初始化项目，由ModelHub XC社区提供模型

Model: Ryder99/Llama-3.2-1B-Instruct-Hindi
Source: Original Platform

.gitattributes

@@ -0,0 +1,40 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+unsloth.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.F16.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+unsloth.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,40 @@
+---
+base_model: unsloth/Llama-3.2-1B-Instruct-unsloth-bnb-4bit
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- llama
+- trl
+- sft
+license: apache-2.0
+language:
+- en
+- hi
+---
+
+# Uploaded  model
+
+- **Developed by:** Ryder99
+- **License:** apache-2.0
+- **Finetuned from model :** unsloth/Llama-3.2-1B-Instruct-unsloth-bnb-4bit
+
+---
+
+This model was created as part of a project for my NLP course at University. I'm limited to what free Colab can handle, but I'm satisfied with the performance
+of this model considering the small size. With some preliminary testing, it appears to be slightly faster than the base Meta Llama 3.2 1B, while producing significantly
+better Hindi output and comparable English output. The model appears to prefer outputting Hindi regardless of prompt language if there is any Hindi in the context.
+
+I intend to do some better testing in the future, but until then this model is provided as is for you to try. It might be convenient to use Google Translate or some
+similar service to write the prompt in Devnagari and translate the output back to English for quick testing if, like me, Hindi is not your first language and you
+struggle to read it. The model seems viable as an on-device model for Hindi-speakers, with usable inference speeds even on a phone (tested using Ollama on Termux).
+
+A slightly bigger model can be found at [Llama-3.2-3B-Instruct-Hindi](https://huggingface.co/Ryder99/Llama-3.2-3B-Instruct-Hindi).
+
+For queries, or to help me train larger models ( ...I couldn't get lab access :( ... ) you can mail me [here](mailto:kanishka_chakraborty@outlook.com).
+
+---
+
+This llama 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)

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "unsloth/Llama-3.2-1B-Instruct-unsloth-bnb-4bit",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128004,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.48.3",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.3.9",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "max_length": 131072,
+  "pad_token_id": 128004,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.48.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edae6d0645929aa4b18fe305c21c241c5b290ea3cbce2cdb192254c498ed461f
+size 2996982200

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55639fba89252d86b3dbd34e26575ae68a634e467f80c7c4598ca8cfe5ea4c86
+size 2997014998

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unsloth.F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb1a5f69a1ba8b3ad2965f98d22c87139416432761fa4dcbe86ba8262e633e20
+size 3004931872

unsloth.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d08c1191a70fcb0b53893f270af6a1ff139bd6d31c9135c7a399ce6a06bb2a40
+size 955445024

unsloth.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ee741ec5d1398e21d1df79383ad00df305d1b61dda350f5e6f10d7bd0f62bb0
+size 1092087584

unsloth.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93999fedc6550162e3d6bb84d26e6579b6e1ac5e592e40c8bb1fe31c61e3f9b8
+size 1600167712