Upload folder using huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+base_model:
+- inceptionai/jais-family-590m
+- inceptionai/jais-family-590m
+tags:
+- merge
+- mergekit
+- lazymergekit
+- inceptionai/jais-family-590m
+---
+
+# Jais-590m-merged
+
+Jais-590m-merged is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [inceptionai/jais-family-590m](https://huggingface.co/inceptionai/jais-family-590m)
+* [inceptionai/jais-family-590m](https://huggingface.co/inceptionai/jais-family-590m)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: inceptionai/jais-family-590m
+        layer_range: [0, 18]
+      - model: inceptionai/jais-family-590m
+        layer_range: [0, 18]
+merge_method: slerp
+base_model: inceptionai/jais-family-590m
+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
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Solshine/Jais-590m-merged"
+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 +1,42 @@
+{
+  "_name_or_path": "inceptionai/jais-family-590m",
+  "activation_function": "swiglu",
+  "alibi_scaling": null,
+  "architectures": [
+    "JAISLMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "inceptionai/jais-family-590m--configuration_jais.JAISConfig",
+    "AutoModel": "inceptionai/jais-family-590m--modeling_jais.JAISModel",
+    "AutoModelForCausalLM": "inceptionai/jais-family-590m--modeling_jais.JAISLMHeadModel",
+    "AutoModelForQuestionAnswering": "inceptionai/jais-family-590m--modeling_jais.JAISForQuestionAnswering",
+    "AutoModelForSequenceClassification": "inceptionai/jais-family-590m--modeling_jais.JAISForSequenceClassification",
+    "AutoModelForTokenClassification": "inceptionai/jais-family-590m--modeling_jais.JAISForTokenClassification"
+  },
+  "bos_token_id": 0,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "jais",
+  "mup_embeddings_scale": 9.1705785388303,
+  "mup_output_alpha": 1.09518349815769,
+  "mup_scale_qk_dot_by_d": true,
+  "mup_width_scale": 0.16666666666666666,
+  "n_embd": 1536,
+  "n_head": 12,
+  "n_inner": 4096,
+  "n_layer": 18,
+  "n_positions": 2048,
+  "pad_token_id": 0,
+  "position_embedding_type": "alibi",
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 84992
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: inceptionai/jais-family-590m
+        layer_range: [0, 18]
+      - model: inceptionai/jais-family-590m
+        layer_range: [0, 18]
+merge_method: slerp
+base_model: inceptionai/jais-family-590m
+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
+dtype: bfloat16

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ceda4458d87153c16524199374065ee45878f191529f95c9e1bd5a65279dc10
+size 1281136720

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 1281110040}, "weight_map": {"transformer.h.0.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.0.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.0.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.0.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.0.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.0.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.0.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.0.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.0.mlp.c_fc2.bias": "model-00001-of-00001.safetensors", "transformer.h.0.mlp.c_fc2.weight": "model-00001-of-00001.safetensors", "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.1.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.1.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.1.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.1.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.1.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.1.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.1.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.1.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.1.mlp.c_fc2.bias": "model-00001-of-00001.safetensors", "transformer.h.1.mlp.c_fc2.weight": "model-00001-of-00001.safetensors", "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.10.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.10.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.10.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.10.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.10.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.10.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.10.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.10.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.10.mlp.c_fc2.bias": "model-00001-of-00001.safetensors", "transformer.h.10.mlp.c_fc2.weight": "model-00001-of-00001.safetensors", "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.11.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.11.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.11.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.11.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.11.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.11.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.11.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.11.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.11.mlp.c_fc2.bias": "model-00001-of-00001.safetensors", "transformer.h.11.mlp.c_fc2.weight": "model-00001-of-00001.safetensors", "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.12.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.12.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.12.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.12.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.12.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.12.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.12.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.12.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.12.mlp.c_fc2.bias": "model-00001-of-00001.safetensors", "transformer.h.12.mlp.c_fc2.weight": "model-00001-of-00001.safetensors", "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.13.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.13.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.13.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.13.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.13.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.13.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.13.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.13.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.13.mlp.c_fc2.bias": "model-00001-of-00001.safetensors", "transformer.h.13.mlp.c_fc2.weight": "model-00001-of-00001.safetensors", "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.14.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.14.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.14.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.14.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.14.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.14.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.14.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.14.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.14.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.14.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.14.mlp.c_fc2.bias": "model-00001-of-00001.safetensors", "transformer.h.14.mlp.c_fc2.weight": "model-00001-of-00001.safetensors", "transformer.h.14.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.15.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.15.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.15.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.15.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.15.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.15.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.15.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.15.