Quant for 6.0

README.md

@@ -6,29 +6,22 @@ datasets:
 language:
 - en
 quantized_by: bartowski
-pipeline_tag: text-generation
 ---
 
-## Exllama v2 Quantizations of TinyLlama-1.1B-intermediate-step-955k-token-2T
+# Exllama v2 Quantizations of TinyLlama-1.1B-intermediate-step-955k-token-2T at 6.0 bits per weight
 
 Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.8">turboderp's ExLlamaV2 v0.0.8</a> for quantization.
 
-Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
-
 Conversion was done using wikitext-103-raw-v1-test.parquet as calibration dataset.
 
-Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.
-
 Original model: https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T
- 
-<a href="https://huggingface.co/bartowski/TinyLlama-1.1B-intermediate-step-955k-token-2T-exl2/tree/8_0">8.0 bits per weight</a>
 
 ## Download instructions
 
 With git:
 
 ```shell
-git clone --single-branch --branch 4_0 https://huggingface.co/bartowski/TinyLlama-1.1B-intermediate-step-955k-token-2T-exl2
+git clone --single-branch --branch 6.0 https://huggingface.co/bartowski/TinyLlama-1.1B-intermediate-step-955k-token-2T-exl2
 ```
 
 With huggingface hub (credit to TheBloke for instructions):
@@ -37,16 +30,9 @@ With huggingface hub (credit to TheBloke for instructions):
 pip3 install huggingface-hub
 ```
 
-To download the `main` (only useful if you only care about measurement.json) branch to a folder called `TinyLlama-1.1B-intermediate-step-955k-token-2T-exl2`:
-
-```shell
-mkdir TinyLlama-1.1B-intermediate-step-955k-token-2T-exl2
-huggingface-cli download bartowski/TinyLlama-1.1B-intermediate-step-955k-token-2T-exl2 --local-dir TinyLlama-1.1B-intermediate-step-955k-token-2T-exl2 --local-dir-use-symlinks False
-```
-
 To download from a different branch, add the `--revision` parameter:
 
 ```shell
 mkdir TinyLlama-1.1B-intermediate-step-955k-token-2T-exl2
-huggingface-cli download bartowski/TinyLlama-1.1B-intermediate-step-955k-token-2T-exl2 --revision 4_0 --local-dir TinyLlama-1.1B-intermediate-step-955k-token-2T-exl2 --local-dir-use-symlinks False
+huggingface-cli download bartowski/TinyLlama-1.1B-intermediate-step-955k-token-2T-exl2 --revision 6_0 --local-dir TinyLlama-1.1B-intermediate-step-955k-token-2T-exl2 --local-dir-use-symlinks False
 ```

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "max_length": 2048,
+  "transformers_version": "4.31.0.dev0"
+}

output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:433b529fb935ec83bcde53e0d88389216f616ad49cf22f8188fb965107a7d283
+size 911711656

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "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 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}