",
|
| 62 |
+
"path": "lm_head",
|
| 63 |
+
"kind": "lm_head",
|
| 64 |
+
"module_type": "Linear",
|
| 65 |
+
"parameter_count": 28385280,
|
| 66 |
+
"linear_like_count": 1,
|
| 67 |
+
"sample_linear_like_names": [
|
| 68 |
+
""
|
| 69 |
+
]
|
| 70 |
+
}
|
| 71 |
+
],
|
| 72 |
+
"default_quantization_components": [
|
| 73 |
+
"text_backbone",
|
| 74 |
+
"multimodal_connector"
|
| 75 |
+
]
|
| 76 |
+
},
|
| 77 |
+
"config": {
|
| 78 |
+
"components": [
|
| 79 |
+
"text_backbone",
|
| 80 |
+
"multimodal_connector"
|
| 81 |
+
],
|
| 82 |
+
"scheme": "tritplane3",
|
| 83 |
+
"group_size": 32,
|
| 84 |
+
"n_iter": 10,
|
| 85 |
+
"salient_fraction": 0.0,
|
| 86 |
+
"rescue_fraction": 0.0,
|
| 87 |
+
"n_planes": 3,
|
| 88 |
+
"allow_all_linear": false,
|
| 89 |
+
"target_module_names": [
|
| 90 |
+
"Wqkv",
|
| 91 |
+
"att_proj",
|
| 92 |
+
"attn.proj",
|
| 93 |
+
"attn.qkv",
|
| 94 |
+
"c_attn",
|
| 95 |
+
"c_fc",
|
| 96 |
+
"c_proj",
|
| 97 |
+
"dense",
|
| 98 |
+
"dense_4h_to_h",
|
| 99 |
+
"dense_h_to_4h",
|
| 100 |
+
"down_proj",
|
| 101 |
+
"fc1",
|
| 102 |
+
"fc2",
|
| 103 |
+
"ff_proj",
|
| 104 |
+
"gate_proj",
|
| 105 |
+
"gate_up_proj",
|
| 106 |
+
"k",
|
| 107 |
+
"k_proj",
|
| 108 |
+
"linear",
|
| 109 |
+
"o",
|
| 110 |
+
"o_proj",
|
| 111 |
+
"out_proj",
|
| 112 |
+
"per_layer_input_gate",
|
| 113 |
+
"per_layer_projection",
|
| 114 |
+
"proj",
|
| 115 |
+
"q",
|
| 116 |
+
"q_proj",
|
| 117 |
+
"qkv",
|
| 118 |
+
"qkv_proj",
|
| 119 |
+
"query_key_value",
|
| 120 |
+
"up_proj",
|
| 121 |
+
"v",
|
| 122 |
+
"v_proj",
|
| 123 |
+
"w1",
|
| 124 |
+
"w2",
|
| 125 |
+
"w3",
|
| 126 |
+
"wi",
|
| 127 |
+
"wi_0",
|
| 128 |
+
"wi_1",
|
| 129 |
+
"wo"
|
| 130 |
+
],
|
| 131 |
+
"max_length": 160,
|
| 132 |
+
"calibration_batch_size": 2,
|
| 133 |
+
"calibration_prompts": null,
|
| 134 |
+
"vlm_use_demo_image": true
|
| 135 |
+
},
|
| 136 |
+
"summary": {
|
| 137 |
+
"method_name": "Broad-tritplane3",
|
| 138 |
+
"model_family": "image_text_to_text",
|
| 139 |
+
"selected_components": [
|
| 140 |
+
"text_backbone",
|
| 141 |
+
"multimodal_connector"
|
| 142 |
+
],
|
| 143 |
+
"quantized_modules": 211,
|
| 144 |
+
"quantized_params": 113246208,
|
| 145 |
+
"quantized_fraction": 0.4415316287123117,
|
| 146 |
+
"avg_relative_error": 0.1487850632142753,
|
| 147 |
+
"avg_effective_bits": 9.0,
|
| 148 |
+
"full_model_effective_bits": 12.909278599013819,
|
| 149 |
+
"compression_ratio": 1.2394185993648237
|
| 150 |
+
}
|
| 151 |
+
}
|
metadata.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tritplane/model_text_model_layers_0_self_attn_k_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af0586dbd924cd5449f6d66e64faac3ac319050ed47fb2e21054f56661797826
|
| 3 |
+
size 127744
|
tritplane/model_text_model_layers_10_mlp_down_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04a099fbcf0dbd30952159c2428aa409f8d1af77aa5a264fd7f89a4c2b622738
|
| 3 |
+
size 998656
|
tritplane/model_text_model_layers_10_mlp_up_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ef399519ff223b2eb99abbc84368778330fc41031caabbf60e1d5da436f2e6a
|
| 3 |
+
size 998656
|
tritplane/model_text_model_layers_10_self_attn_k_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8db434a2ba1cdd38091349a02a3450362cd1fdcdb7d0c273c9e6898593c326ec
|
| 3 |
+
size 127744
|
tritplane/model_text_model_layers_10_self_attn_q_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:694f6fb5619f29e6567dabc08fa15d17caff2861fa953ea4f28cd1e4a129d6b1
|
| 3 |
+
size 376576
|
tritplane/model_text_model_layers_13_self_attn_q_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:580689914639c012a2b333633f8d9c79882b9671600a0d75e4d7f50f98dd492d
|
| 3 |
+
size 376576
|
tritplane/model_text_model_layers_15_self_attn_k_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15f7ae3c955a95359b674086fc376e0bdbdc3304bd05cff3f40d7345e9b9cf6f