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.15.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.15.mlp.c_fc2.bias": "model-00001-of-00001.safetensors", "transformer.h.15.mlp.c_fc2.weight": "model-00001-of-00001.safetensors", "transformer.h.15.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.15.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.16.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.16.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.16.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.16.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.16.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.16.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.16.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.16.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.16.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.16.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.16.mlp.c_fc2.bias": "model-00001-of-00001.safetensors", "transformer.h.16.mlp.c_fc2.weight": "model-00001-of-00001.safetensors", "transformer.h.16.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.16.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.17.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.17.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.17.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.17.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.17.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.17.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.17.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.17.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.17.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.17.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.17.mlp.c_fc2.bias": "model-00001-of-00001.safetensors", "transformer.h.17.mlp.c_fc2.weight": "model-00001-of-00001.safetensors", "transformer.h.17.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.17.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.2.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.2.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.2.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.2.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.2.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.2.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.2.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.2.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.2.mlp.c_fc2.bias": "model-00001-of-00001.safetensors", "transformer.h.2.mlp.c_fc2.weight": "model-00001-of-00001.safetensors", "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.3.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.3.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.3.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.3.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.3.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.3.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.3.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.3.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.3.mlp.c_fc2.bias": "model-00001-of-00001.safetensors", "transformer.h.3.mlp.c_fc2.weight": "model-00001-of-00001.safetensors", "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.4.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.4.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.4.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.4.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.4.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.4.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.4.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.4.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.4.mlp.c_fc2.bias": "model-00001-of-00001.safetensors", "transformer.h.4.mlp.c_fc2.weight": "model-00001-of-00001.safetensors", "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.5.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.5.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.5.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.5.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.5.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.5.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.5.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.5.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.5.mlp.c_fc2.bias": "model-00001-of-00001.safetensors", "transformer.h.5.mlp.c_fc2.weight": "model-00001-of-00001.safetensors", "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.6.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.6.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.6.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.6.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.6.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.6.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.6.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.6.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.6.mlp.c_fc2.bias": "model-00001-of-00001.safetensors", "transformer.h.6.mlp.c_fc2.weight": "model-00001-of-00001.safetensors", "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.7.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.7.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.7.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.7.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.7.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.7.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.7.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.7.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.7.mlp.c_fc2.bias": "model-00001-of-00001.safetensors", "transformer.h.7.mlp.c_fc2.weight": "model-00001-of-00001.safetensors", "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.8.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.8.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.8.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.8.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.8.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.8.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.8.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.8.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.8.mlp.c_fc2.bias": "model-00001-of-00001.safetensors", "transformer.h.8.mlp.c_fc2.weight": "model-00001-of-00001.safetensors", "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.9.attn.c_attn.bias": "model-00001-of-00001.safetensors", "transformer.h.9.attn.c_attn.weight": "model-00001-of-00001.safetensors", "transformer.h.9.attn.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.9.attn.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.h.9.ln_1.bias": "model-00001-of-00001.safetensors", "transformer.h.9.ln_1.weight": "model-00001-of-00001.safetensors", "transformer.h.9.ln_2.bias": "model-00001-of-00001.safetensors", "transformer.h.9.ln_2.weight": "model-00001-of-00001.safetensors", "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00001.safetensors", "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00001.safetensors", "transformer.h.9.mlp.c_fc2.bias": "model-00001-of-00001.safetensors", "transformer.h.9.mlp.c_fc2.weight": "model-00001-of-00001.safetensors", "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00001.safetensors", "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00001.safetensors", "transformer.ln_f.bias": "model-00001-of-00001.safetensors", "transformer.ln_f.weight": "model-00001-of-00001.safetensors", "transformer.relative_pe.slopes": "model-00001-of-00001.safetensors", "transformer.wte.weight": "model-00001-of-00001.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<|endoftext|>"
+}