initial commit

Signed-off-by: José Carlos García <[email protected]>

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+*.gguf filter=lfs diff=lfs merge=lfs -text

Falcon3-7B-Base-1.58bit-q2b0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a88bf98369744d8be899485b2aab3b45618e79fea37031febcd58bbd1b6c9b7
+size 2220044864

README.md

@@ -0,0 +1,39 @@
+---
+library_name: transformers
+tags:
+- bitnet
+- falcon3
+base_model: tiiuae/Falcon3-7B-Base
+license: other
+license_name: falcon-llm-license
+license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
+---
+
+# Model Card for Falcon3-7B-Base-1.58bit-q2b0
+
+### Falcon3-7B-1.58 Models
+
+The **Falcon3-7B-1.58bit-q2b0** is a quantized version of **Falcon3-7B-Base**, leveraging the **q2b0 quantization method** from Candle. This enables extreme compression while maintaining strong performance across various NLP tasks.
+
+## Model Details
+
+### Model Sources
+
+- **Repository:** [tiiuae/Falcon3-7B-Base](https://huggingface.co/tiiuae/Falcon3-7B-Base)
+- **Quantization PR:** [Candle q2b0 Quantization](https://github.com/huggingface/candle/pull/2683)
+
+## Quantization Details
+
+The model has been quantized using the **q2b0** method from Candle. This approach reduces model size significantly while preserving performance. For more details on this quantization technique, refer to the [Candle PR #2683](https://github.com/huggingface/candle/pull/2683).
+
+## Training Details
+
+For details on the dataset and training process, refer to the original [Falcon3-7B-Base repository](https://huggingface.co/tiiuae/Falcon3-7B-Base).
+
+## License
+
+This model is licensed under the [Falcon LLM License](https://falconllm.tii.ae/falcon-terms-and-conditions.html).
+
+---
+
+For additional information or questions, please refer to the main [Falcon3-7B-Base repository](https://huggingface.co/tiiuae/Falcon3-7B-Base).

config.json

@@ -0,0 +1,38 @@
+{
+  "activation": "swiglu",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 23040,
+  "is_bitnet_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "parallel_attn": false,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "modules_to_not_convert": [
+      "lm_head"
+    ],
+    "quant_method": "bitnet"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000042,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0.dev0",
+  "use_cache": true,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "transformers_version": "4.46.0.dev0"
+}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>EMAIL_ADDRESS<<",
+    ">>IP_ADDRESS<<",
+    "<|startoftext|>",
+    ">>IP_ADDRESS_0<<",
+    ">>IP_ADDRESS_1<<",
+    ">>IP_ADDRESS_2<<",
+    ">>IP_ADDRESS_3<<",
+    ">>IP_ADDRESS_4<<",
+    ">>IP_ADDRESS_5<<",
+    ">>IP_ADDRESS_6<<",
+    ">>IP_ADDRESS_7<<",
+    ">>IP_ADDRESS_8<<",
+    ">>IP_ADDRESS_9<<",
+    ">>PASSWORD<<",
+    ">>KEY<<"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}