Upload 8-bit quantized E5 large instruct model

.gitattributes

@@ -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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,70 @@
----
-license: mit
----
+
+# Multilingual E5 Large Instruct - 8-bit Quantized
+
+This is an 8-bit quantized version of the [intfloat/multilingual-e5-large-instruct](https://huggingface.co/intfloat/multilingual-e5-large-instruct) model.
+
+## Model Details
+
+- Original model: [intfloat/multilingual-e5-large-instruct](https://huggingface.co/intfloat/multilingual-e5-large-instruct)
+- Quantization: 8-bit (using bitsandbytes)
+- Model architecture: XLM-RoBERTa Large with instruction tuning
+- Original parameters: 560M
+- Embedding dimensions: 1024
+- Context length: 512 tokens
+- Languages supported: 94+ languages
+
+## Usage
+
+This model can be used with the `transformers` library for generating embeddings:
+
+```python
+from transformers import AutoModel, AutoTokenizer
+import torch.nn.functional as F
+
+# Load the model
+model_name = "gopersonal/multilingual-e5-large-instruct-8bit"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModel.from_pretrained(model_name, load_in_8bit=True, device_map="auto")
+
+# Define function to get embeddings
+def average_pool(last_hidden_states, attention_mask):
+    last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
+    return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
+
+def get_detailed_instruct(task_description, query):
+    return f'Instruct: task_description\nQuery: query'
+
+# Prepare your texts
+task = 'Given a web search query, retrieve relevant passages that answer the query'
+queries = [
+    get_detailed_instruct(task, 'how much protein should a female eat'),
+    get_detailed_instruct(task, 'best restaurants in new york')
+]
+
+# Tokenize and generate embeddings
+batch_dict = tokenizer(queries, max_length=512, padding=True, truncation=True, return_tensors='pt')
+outputs = model(**batch_dict)
+embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
+
+# Normalize embeddings
+embeddings = F.normalize(embeddings, p=2, dim=1)
+```
+
+## Infinity Embedding Server Usage
+
+```bash
+docker run --gpus all -v $PWD/models:/app/.cache -p 7997:7997 \
+  michaelf34/infinity:latest \
+  v2 --model-id gopersonal/multilingual-e5-large-instruct-8bit \
+  --dtype int8 --batch-size 8 --engine torch --port 7997 --device auto
+```
+
+## Benefits of 8-bit Quantization
+
+- Approximately 50% reduction in memory usage compared to FP16
+- Faster inference, especially on GPUs with limited VRAM
+- Minimal impact on embedding quality and similarity calculations
+
+## License
+
+This model inherits the license of the original model: MIT

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "intfloat/multilingual-e5-large-instruct",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72f89215ff8df34458cf7862a1b3dc23ed9a1094c9e748808be7aad1e64353f6
+size 818751864

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}