初始化项目，由ModelHub XC社区提供模型

Model: brunopio/Llama3-8B-1.58-100B-tokens-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,38 @@
+*.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
+Llama3-8B-1.58-100B-tokens-TQ1_0-F16.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3-8B-1.58-100B-tokens-TQ1_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3-8B-1.58-100B-tokens-TQ2_0.gguf filter=lfs diff=lfs merge=lfs -text

Llama3-8B-1.58-100B-tokens-TQ1_0-F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28a00bf187438010b20907220da068d76cf77821e6c516e7547964def1838566
+size 3582448384

Llama3-8B-1.58-100B-tokens-TQ1_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83282fd9a6871536d773758d8c9b7d54f299122405a0f4a396e6bd60c581d337
+size 2207544064

Llama3-8B-1.58-100B-tokens-TQ2_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2565559c82a1d03ecd1101f536c5e99418d07e55a88bd5e391ed734f6b3989ac
+size 2534699776

README.md

@@ -0,0 +1,53 @@
+---
+library_name: transformers
+base_model:
+- meta-llama/Meta-Llama-3-8B-Instruct
+- HF1BitLLM/Llama3-8B-1.58-100B-tokens
+---
+
+# Model Card for Model ID
+
+### Llama3-8B-1.58 Models
+
+This model was converted to GGUF format from [HF1BitLLM/Llama3-8B-1.58-100B-tokens](https://huggingface.co/HF1BitLLM/Llama3-8B-1.58-100B-tokens) using llama.cpp.
+
+
+## Use with llama.cpp
+Install llama.cpp through brew (works on Mac and Linux)
+
+```bash
+brew install llama.cpp
+
+```
+Invoke the llama.cpp server or the CLI.
+
+### CLI:
+```bash
+llama-cli --hf-repo brunopio/Llama3-8B-1.58-100B-tokens-GGUF --hf-file Llama3-8B-1.58-100B-tokens-GGUF -p "The meaning to life and the universe is"
+```
+
+### Server:
+```bash
+llama-server --hf-repo brunopio/Llama3-8B-1.58-100B-tokens-GGUF --hf-file Llama3-8B-1.58-100B-tokens-GGUF -c 2048
+```
+
+Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
+
+Step 1: Clone llama.cpp from GitHub.
+```
+git clone https://github.com/ggerganov/llama.cpp
+```
+
+Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
+```
+cd llama.cpp && LLAMA_CURL=1 make
+```
+
+Step 3: Run inference through the main binary.
+```
+./llama-cli --hf-repo brunopio/Llama3-8B-1.58-100B-tokens-GGUF --hf-file Llama3-8B-1.58-100B-tokens-GGUF -p "The meaning to life and the universe is"
+```
+or 
+```
+./llama-server --hf-repo brunopio/Llama3-8B-1.58-100B-tokens-GGUF --hf-file Llama3-8B-1.58-100B-tokens-GGUF -c 2048
+```

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "/fsx/mohamed/scripts_training/quantized_model_llama_8B_10",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "is_bitnet_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "modules_to_not_convert": null,
+    "quant_method": "bitnet"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256,
+  "quantization_config": {
+    "quant_method": "bitnet"
+  }
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "transformers_version": "4.44.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdde078a512acfc44cdc36b665c452bfcf230605e6f6a9a9ecdaa3e234cd8c5d
+size 3846768552