|
| 3 |
+
size 127744
|
tritplane/model_text_model_layers_15_self_attn_q_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:044a969a0aaf70ed9b696c57fbe42f463406948c877f9460907566a20a41100a
|
| 3 |
+
size 376576
|
tritplane/model_text_model_layers_16_self_attn_q_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75f3b0c0da54a38e52dfe2581a00cf00ebaa94d844bd761183871a17493ac3d0
|
| 3 |
+
size 376576
|
tritplane/model_text_model_layers_17_mlp_gate_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f6e0a7e6896f902c0fdbf726cb21a4f21ef95ef1b03adb9acbec31818ab757e
|
| 3 |
+
size 998656
|
tritplane/model_text_model_layers_17_mlp_up_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:508688a6d86d57e5165b239d8e5c52dff415bebaaf6eb9ef00708833345f18bf
|
| 3 |
+
size 998656
|
tritplane/model_text_model_layers_18_mlp_down_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:394f3b10b9b08a7761984c4c26786cabd00d95d041f04c894bdb5be260107cd9
|
| 3 |
+
size 998656
|
tritplane/model_text_model_layers_18_self_attn_v_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af25f97c04ae8375df5bb57dc5a564e58882fa506effb8bedebf2029431048a4
|
| 3 |
+
size 127744
|
tritplane/model_text_model_layers_19_mlp_down_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:218969c9a9325411657e1a04aee40531e1c8ae277004d1cb7b4eb51b5109b430
|
| 3 |
+
size 998656
|
tritplane/model_text_model_layers_19_self_attn_k_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f510ee975ae598183f2622d14b556bc46dea3ad20487a1fba56e49d55d108c28
|
| 3 |
+
size 127744
|
tritplane/model_text_model_layers_19_self_attn_o_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c86371f6e3388b54084fa55466734a4d36c99b8775749ce9e67fddea17783fd
|
| 3 |
+
size 376576
|
tritplane/model_text_model_layers_19_self_attn_q_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8964abd36d5c53b6d648b681227f146075ea741b4231f41f2540cba17a2ea977
|
| 3 |
+
size 376576
|
tritplane/model_text_model_layers_20_self_attn_v_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b11beed5c7295e588e9be82d8c088ee82978eb192b83d7e04ae9b2d3550893cb
|
| 3 |
+
size 127744
|
tritplane/model_text_model_layers_21_self_attn_k_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:399f7b88ad8298ef1fd58c77d5cd8e6166ca65132431cbd76cd45c2b95a2807e
|
| 3 |
+
size 127744
|
tritplane/model_text_model_layers_21_self_attn_o_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b07233c33d8a5252e2918a08ad1afe3791ca27bb26581e60262c7fbae5ea217
|
| 3 |
+
size 376576
|
tritplane/model_text_model_layers_21_self_attn_q_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d89a034e893155b1761143b5a061967ce77685d68073b9fb22deb635ee7b4a4c
|
| 3 |
+
size 376576
|
tritplane/model_text_model_layers_22_mlp_up_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e999e3d75d684775b5910c84fa59a2ebac76647d87dcd25e215c6ea1b3a4856
|
| 3 |
+
size 998656
|
tritplane/model_text_model_layers_22_self_attn_k_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5b2a6ac67c823f2901bd8277ee42b4fa03ebca12c72389e88707f1ada0ae9fb
|
| 3 |
+
size 127744
|
tritplane/model_text_model_layers_23_mlp_gate_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2a45126caef19375e88dbc631b679ce608c8146570f08248ebd4d1c5fa5920d
|
| 3 |
+
size 998656
|
tritplane/model_text_model_layers_24_mlp_down_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbd4df98ec41d5d7c7cf24b3ecbd924bb828f7ac8179f3deb740326034fc8aa8
|
| 3 |
+
size 998656
|
tritplane/model_text_model_layers_24_self_attn_k_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:256421dce34c776424599a2555dc36cf082c3ea974d8dbae6a6abfb6c589df4e
|
| 3 |
+
size 127744
|
tritplane/model_text_model_layers_24_self_attn_o_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b9308a1414f4a0938f0ee5525a4df4d49783a615b7a2ab306960471acdcaba4
