Duplicate from liuhaotian/LLaVA-Lightning-MPT-7B-preview

Co-authored-by: Haotian Liu <liuhaotian@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,48 @@
+---
+license: cc-by-nc-sa-4.0
+inference: false
+---
+
+
+**NOTE: This is a research preview of the LLaVA-Lightning based on MPT-7B-chat checkpoint. The usage of the model should comply with MPT-7B-chat license and agreements.**
+
+**NOTE: Unlike other LLaVA models, this model can (should) be used directly without delta weights conversion!**
+
+<br>
+<br>
+
+# LLaVA Model Card
+
+## Model details
+
+**Model type:**
+LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna/MPT on GPT-generated multimodal instruction-following data.
+It is an auto-regressive language model, based on the transformer architecture.
+
+**Model date:**
+LLaVA-Lightning-MPT was trained in May 2023.
+
+**Paper or resources for more information:**
+https://llava-vl.github.io/
+
+**License:**
+CC-BY-NC-SA 4.0
+
+**Where to send questions or comments about the model:**
+https://github.com/haotian-liu/LLaVA/issues
+
+## Intended use
+**Primary intended uses:**
+The primary use of LLaVA is research on large multimodal models and chatbots.
+
+**Primary intended users:**
+The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
+
+## Training dataset
+558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.
+80K GPT-generated multimodal instruction-following data.
+
+## Evaluation dataset
+A preliminary evaluation of the model quality is conducted by creating a set of 90 visual reasoning questions from 30 unique images randomly sampled from COCO val 2014 and each is associated with three types of questions: conversational, detailed description, and complex reasoning. We utilize GPT-4 to judge the model outputs.
+We also evaluate our model on the ScienceQA dataset.  Our synergy with GPT-4 sets a new state-of-the-art on the dataset.
+See https://llava-vl.github.io/ for more details.

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "llava-mpt-7b-pretrain_blip_558k_new_template_1e-instruct_conv_reason_nooverlap_80k-1epoch",
+  "architectures": [
+    "LlavaMPTForCausalLM"
+  ],
+  "attn_config": {
+    "alibi": true,
+    "alibi_bias_max": 8,
+    "attn_impl": "torch",
+    "attn_pdrop": 0,
+    "attn_type": "multihead_attention",
+    "attn_uses_sequence_id": false,
+    "clip_qkv": null,
+    "prefix_lm": false,
+    "qk_ln": false,
+    "softmax_scale": null
+  },
+  "d_model": 4096,
+  "emb_pdrop": 0,
+  "embedding_fraction": 1.0,
+  "expansion_ratio": 4,
+  "freeze_mm_mlp_adapter": false,
+  "init_config": {
+    "emb_init_std": null,
+    "emb_init_uniform_lim": null,
+    "fan_mode": "fan_in",
+    "init_div_is_residual": true,
+    "init_gain": 0,
+    "init_nonlinearity": "relu",
+    "init_std": 0.02,
+    "name": "kaiming_normal_",
+    "verbose": 0
+  },
+  "init_device": "cpu",
+  "learned_pos_emb": true,
+  "logit_scale": null,
+  "max_seq_len": 2048,
+  "mm_hidden_size": 1024,
+  "mm_use_im_start_end": true,
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14",
+  "model_type": "llava_mpt",
+  "n_heads": 32,
+  "n_layers": 32,
+  "no_bias": true,
+  "norm_type": "low_precision_layernorm",
+  "resid_pdrop": 0,
+  "sep_image_conv_front": false,
+  "tokenizer_name": "sam-mosaic/gpt-neox-20b-chatml",
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.0.dev0",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "verbose": 0,
+  "vocab_size": 50282
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": true
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3b5c5fc9fb3396457831435c0d1c2ebed563113ded07f29ff0c327c28e67a5b
+size 9941811475

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff8b9d6cf665daec893970697c6204fcce087f0e5035beab0cde2ed3afe8a4a9
+size 3363996599

pytorch_model.bin.index.json

@@ -0,0 +1,203 @@
+{
+  "metadata": {
+    "total_size": 13305741312
+  },
+  "weight_map": {
+    "transformer.blocks.0.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.0.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.0.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.0.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.0.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.0.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.1.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.1.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.1.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.1.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.1.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.1.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.10.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.10.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.10.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.10.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.10.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.10.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.11.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.11.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.11.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.11.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.11.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.11.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.12.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.12.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.12.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.12.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.12.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.12.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.13.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.13.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.13.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.13.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.13.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.13.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.14.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.14.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.14.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.14.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.14.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.14.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.15.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.15.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.15.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.15.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.15.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.15.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.16.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.16.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.16.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.16.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.16.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.16.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.17.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.17.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.17.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.17.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.17.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.17.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.18.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.18.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.18.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.18.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.18.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.18.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.19.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.19.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.19.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.19.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.19.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.19.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.2.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.2.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.2.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.2.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.2.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.2.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.20.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.20.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.20.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.20.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.20.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.20.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.21.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.21.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.21.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.21.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.21.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.21.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.22.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.22.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.22.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.22.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.22.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.22.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.23.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.23.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.23.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.23.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.23.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.23.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.24.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.24.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.24.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.24.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.24.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.24.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.25.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.25.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.25.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.25.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.25.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.25.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.26.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.26.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.26.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.26.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.26.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.26.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.27.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.27.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.27.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.27.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.27.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.27.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.28.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.28.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.28.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.28.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.28.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.28.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.29.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.29.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.29.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.29.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.29.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.29.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.3.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.3.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.3.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.3.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.3.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.3.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.30.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.30.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.30.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.30.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.30.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.30.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.31.attn.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.31.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.31.ffn.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.31.ffn.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.31.norm_1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.31.norm_2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.blocks.4.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.4.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.4.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.4.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.4.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.4.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.5.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.5.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.5.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.5.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.5.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.5.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.6.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.6.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.6.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.6.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.6.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.6.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.7.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.7.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.7.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.7.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.7.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.7.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.8.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.8.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.8.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.8.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.8.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.8.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.9.attn.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.9.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.9.ffn.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.9.ffn.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.9.norm_1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.blocks.9.norm_2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.mm_projector.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.mm_projector.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.norm_f.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,10 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "padding_side": "right",
+  "special_tokens_map_file": "./checkpoints/mpt-7b-chat/special_tokens_map.json",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}