update

LLaMa-65B-GPTQ4bit.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38adc50b9fef306016f635688d64d287a54b1d36ae5d08a12285e23c3cc11c8b
+size 33471316664

README.md

@@ -0,0 +1,47 @@
+---
+license: other
+inference: false
+tags:
+- GPTQ
+- 3-bit
+- quantized
+---
+# LLaMa 65B 3bit GPTQ
+
+This is a GPTQ format quantised 3-bit model of LLaMa 65B.
+
+It is the result of quantising to 3-bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
+
+## How to easily download and use this model in text-generation-webui
+
+Open the text-generation-webui UI as normal.
+
+1. Click the **Model tab**.
+2. Under **Download custom model or LoRA**, enter `TheBloke/LLaMa-65B-GPTQ-3bit`.
+3. Click **Download**.
+4. Wait until it says it's finished downloading.
+5. Click the **Refresh** icon next to **Model** in the top left.
+6. In the **Model drop-down**: choose the model you just downloaded, `LLaMa-65B-GPTQ-3bit`.
+7. If you see an error in the bottom right, ignore it - it's temporary.
+8. Fill out the `GPTQ parameters` on the right: `Bits = 3`, `Groupsize = None`, `model_type = Llama`
+9. Click **Save settings for this model** in the top right.
+10. Click **Reload the Model** in the top right.
+11. Once it says it's loaded, click the **Text Generation tab** and enter a prompt!
+
+## Provided files
+
+**Compatible file - LLaMa-65B-GPTQ-3bit.safetensors**
+
+This will work with all versions of GPTQ-for-LLaMa. It has maximum compatibility
+
+It was created with the `--act-order` parameter to maximise inference quality, and with group_size = None to minmise VRAM requirements.
+
+* `Wizard-Vicuna-13B-Uncensored-GPTQ-4bit-128g.compat.no-act-order.safetensors`
+  * Works with all versions of GPTQ-for-LLaMa code, both Triton and CUDA branches
+  * Works with AutoGPTQ.
+  * Works with text-generation-webui one-click-installers
+  * Parameters: Groupsize = None. act-order.
+  * Command used to create the GPTQ:
+    ```
+    python llama.py /workspace/models/huggyllama_llama-65b wikitext2 --wbits 3 --true-sequential --act-order   --save_safetensors /workspace/llama-3bit/LLaMa-65B-GPTQ-3bit.safetensors
+    ```

config.json

@@ -0,0 +1,22 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 22016,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.0.dev0"
+}

quantize_config.json

@@ -0,0 +1,8 @@
+{
+  "bits": 3,
+  "group_size": -1,
+  "damp_percent": 0.01,
+  "desc_act": true,
+  "sym": true,
+  "true_sequential": true
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}