Upload folder using huggingface_hub

README.md

@@ -0,0 +1,84 @@
+---
+base_model:
+- mistralai/Mistral-7B-v0.3
+datasets:
+- wikimedia/wikipedia
+- FreedomIntelligence/alpaca-gpt4-arabic
+language:
+- ar
+- en
+license: apache-2.0
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- mistral
+- trl
+---
+
+Experimenting with pre-training Arabic language + finetuning on instructions using the quantized model `mistralai/Mistral-7B-v0.3` from `unsloth`. First time trying pre-training, expect issues and low quality outputs. The repo contains the merged, quantized model and GGUF format.
+
+### Example usage
+
+#### llama-cpp-python
+
+```python
+from llama_cpp import Llama
+
+inference_prompt = """فيما يلي تعليمات تصف مهمة. اكتب استجابة تكمل الطلب بشكل مناسب.
+
+### تعليمات:
+{}
+
+### إجابة:
+"""
+
+llm = Llama.from_pretrained(
+	repo_id="nazimali/mistral-7b-v0.3-instruct-arabic",
+	filename="gguf/Q4_K_M.gguf",
+)
+
+llm.create_chat_completion(
+	messages = [
+		{
+			"role": "user",
+			"content": inference_prompt.format("السلام عليكم، هيا نموء")
+		}
+	]
+)
+```
+
+#### llama.cpp
+
+```shell
+./llama-cli \
+  --hf-repo "nazimali/mistral-7b-v0.3-instruct-arabic" \
+  --hf-file gguf/Q4_K_M.gguf \
+  -p "السلام عليكم، هيا نموء" \
+  --conversation
+```
+
+### Training
+
+#### Pre-training data:
+
+- `wikimedia/wikipedia`
+- `20231101.ar`
+- Used 6,096 rows, 0.05% of the total data
+
+#### Finetuning data:
+
+- `FreedomIntelligence/alpaca-gpt4-arabic`
+- Used 49,969 rows, 100% of all the data
+
+#### Finetuning instruction format:
+
+```python
+finetune_prompt = """فيما يلي تعليمات تصف مهمة. اكتب استجابة تكمل الطلب بشكل مناسب.
+
+### تعليمات:
+{}
+
+### إجابة:
+"""
+```

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "unsloth/mistral-7b-v0.3-bnb-4bit",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "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,
+  "pad_token_id": 770,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.45.0",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 32768,
+  "pad_token_id": 770,
+  "transformers_version": "4.45.0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3c5d6ad99e755a61f5e7b651e2d28baa5a441be87bd1774dc2171abe4b2250
+size 1978231989

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2192f79a6a31651ef12609244d15226594123cf7a75455fa56ba5cce7d849d86
+size 1891601745

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:135f10d914b4d44036fb7fd159a6e91e65e7be916d0c5cc30456a3ba752184fd
+size 268435584

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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404