Delete folder gemma-3-1b-it-int8-v1 with huggingface_hub

gemma-3-1b-it-int8-v1/README.md

@@ -1,48 +0,0 @@
----
-library_name: cellm
-tags:
-- mobile
-- rust
-- memory-efficient
-- quantized
-- gemma
----
-
-# Gemma 3 1B IT (Cellm Int8)
-
-This folder contains a Cellm-converted Gemma 3 1B Instruct model and tokenizer assets, ready for publishing to Hugging Face.
-
-## Files
-- `gemma-3-1b-it-int8-v1.cellm`
-- `tokenizer.json`
-- `tokenizer_config.json`
-- `chat_template.jinja`
-
-## Model Details
-- **Base model**: `google/gemma-3-1b-it`
-- **Format**: `.cellm`
-- **Quantization**: INT8 symmetric weight-only
-- **Size**: ~1.2 GB
-
-## Inference Check (cellm)
-
-```bash
-cd /Users/jeff/Desktop/cellm
-./target/release/infer \
-  --model models/to-huggingface/gemma-3-1b-it-int8-v1/gemma-3-1b-it-int8-v1.cellm \
-  --tokenizer models/to-huggingface/gemma-3-1b-it-int8-v1/tokenizer.json \
-  --prompt "what's twitch.com?" \
-  --chat \
-  --chat-format plain \
-  --gen 48 \
-  --temperature 0 \
-  --backend cpu \
-  --kv-encoding f16
-```
-
-## Notes
-- This INT8 variant produced coherent output in local validation.
-- INT4 variant was smaller (~481 MB) but quality was significantly worse.
-
-## License
-Subject to Gemma terms and upstream license constraints.

gemma-3-1b-it-int8-v1/chat_template.jinja

@@ -1,47 +0,0 @@
-{{ bos_token }}
-{%- if messages[0]['role'] == 'system' -%}
-    {%- if messages[0]['content'] is string -%}
-        {%- set first_user_prefix = messages[0]['content'] + '
-
-' -%}
-    {%- else -%}
-        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
-
-' -%}
-    {%- endif -%}
-    {%- set loop_messages = messages[1:] -%}
-{%- else -%}
-    {%- set first_user_prefix = "" -%}
-    {%- set loop_messages = messages -%}
-{%- endif -%}
-{%- for message in loop_messages -%}
-    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
-        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
-    {%- endif -%}
-    {%- if (message['role'] == 'assistant') -%}
-        {%- set role = "model" -%}
-    {%- else -%}
-        {%- set role = message['role'] -%}
-    {%- endif -%}
-    {{ '<start_of_turn>' + role + '
-' + (first_user_prefix if loop.first else "") }}
-    {%- if message['content'] is string -%}
-        {{ message['content'] | trim }}
-    {%- elif message['content'] is iterable -%}
-        {%- for item in message['content'] -%}
-            {%- if item['type'] == 'image' -%}
-                {{ '<start_of_image>' }}
-            {%- elif item['type'] == 'text' -%}
-                {{ item['text'] | trim }}
-            {%- endif -%}
-        {%- endfor -%}
-    {%- else -%}
-        {{ raise_exception("Invalid content type") }}
-    {%- endif -%}
-    {{ '<end_of_turn>
-' }}
-{%- endfor -%}
-{%- if add_generation_prompt -%}
-    {{'<start_of_turn>model
-'}}
-{%- endif -%}

gemma-3-1b-it-int8-v1/gemma-3-1b-it-int8-v1.cellm

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:73cc1fe14164fc1ac208c7c86ead0f1a56d07375f0da52461c282f954ec623d8
-size 1302993856

gemma-3-1b-it-int8-v1/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
-size 33384568