Upload 11 files

README.md

@@ -0,0 +1,47 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- mistral
+- trl
+- sft
+base_model: augmxnt/shisa-base-7b-v1
+datasets:
+- NilanE/ParallelFiction-Ja_En-100k
+- mpasila/ParallelFiction-Ja_En-100k-alpaca
+---
+This is an ExLlamaV2 quantized model in 4bpw of [mpasila/JP-EN-Translator-2K-steps-7B](https://huggingface.co/mpasila/JP-EN-Translator-2K-steps-7B) using the default calibration dataset.
+
+# Original Model card
+
+Experimental model, may not perform that well. Dataset used is [a modified](https://huggingface.co/datasets/mpasila/ParallelFiction-Ja_En-100k-alpaca) version of [NilanE/ParallelFiction-Ja_En-100k](https://huggingface.co/datasets/NilanE/ParallelFiction-Ja_En-100k).
+
+After training with an 8k context length it didn't appear to improve performance much at all. Not sure if I should keep training it (which is costly) or if I should fix some issues with the dataset (like it starting with Ch or Chapter) or I go back to finetuning Finnish models.
+
+### Prompt format: Alpaca
+```
+Below is a translation task, paired with an input that provides further context. Write a response that appropriately completes the request.
+
+### Instruction:
+{}
+
+### Input:
+{}
+
+### Response:
+{}
+```
+
+# Uploaded  model
+
+- **Developed by:** mpasila
+- **License:** apache-2.0
+- **Finetuned from model :** augmxnt/shisa-base-7b-v1
+
+This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|extra_idx|>": 120073
+}

config.json

@@ -0,0 +1,38 @@
+{
+    "_name_or_path": "augmxnt/shisa-base-7b-v1",
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 10000.0,
+    "sliding_window": 4096,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.39.1",
+    "unsloth_version": "2024.3",
+    "use_cache": false,
+    "vocab_size": 120074,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.0.16",
+        "bits": 4.0,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.39.1",
+  "use_cache": false
+}

output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8416b8dbddb0d8ba1caf9982856888e5e60fd4e7c7ba0db2c1b3b9196615cae2
+size 4863827040

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": "<unk>",
+    "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "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
+    },
+    "120073": {
+      "content": "<|extra_idx|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 32768,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}