Upload folder using huggingface_hub

README.md

@@ -0,0 +1,54 @@
+---
+base_model:
+- premai-io/prem-1B-chat
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# prem-7B-chat
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [premai-io/prem-1B-chat](https://huggingface.co/premai-io/prem-1B-chat)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+    - model: premai-io/prem-1B-chat
+      layer_range: [0, 22]
+  - sources:
+    - model: premai-io/prem-1B-chat
+      layer_range: [0, 22]
+  - sources:
+    - model: premai-io/prem-1B-chat
+      layer_range: [0, 22]
+  - sources:
+    - model: premai-io/prem-1B-chat
+      layer_range: [0, 22]
+  - sources:
+    - model: premai-io/prem-1B-chat
+      layer_range: [0, 22]
+  - sources:
+    - model: premai-io/prem-1B-chat
+      layer_range: [0, 22]
+  - sources:
+    - model: premai-io/prem-1B-chat
+      layer_range: [0, 22]                              
+merge_method: passthrough
+dtype: bfloat16
+
+```

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|end_header_id|>": 32001,
+  "<|eot_id|>": 32002,
+  "<|start_header_id|>": 32000,
+  "[PAD]": 32003
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "premai-io/prem-1B-chat",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 154,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 32004
+}

mergekit_config.yml

@@ -0,0 +1,24 @@
+slices:
+  - sources:
+    - model: premai-io/prem-1B-chat
+      layer_range: [0, 22]
+  - sources:
+    - model: premai-io/prem-1B-chat
+      layer_range: [0, 22]
+  - sources:
+    - model: premai-io/prem-1B-chat
+      layer_range: [0, 22]
+  - sources:
+    - model: premai-io/prem-1B-chat
+      layer_range: [0, 22]
+  - sources:
+    - model: premai-io/prem-1B-chat
+      layer_range: [0, 22]
+  - sources:
+    - model: premai-io/prem-1B-chat
+      layer_range: [0, 22]
+  - sources:
+    - model: premai-io/prem-1B-chat
+      layer_range: [0, 22]                              
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a6da7adf673740a1ad39c2a325dc6e23b7337ede12f2c11ddd5d97aeda9b0c
+size 4993836096

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e4a690d5758abcff6d0e216004ea3f0ece87d4052578fbcbd719d4a4d6477e2
+size 4979156384

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55bcc0ef4bf99630318fd0d910b46dc5692f9f7d06e908811c37afa280613537
+size 3854990320

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<|start_header_id|>",
+    "<|end_header_id|>",
+    "<|eot_id|>"
+  ],
+  "bos_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
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,79 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "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
+    },
+    "32000": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|start_header_id|>",
+    "<|end_header_id|>",
+    "<|eot_id|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}