Upload folder using huggingface_hub

README.md

@@ -0,0 +1,67 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- CGCTG/camembert-base_jina-embeddings-v2-small-en_fr
+- CGCTG/distilcamembert-base_jina-embeddings-v2-small-en_fr
+base_model:
+- CGCTG/camembert-base_jina-embeddings-v2-small-en_fr
+- CGCTG/distilcamembert-base_jina-embeddings-v2-small-en_fr
+---
+
+# Cam_DistilCamembert_FR_SLERP
+
+Cam_DistilCamembert_FR_SLERP is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [CGCTG/camembert-base_jina-embeddings-v2-small-en_fr](https://huggingface.co/CGCTG/camembert-base_jina-embeddings-v2-small-en_fr)
+* [CGCTG/distilcamembert-base_jina-embeddings-v2-small-en_fr](https://huggingface.co/CGCTG/distilcamembert-base_jina-embeddings-v2-small-en_fr)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: CGCTG/camembert-base_jina-embeddings-v2-small-en_fr
+        layer_range: [0, 4]
+      - model: CGCTG/distilcamembert-base_jina-embeddings-v2-small-en_fr
+        layer_range: [0, 4]
+# or, the equivalent models: syntax:
+#models:
+#   - model: ClassCat/gpt2-base-french
+#   - model: cmarkea/distilcamembert-base
+merge_method: slerp
+base_model: CGCTG/camembert-base_jina-embeddings-v2-small-en_fr
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5 # fallback for rest of tensors
+dtype: float16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "CGCTG/Cam_DistilCamembert_FR_SLERP"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "CGCTG/camembert-base_jina-embeddings-v2-small-en_fr",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "attn_implementation": null,
+  "auto_map": {
+    "AutoConfig": "jinaai/jina-bert-implementation--configuration_bert.JinaBertConfig",
+    "AutoModel": "jinaai/jina-bert-implementation--modeling_bert.JinaBertModel",
+    "AutoModelForMaskedLM": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForMaskedLM",
+    "AutoModelForSequenceClassification": "jinaai/jina-bert-implementation--modeling_bert.JinaBertForSequenceClassification"
+  },
+  "classifier_dropout": null,
+  "emb_pooler": "mean",
+  "feed_forward_type": "geglu",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 8192,
+  "model_max_length": 8192,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "alibi",
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30528
+}

mergekit_config.yml

@@ -0,0 +1,21 @@
+
+slices:
+  - sources:
+      - model: CGCTG/camembert-base_jina-embeddings-v2-small-en_fr
+        layer_range: [0, 4]
+      - model: CGCTG/distilcamembert-base_jina-embeddings-v2-small-en_fr
+        layer_range: [0, 4]
+# or, the equivalent models: syntax:
+#models:
+#   - model: ClassCat/gpt2-base-french
+#   - model: cmarkea/distilcamembert-base
+merge_method: slerp
+base_model: CGCTG/camembert-base_jina-embeddings-v2-small-en_fr
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5 # fallback for rest of tensors
+dtype: float16

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a8cd6b5de4235652e4e8df40f0d584aff58994229d1f8fb60c329081d6ddde7
+size 65405552

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 65397760}, "weight_map": {"embeddings.LayerNorm.bias": "model-00001-of-00001.safetensors", "embeddings.LayerNorm.weight": "model-00001-of-00001.safetensors", "embeddings.position_embeddings.weight": "model-00001-of-00001.safetensors", "embeddings.token_type_embeddings.weight": "model-00001-of-00001.safetensors", "embeddings.word_embeddings.weight": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.output.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.output.dense.weight": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.self.key.bias": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.self.key.weight": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.self.query.bias": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.self.query.weight": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.self.value.bias": "model-00001-of-00001.safetensors", "encoder.layer.0.attention.self.value.weight": "model-00001-of-00001.safetensors", "encoder.layer.0.intermediate.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.0.intermediate.dense.weight": "model-00001-of-00001.safetensors", "encoder.layer.0.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "encoder.layer.0.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "encoder.layer.0.output.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.0.output.dense.weight": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.output.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.output.dense.weight": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.self.key.bias": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.self.key.weight": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.self.query.bias": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.self.query.weight": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.self.value.bias": "model-00001-of-00001.safetensors", "encoder.layer.1.attention.self.value.weight": "model-00001-of-00001.safetensors", "encoder.layer.1.intermediate.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.1.intermediate.dense.weight": "model-00001-of-00001.safetensors", "encoder.layer.1.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "encoder.layer.1.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "encoder.layer.1.output.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.1.output.dense.weight": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.output.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.output.dense.weight": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.self.key.bias": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.self.key.weight": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.self.query.bias": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.self.query.weight": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.self.value.bias": "model-00001-of-00001.safetensors", "encoder.layer.2.attention.self.value.weight": "model-00001-of-00001.safetensors", "encoder.layer.2.intermediate.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.2.intermediate.dense.weight": "model-00001-of-00001.safetensors", "encoder.layer.2.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "encoder.layer.2.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "encoder.layer.2.output.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.2.output.dense.weight": "model-00001-of-00001.safetensors", "encoder.layer.3.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "encoder.layer.3.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "encoder.layer.3.attention.output.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.3.attention.output.dense.weight": "model-00001-of-00001.safetensors", "encoder.layer.3.attention.self.key.bias": "model-00001-of-00001.safetensors", "encoder.layer.3.attention.self.key.weight": "model-00001-of-00001.safetensors", "encoder.layer.3.attention.self.query.bias": "model-00001-of-00001.safetensors", "encoder.layer.3.attention.self.query.weight": "model-00001-of-00001.safetensors", "encoder.layer.3.attention.self.value.bias": "model-00001-of-00001.safetensors", "encoder.layer.3.attention.self.value.weight": "model-00001-of-00001.safetensors", "encoder.layer.3.intermediate.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.3.intermediate.dense.weight": "model-00001-of-00001.safetensors", "encoder.layer.3.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "encoder.layer.3.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "encoder.layer.3.output.dense.bias": "model-00001-of-00001.safetensors", "encoder.layer.3.output.dense.weight": "model-00001-of-00001.safetensors", "pooler.dense.bias": "model-00001-of-00001.safetensors", "pooler.dense.weight": "model-00001-of-00001.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 8192,
+  "model_max_length": 2147483648,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}