Upload folder using huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+base_model:
+- Finnish-NLP/sft-hf_hf_2024_06_29_14_08_01_checkpoint_564_dpo-checkpoint-249
+- Finnish-NLP/sft-hf_hf_2024_07_09_16_33_52_checkpoint_1758_dpo-checkpoint-832
+tags:
+- merge
+- mergekit
+- lazymergekit
+- Finnish-NLP/sft-hf_hf_2024_06_29_14_08_01_checkpoint_564_dpo-checkpoint-249
+- Finnish-NLP/sft-hf_hf_2024_07_09_16_33_52_checkpoint_1758_dpo-checkpoint-832
+---
+
+# Ahma-3B-dpo-slerp
+
+Ahma-3B-dpo-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [Finnish-NLP/sft-hf_hf_2024_06_29_14_08_01_checkpoint_564_dpo-checkpoint-249](https://huggingface.co/Finnish-NLP/sft-hf_hf_2024_06_29_14_08_01_checkpoint_564_dpo-checkpoint-249)
+* [Finnish-NLP/sft-hf_hf_2024_07_09_16_33_52_checkpoint_1758_dpo-checkpoint-832](https://huggingface.co/Finnish-NLP/sft-hf_hf_2024_07_09_16_33_52_checkpoint_1758_dpo-checkpoint-832)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: Finnish-NLP/sft-hf_hf_2024_06_29_14_08_01_checkpoint_564_dpo-checkpoint-249
+        layer_range: [0, 26]
+      - model: Finnish-NLP/sft-hf_hf_2024_07_09_16_33_52_checkpoint_1758_dpo-checkpoint-832
+        layer_range: [0, 26]
+merge_method: slerp
+base_model: Finnish-NLP/sft-hf_hf_2024_06_29_14_08_01_checkpoint_564_dpo-checkpoint-249
+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 = "RASMUS/Ahma-3B-dpo-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 +1,29 @@
+{
+  "_name_or_path": "Finnish-NLP/sft-hf_hf_2024_06_29_14_08_01_checkpoint_564_dpo-checkpoint-249",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 3200,
+  "initializer_range": 0.02,
+  "intermediate_size": 8640,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 64257
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: Finnish-NLP/sft-hf_hf_2024_06_29_14_08_01_checkpoint_564_dpo-checkpoint-249
+        layer_range: [0, 26]
+      - model: Finnish-NLP/sft-hf_hf_2024_07_09_16_33_52_checkpoint_1758_dpo-checkpoint-832
+        layer_range: [0, 26]
+merge_method: slerp
+base_model: Finnish-NLP/sft-hf_hf_2024_06_29_14_08_01_checkpoint_564_dpo-checkpoint-249
+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-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a0f90a924dd06dd1a1c87018f4aaee3b74c3f81de1d48c80a81b847cf425d9
+size 988391192

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22481a6922fff44b2b7212a4bbf3cf604874e4fecea1b2790a48e13b115d15e9
+size 991287336

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d82446b618357cfe1e3b9cff6dde31e100fde31f6f2bdd1b708bfa4dcfc9062
+size 991287344

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9827701289f49b088af796015b9a9bc68b70b5121e7ef72c905933aaca09ec47
+size 991287344

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86bf6f50da8199d4dff9b49f7ef8ab0b0de474e60d11a98d7c585d56a2b86264
+size 991287344

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dceb07c0abd36cb78b2221cd41e5a3be2d87d9a58f0df4570e0bd200830808f
+size 991287328

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d51a52d3cd500fc45b1a176333a298732f81a2bb8e531d4effa5dbbc67517e2
+size 991287312

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8180e06c85a5487b302a74972d9a45b6ca94c129750ad2a7fcc5d61d87858ae0
+size 329748792

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 7265836800}, "weight_map": {"lm_head.weight": "model-00001-of-00008.safetensors", "model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.norm.weight": "model-00008-of-00008.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,83 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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
+    },
+    "3": {
+      "content": "[INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[/INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<<SYS>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<</SYS>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64256": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'Olet tekoälyavustaja. Vastaat aina mahdollisimman avuliaasti. Vastauksesi eivät saa sisältää mitään haitallista, epäeettistä, rasistista, seksististä, vaarallista tai laitonta sisältöä. Jos kysymyksessä ei ole mitään järkeä tai se ei ole asiasisällöltään johdonmukainen, selitä miksi sen sijaan, että vastaisit jotain väärin. Jos et tiedä vastausta kysymykseen, älä kerro väärää tietoa.' %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + ' [INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}