Quant for 3.0

README.md

@@ -1,43 +1,21 @@
 ---
-license: apache-2.0
-datasets:
-- cerebras/SlimPajama-627B
-- bigcode/starcoderdata
-- OpenAssistant/oasst_top1_2023-08-25
-language:
-- en
 quantized_by: bartowski
-pipeline_tag: text-generation
 ---
 
-## Exllama v2 Quantizations of TinyLlama-1.1B-Chat-v1.0
+# Exllama v2 Quantizations of TinyLlama-1.1B-Chat-v1.0 at 3.0 bits per weight
 
 Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.11">turboderp's ExLlamaV2 v0.0.11</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 the default 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-Chat-v1.0
- 
-<a href="https://huggingface.co/bartowski/TinyLlama-1.1B-Chat-v1.0-exl2/tree/3_5">3.5 bits per weight</a>
- 
-<a href="https://huggingface.co/bartowski/TinyLlama-1.1B-Chat-v1.0-exl2/tree/4_0">4.0 bits per weight</a>
- 
-<a href="https://huggingface.co/bartowski/TinyLlama-1.1B-Chat-v1.0-exl2/tree/5_0">5.0 bits per weight</a>
- 
-<a href="https://huggingface.co/bartowski/TinyLlama-1.1B-Chat-v1.0-exl2/tree/6_5">6.5 bits per weight</a>
- 
-<a href="https://huggingface.co/bartowski/TinyLlama-1.1B-Chat-v1.0-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-Chat-v1.0-exl2
+git clone --single-branch --branch 3.0 https://huggingface.co/bartowski/TinyLlama-1.1B-Chat-v1.0-exl2
 ```
 
 With huggingface hub (credit to TheBloke for instructions):
@@ -46,16 +24,9 @@ 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-Chat-v1.0-exl2`:
-
-```shell
-mkdir TinyLlama-1.1B-Chat-v1.0-exl2
-huggingface-cli download bartowski/TinyLlama-1.1B-Chat-v1.0-exl2 --local-dir TinyLlama-1.1B-Chat-v1.0-exl2 --local-dir-use-symlinks False
-```
-
 To download from a different branch, add the `--revision` parameter:
 
 ```shell
 mkdir TinyLlama-1.1B-Chat-v1.0-exl2
-huggingface-cli download bartowski/TinyLlama-1.1B-Chat-v1.0-exl2 --revision 4_0 --local-dir TinyLlama-1.1B-Chat-v1.0-exl2 --local-dir-use-symlinks False
+huggingface-cli download bartowski/TinyLlama-1.1B-Chat-v1.0-exl2 --revision 3_0 --local-dir TinyLlama-1.1B-Chat-v1.0-exl2 --local-dir-use-symlinks False
 ```

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "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,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_logits/chosen": -2.707406759262085,
+    "eval_logits/rejected": -2.656524419784546,
+    "eval_logps/chosen": -370.1297607421875,
+    "eval_logps/rejected": -296.0738525390625,
+    "eval_loss": 0.513750433921814,
+    "eval_rewards/accuracies": 0.738095223903656,
+    "eval_rewards/chosen": -0.02744222804903984,
+    "eval_rewards/margins": 1.0087225437164307,
+    "eval_rewards/rejected": -1.03616464138031,
+    "eval_runtime": 93.5908,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 21.37,
+    "eval_steps_per_second": 0.673
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.0"
+}

original_repo_url.txt

@@ -0,0 +1 @@
+https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0

output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fff80b2e5085fd742ea96969c4d22875cc4e2546e5b9a4758acb074497a7d92d
+size 548685216

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_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_config.json

@@ -0,0 +1,40 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}