初始化项目，由ModelHub XC社区提供模型

Model: manucif/latamgpt-1b-sft
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.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

README.md

@@ -0,0 +1,76 @@
+---
+license: llama3.2
+base_model: meta-llama/Llama-3.2-1B
+language:
+- es
+- pt
+- en
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- sft
+- latam
+- llama
+- latam-gpt
+datasets:
+- latam-gpt/wikipedia-qa-iberoamerica-clean
+- latam-gpt/tulu-3-sft-mixture-no-identity-clean
+- latam-gpt/sft-mcqa-unified-clean
+- latam-gpt/self-identity-v3-clean
+- latam-gpt/copuchatV2-clean
+---
+
+# latamgpt-1b-sft
+
+Full supervised fine-tune of `meta-llama/Llama-3.2-1B` on a Latin American instruction mixture, with sequence packing and assistant-only loss masking.
+
+## Training data
+
+| Dataset | Role |
+|---|---|
+| `latam-gpt/wikipedia-qa-iberoamerica-clean` | Iberoamerican QA |
+| `latam-gpt/tulu-3-sft-mixture-no-identity-clean` | General SFT mixture |
+| `latam-gpt/sft-mcqa-unified-clean` | Multiple-choice QA |
+| `latam-gpt/self-identity-v3-clean` | Self-identity |
+| `latam-gpt/copuchatV2-clean` | Chilean conversational |
+
+After tokenization with the Llama 3 chat template and FFD packing at 4096 tokens (99.16% packing efficiency), the training set is **175,995 packed sequences (~721M tokens)** with **119,573 validation examples**.
+
+## Training setup
+
+- **Base model:** `meta-llama/Llama-3.2-1B`
+- **Method:** Full fine-tune (no LoRA)
+- **Sequence length:** 4096, packed with assistant-only loss masking
+- **Epochs:** 2
+- **Learning rate:** 1e-5 (cosine, 3% warmup)
+- **Batch:** 8 per device × 8 grad accumulation × 2 GPUs = **128 effective**
+- **Precision:** bf16 + DeepSpeed ZeRO-2 + gradient checkpointing + Flash Attention 2
+- **Hardware:** 2× H100 80GB
+- **Wall time:** ~7.5h
+
+## Results
+
+| Metric | Value |
+|---|---|
+| `train_loss` | 0.8579 |
+| `eval_loss` | 0.8910 |
+| `epoch` | 2.0 |
+| `train_samples` | 175,995 |
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tok = AutoTokenizer.from_pretrained("latam-gpt/latamgpt-1b-sft")
+model = AutoModelForCausalLM.from_pretrained("latam-gpt/latamgpt-1b-sft", torch_dtype="bfloat16", device_map="auto")
+
+messages = [{"role": "user", "content": "¿Cuál es la capital de Chile?"}]
+inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
+out = model.generate(inputs, max_new_tokens=256, do_sample=True, temperature=0.7)
+print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))
+```
+
+## License
+
+Inherits the [Llama 3.2 Community License](https://www.llama.com/llama3_2/license/) from the base model.

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.890963077545166,
+    "eval_runtime": 1952.8654,
+    "eval_samples_per_second": 61.23,
+    "eval_steps_per_second": 7.654,
+    "total_flos": 8.418445674676224e+18,
+    "train_loss": 0.8579012258703058,
+    "train_runtime": 27047.1098,
+    "train_samples": 175995,
+    "train_samples_per_second": 13.014,
+    "train_steps_per_second": 0.102
+}

chat_template.jinja

@@ -0,0 +1,5 @@
+{% for message in messages %}{% if loop.index0 == 0 %}{{ bos_token }}{% endif %}<|start_header_id|>{{ message['role'] }}<|end_header_id|>
+
+{% if message['role'] == 'assistant' %}{% generation %}{{ message['content'] | trim }}<|eot_id|>{% endgeneration %}{% else %}{{ message['content'] | trim }}<|eot_id|>{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
+' }}{% endif %}

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128001,
+  "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": 128001,
+  "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,
+  "transformers_version": "4.57.6",
+  "use_cache": false,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.890963077545166,
+    "eval_runtime": 1952.8654,
+    "eval_samples_per_second": 61.23,
+    "eval_steps_per_second": 7.654
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001
+  ],
+  "pad_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.57.6"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31adb65c631f8a9b1aceae03ef4e63e6c31d1ee636f202dd5c0df3cd5e39d229
+size 2996982344

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": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 8.418445674676224e+18,
+    "train_loss": 0.8579012258703058,
+    "train_runtime": 27047.1098,
+    "train_samples": 175995,
+    "train_samples_per_second": 13.014,
+    "train_steps_per_second": 0.102
+}