Add model

README.md

@@ -1,3 +1,43 @@
 ---
+library_name: peft
 license: apache-2.0
 ---
+# minihf_evaluator_mistral_7b_v0.1
+
+`minihf_evaluator_mistral_7b_v0.1` is a LoRA instruct fine-tune of [Mistral 7B](https://huggingface.co/mistralai/Mistral-7B-v0.1).
+
+The sequence `<|end|>` was used to separate the prompt and response. The correct way to prompt the model is: `Does 2 + 2 = 4?<|end|>`. The tokenizer will prepend a BOS token (`<s>`) by default. The response will end with an EOS token (`</s>`).
+
+## Training procedure
+
+`minihf_evaluator_mistral_7b_v0.1` was fine-tuned for 100,000 examples on 90% [Muennighoff/flan](https://huggingface.co/datasets/Muennighoff/flan) / 10% [databricks/databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) using batch size 4 per GPU on 8 80GB H100 GPUs. Examples where the prompt and response would not fit into 4096 tokens were dropped. The fine-tuning was done using the following command:
+
+```bash
+accelerate launch sft_evaluator.py --output-dir minihf_evaluator_mistral_7b_v0.1
+```
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+- PEFT 0.5.0
+- PEFT 0.5.0
+- PEFT 0.5.0
+- PEFT 0.5.0
+- PEFT 0.5.0
+- PEFT 0.5.0
+- PEFT 0.5.0
+- PEFT 0.5.0
+- PEFT 0.5.0
+
+- PEFT 0.5.0

adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "auto_mapping": {
+    "base_model_class": "MistralForCausalLM",
+    "parent_library": "transformers.models.mistral.modeling_mistral"
+  },
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 8,
+  "lora_dropout": 0.0,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "revision": null,
+  "target_modules": [
+    "self_attn.q_proj",
+    "self_attn.k_proj",
+    "self_attn.v_proj",
+    "self_attn.o_proj",
+    "mlp.gate_proj",
+    "mlp.up_proj",
+    "mlp.down_proj",
+    "lm_head"
+  ],
+  "task_type": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5b41c3b7ab4216b02d1322b62caa099df7ee319197560b9099f6beefe2d98ca
+size 340225224

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "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 +1,40 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}