|
| 3 |
+
size 376576
|
tritplane/model_text_model_layers_24_self_attn_q_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70130ede9d7d7c0a8e561436bebe08fcd3aedf5480c0531ac6b0886341e22ba3
|
| 3 |
+
size 376576
|
tritplane/model_text_model_layers_25_self_attn_v_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bbb18fbf59c90b557b00e8a061541a5f66c2918c14645a4dba6888209bfec18
|
| 3 |
+
size 127744
|
tritplane/model_text_model_layers_27_self_attn_k_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9ce2fd7dc5bf672ac641587545b7ab0475baa82ab6390f67f87497c86f32ad3
|
| 3 |
+
size 127744
|
tritplane/model_text_model_layers_28_mlp_down_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4095341fc05e72d74405840ec3fbff9866f925a62fc1cca48ea99402e419d9e
|
| 3 |
+
size 998656
|
tritplane/model_text_model_layers_28_self_attn_k_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4869fd6e1bc38f686e6f8c9e1bf479fc67d96bf5839b1b0ac7d374a331b8e29
|
| 3 |
+
size 127744
|
tritplane/model_text_model_layers_28_self_attn_q_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a2d84b5dc1bfdd23fe59eb1b261763d9de06777619052e51029f36e1076f88c
|
| 3 |
+
size 376576
|
tritplane/model_text_model_layers_2_mlp_down_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eef115ef99b37998840771748c4afe971124455a3f9b0ee263319fd6d85984bb
|
| 3 |
+
size 998656
|
tritplane/model_text_model_layers_2_self_attn_v_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29a3874675ac6c391f519cf4b9705aff9f4a04507e876d23bec4e85f0061fd05
|
| 3 |
+
size 127744
|
tritplane/model_text_model_layers_3_mlp_up_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:902d2c6e47ccc9b5893c198f50a27f1034f52669980e0086ce12fa95d3c10bfc
|
| 3 |
+
size 998656
|
tritplane/model_text_model_layers_3_self_attn_o_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8aa79ecf74130d460e6405a8118e332789703dd10fc9595a47d662cbd8d176b6
|
| 3 |
+
size 376576
|
tritplane/model_text_model_layers_3_self_attn_q_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2a7a9f255c10f0f9ee9a1c6ff36e7b68b60e93a50f9a9b1200b7d9e45368a61
|
| 3 |
+
size 376576
|
tritplane/model_text_model_layers_5_mlp_gate_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:998546670f74ec31dbb1db621bf401949833abb0d2acbe2de60f5012508a9848
|
| 3 |
+
size 998656
|
tritplane/model_text_model_layers_6_mlp_up_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec42ec2ad6c29eb492210dfd5195eae74f20780d34dca7420305768d596474cb
|
| 3 |
+
size 998656
|
tritplane/model_text_model_layers_6_self_attn_o_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c94d6d893a0261d6f65624360983ac912a77231419b18dd91fce2592823e643
|
| 3 |
+
size 376576
|
tritplane/model_text_model_layers_6_self_attn_q_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99189efb82dd419b847a988e734a0b02b84a1cbe1c53da9d5e758da5d9c0b574
|
| 3 |
+
size 376576
|
tritplane/model_text_model_layers_7_self_attn_v_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a66f0021a698e783f9d5deda9a18b5c3bb3ce935b4fffce1cf24771dab09544
|
| 3 |
+
size 127744
|
tritplane/model_text_model_layers_8_self_attn_v_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a24d8e29d53fc75ad5f0dad86d068711bc60fb7c19720253d8f7adfdc9418566
|
| 3 |
+
size 127744
|
tritplane/model_text_model_layers_9_mlp_gate_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:374a38c552c030b941e1b579f3bf9b03e50beae939f14b7ca081cd3f8a23a7ab
|
| 3 |
+
size 998656
|
tritplane/model_text_model_layers_9_mlp_up_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5536a167e74770981a0ff2dca3a8c5d517bc959d3bf99ef196abfaff9e47463
|
| 3 |
+
size 998656
|
tritplane/model_text_model_layers_9_self_attn_o_proj.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe36bfb5611151e40644894cfad8876ac933c9712e899fd79539a642760493ff
|
| 3 |
+
size 376576
|